def kalman_predict_out_line(track, line, out_direction, predict_long=None):
# print(track.track_id)
# print(line)
# print(out_direction)
# print(track.tlbr)
if box_line_relative(track.tlbr, line) == out_direction:
return 0
predict_num_out = 0
prev_mean, prev_cov = track.mean, track.covariance
kal_man = KalmanFilter()
predict_thres = 15 if out_direction == 'up' else 0
if predict_long is not None:
max_long_predict = predict_long
else:
max_long_predict = 50 if out_direction == 'up' else 4
while box_line_relative(mean_to_tlbr(prev_mean), line) != out_direction:
predict_num_out += 1
cur_mean = prev_mean #of t
mean, cov = kal_man.predict(prev_mean, prev_cov)
if predict_num_out > predict_thres:
new_mean, new_cov = mean, cov
else:
new_mean, new_cov = kal_man.update(prev_mean, prev_cov, mean[:4])
prev_mean, prev_cov = new_mean, new_cov #of t+1
if predict_num_out >= max_long_predict or np.sum(
np.abs(cur_mean - mean)) == 0:
break
# print(mean_to_tlbr(mean))
return predict_num_out
def kalman_predict_out_line(track,line,out_direction):
# print(track.track_id)
# print(line)
# print(out_direction)
# print(track.tlbr)
if box_line_relative(track.tlbr,line)==out_direction:
return 0
predict_num_out=0
prev_mean,prev_cov=track.mean,track.covariance
kal_man=KalmanFilter()
predict_thres=0 if out_direction=='up' else 0
max_long_predict=5 if out_direction=='up' else 2 if track.infer_type() in ['person','motorcycle','biycycle'] else 8
while box_line_relative(mean_to_tlbr(prev_mean),line) !=out_direction:
predict_num_out+=1
cur_mean=prev_mean #of t
mean,cov=kal_man.predict(prev_mean,prev_cov)
if predict_num_out>predict_thres:
new_mean,new_cov=mean,cov
else:
new_mean,new_cov= kal_man.update(prev_mean,prev_cov,mean[:4])
prev_mean,prev_cov=new_mean,new_cov #of t+1
if predict_num_out>=max_long_predict or np.sum(np.abs(cur_mean-mean))==0:
break
# print(mean_to_tlbr(mean))
return predict_num_out
def __init__(self, opt, frame_rate=30): # 帧率的意义
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv) # 加载模型，
self.model = load_model(self.model, opt.load_model)
self.model = self.model.to(opt.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack] # 保存一系列追踪中的轨迹
self.lost_stracks = [] # type: list[STrack] # 保存已经丢失的轨迹
self.removed_stracks = [] # type: list[STrack] # 保存已经移除的轨迹
self.frame_id = 0
self.det_thresh = opt.conf_thres # 检测框阈值，这里设置为与tracking的置信度阈值相同
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer) # 还是等于输入视频的真实帧率
self.max_time_lost = self.buffer_size # 最大连续self.buffer_size次没有匹配到目标时，表示该轨迹丢失
self.max_per_image = 128
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter() # 预测，根据上一帧目标的检测位置和速度，预测当前帧目标的检测位置和速度
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv)
self.model = load_model(self.model, opt.load_model)
self.model = self.model.to(opt.device)
self.model.eval()
# input = torch.randn(1, 3, 640, 640, requires_grad=True)
# input=input.to(opt.device)
# out = self.model(input)
# torch.onnx.export(self.model, # model being run
# input, # model input (or a tuple for multiple inputs)
# "./test.onnx", # where to save the model (can be a file or file-like object)
# export_params=True, # store the trained parameter weights inside the model file# )
# opset_version=9
# )
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv)
self.model = load_model(self.model, opt.load_model)
self.model = self.model.to(opt.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
self.roi_align = RoIAlign(7, 7)
cfg = get_config()
cfg.merge_from_file(
"/home/hongwei/track-human/FairMOT/src/lib/tracker/deep_configs/yolov3.yaml"
)
cfg.merge_from_file(
"/home/hongwei/track-human/FairMOT/src/lib/tracker/deep_configs/deep_sort.yaml"
)
self.detector = build_detector(cfg, True)
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv)
self.model = load_model(self.model, opt.load_model)
self.model = self.model.to(opt.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = 128
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv)
self.model = load_model(self.model, opt.load_model)
self.model = self.model.to(opt.device)
self.model.eval()
# convert to onnx
# input_names = ["input0"]
# output_names = ["hm", "wh", "id", "reg"]
# inputs = torch.randn(1, 3, 480, 640).to('cpu')
# torch_out = torch.onnx._export(self.model, inputs, 'pruned.onnx', export_params=True, verbose=False,
# input_names=input_names, output_names=output_names)
# print("export onnx sucess")
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
self.model = create_model(opt.arch, opt.heads, opt.head_conv,
num_gnn_layers=opt.num_gnn_layers,
gnn_type=opt.gnn_type,
use_residual=opt.use_residual,
return_pre_gnn_layer_outputs=opt.return_pre_gnn_layer_outputs,
heads_share_params=opt.heads_share_params,
omit_gnn=opt.omit_gnn,
use_roi_align=opt.use_roi_align,
viz_attention=opt.viz_attention)
self.model = load_model(self.model, opt.load_model, distributed=True, copy_head_weights=False)
self.model = self.model.to(opt.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
# self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
self.viz_attention = opt.viz_attention
def __init__(self, opt, frame_rate=30):
self.opt = opt
if opt.use_hog_reid:
print('USE HOG AS FEATURE EXTRACTION !!!!')
self.re_im_h, self.re_im_w = 300, 120
cell_size = (50, 24)
block_size = (6, 5)
nbins = 9
self.reid_model = cv2.HOGDescriptor(
_winSize=(self.re_im_w // cell_size[1] * cell_size[1],
self.re_im_h // cell_size[0] * cell_size[0]),
_blockSize=(block_size[1] * cell_size[1],
block_size[0] * cell_size[0]),
_blockStride=(cell_size[1], cell_size[0]),
_cellSize=(cell_size[1], cell_size[0]),
_nbins=nbins)
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.prev_img = None
self.kalman_filter = KalmanFilter()
def reset(self):
"""
:return:
"""
# Reset tracks dict
self.tracked_tracks_dict = defaultdict(list) # value type: list[Track]
self.lost_tracks_dict = defaultdict(list) # value type: list[Track]
self.removed_tracks_dict = defaultdict(list) # value type: list[Track]
# Reset frame id
self.frame_id = 0
# Reset kalman filter to stabilize tracking
self.kalman_filter = KalmanFilter()
def __init__(self, opt):
self.opt = opt
# ---------- Init model
max_ids_dict = {
0: 330,
1: 102,
2: 104,
3: 312,
4: 53
} # cls_id -> track id number for traning
device = opt.device
# model in track mode(do detection and reid feature vector extraction)
self.model = Darknet(opt.cfg, opt.img_size, False, max_ids_dict, 128, 'track').to(device)
# Load checkpoint
if opt.weights.endswith('.pt'): # pytorch format
ckpt = torch.load(opt.weights, map_location=device)
self.model.load_state_dict(ckpt['model'])
if 'epoch' in ckpt.keys():
print('Checkpoint of epoch {} loaded.'.format(ckpt['epoch']))
else: # darknet format
load_darknet_weights(self.model, opt.weights)
# Put model to device and set eval mode
self.model.to(device).eval()
# ----------
# Define tracks dict
self.tracked_tracks_dict = defaultdict(list) # value type: list[Track]
self.lost_tracks_dict = defaultdict(list) # value type: list[Track]
self.removed_tracks_dict = defaultdict(list) # value type: list[Track]
# init frame index
self.frame_id = 0
# init hyp
self.det_thresh = opt.conf_thres
self.buffer_size = int(opt.track_buffer)
self.max_time_lost = self.buffer_size
# self.mean = np.array([0.408, 0.447, 0.470]).reshape(1, 1, 3)
# self.std = np.array([0.289, 0.274, 0.278]).reshape(1, 1, 3)
# init kalman filter(to stabilize tracking)
self.kalman_filter = KalmanFilter()
def __init__(self, opt, model, frame_rate=30):
self.opt = opt
print('Creating model...')
self.model = model
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.mean = np.array(opt.mean, dtype=np.float32).reshape(1, 1, 3)
self.std = np.array(opt.std, dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
def __init__(self, opt, frame_rate=30):
self.opt = opt
print('Creating model...')
self.model = create_model('dla_34', opt.heads, opt.head_conv)
if opt.multi_load_model != '':
self.model = load_model(self.model, opt.multi_load_model)
self.model = self.model.to(opt.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.kalman_filter = KalmanFilter()
def __init__(self, gpus, load_model_name, frame_rate=30):
# self.opt = opt
# if opt.gpus[0] >= 0:
# opt.device = torch.device('cuda')
# else:
# opt.device = torch.device('cpu')
if len(gpus) > 0:
self.device = torch.device('cuda')
else:
self.device = torch.device('cpu')
print('Creating model...')
heads = {'hm': 1, 'wh': 4, 'id': 128, 'reg': 2}
head_conv = 256
self.model = create_model(heads, head_conv)
self.model = load_model(self.model, load_model_name)
self.model = self.model.to(self.device)
self.model.eval()
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = 0.4
self.buffer_size = int(frame_rate / 30.0 * 30)
self.max_time_lost = self.buffer_size
self.max_per_image = 500
self.mean = np.array([0.408, 0.447, 0.47],
dtype=np.float32).reshape(1, 1, 3)
self.std = np.array([0.289, 0.274, 0.278],
dtype=np.float32).reshape(1, 1, 3)
self.kalman_filter = KalmanFilter()
self.num_classes = 1
self.down_ratio = 4
self.reg_offset = True
self.ltrb = True
self.K = 500
self.conf_thres = 0.4
class STrack(BaseTrack):
shared_kalman = KalmanFilter()
out_of_frame_patience = 5
num_cluster = 5
def __init__(self, tlwh, score, temp_feat, buffer_size=30):
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.tracklet_len = 0
self.smooth_feat = None
self.update_features(temp_feat, None)
self.alpha = 0.9
self.occlusion_status = False # use for bbox only
self.iou_box = None #use for bbox only
self.num_out_frame = 0
def update_features(self, feat, new_track):
feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
self.smooth_feat = self.alpha * self.smooth_feat + (
1 - self.alpha) * feat
self.smooth_feat /= np.linalg.norm(self.smooth_feat)
@staticmethod
def warp_predict(mean, cov, warp_matrix, warp_mode):
if warp_matrix is None:
return mean, cov
track_xyah = mean[:4]
track_tlwh = STrack.xyah_to_tlwh(track_xyah)
track_tlbr = STrack.tlwh_to_tlbr(track_tlwh)
t, l, b, r = track_tlbr
if warp_mode == cv2.MOTION_HOMOGRAPHY:
warp_tlbr = cv2.perspectiveTransform(np.array([[[t, l], [b, r]]]),
warp_matrix)[0].flatten()
else:
warp_tlbr = cv2.transform(np.array([[[t, l], [b, r]]]),
warp_matrix)[0].flatten()
warp_tlwh = STrack.tlbr_to_tlwh(warp_tlbr)
warp_xyah = STrack.tlwh_to_xyah(warp_tlwh)
track_mean, track_cov = list(warp_xyah) + list(mean[4:]), cov
return np.array(track_mean), track_cov
@staticmethod
def get_camera_intension(warp_matrix, warp_mode):
if warp_matrix is None:
return 0
warp_matrix_flattern = warp_matrix.flatten()
if warp_mode == cv2.MOTION_HOMOGRAPHY:
non_change_warp = np.array([1, 0, 0, 0, 1, 0, 0, 0, 1])
else:
non_change_warp = np.array([1, 0, 0, 0, 1, 0])
similarity = np.dot(warp_matrix_flattern, non_change_warp) / (
np.sqrt(np.sum(warp_matrix_flattern**2)) *
np.sqrt(np.sum(non_change_warp**2)))
return 1 - similarity
def predict(self, warp_matrix, warp_mode, smooth=0.0):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
motion_intensity = STrack.get_camera_intension(warp_matrix,
warp_mode) * smooth
self.mean, self.covariance = self.kalman_filter.predict(
mean_state, self.covariance, motion_intensity=motion_intensity)
self.mean, self.covariance = STrack.warp_predict(
self.mean, self.covariance, warp_matrix, warp_mode)
@staticmethod
def multi_predict(stracks, warp_matrix, warp_mode, smooth=0.0):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
motion_intensity = STrack.get_camera_intension(
warp_matrix, warp_mode) * smooth
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(
multi_mean,
multi_covariance,
motion_intensity=motion_intensity)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
stracks[i].mean, stracks[i].covariance = STrack.warp_predict(
stracks[i].mean, stracks[i].covariance, warp_matrix,
warp_mode)
def activate(self, kalman_filter, frame_id):
"""Start a new tracklet"""
self.kalman_filter = kalman_filter
self.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(
self.tlwh_to_xyah(self._tlwh))
self.tracklet_len = 0
self.state = TrackState.Tracked
#self.is_activated = True
self.frame_id = frame_id
self.start_frame = frame_id
# self.box_hist.append(self.tlwh)
# self.track_frames.append(frame_id)
def re_activate(self, new_track, frame_id, new_id=False):
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh))
self.update_features(new_track.curr_feat, new_track)
#self.update_cluster(new_track.curr_feat)
self.tracklet_len = 0
self.state = TrackState.Tracked
self.is_activated = True
self.frame_id = frame_id
if new_id:
self.track_id = self.next_id()
def update(self, new_track, frame_id, update_feature=True):
"""
Update a matched track
:type new_track: STrack
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id
self.tracklet_len += 1
new_tlwh = new_track.tlwh
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh))
self.state = TrackState.Tracked
self.is_activated = True
self.score = new_track.score
if update_feature:
self.update_features(new_track.curr_feat, new_track)
@property
# @jit(nopython=True)
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
# @jit(nopython=True)
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
@staticmethod
# @jit(nopython=True)
def xyah_to_tlwh(xyah):
w, h = xyah[2] * xyah[3], xyah[3]
x, y = xyah[0], xyah[1]
t, l = x - w / 2, y - h / 2
return [t, l, w, h]
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
# @jit(nopython=True)
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy()
ret[2:] -= ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame,
self.end_frame)
def __init__(self, opt,polygon, paths, polygon2=None,frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
self.input_size = input_sizes[opt.compound_coef]
if opt.detection_model=='Efficient' :
self.obj_list =['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', '', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', '', 'backpack', 'umbrella', '', '', 'handbag', 'tie',
'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
'skateboard', 'surfboard', 'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut',
'cake', 'chair', 'couch', 'potted plant', 'bed', '', 'dining table', '', '', 'toilet', '', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
'toothbrush']
self.person_or_motorcycle=['person']
self.obj_interest=[ 'motorcycle','bicycle', 'bus', 'truck','car'] if self.person_or_motorcycle[0]!='person' else [ 'person', 'bus', 'truck','car']
self.detetection_model= EfficientDetBackbone(compound_coef=opt.compound_coef, num_classes=len(self.obj_list),
ratios=anchor_ratios, scales=anchor_scales)
self.detetection_model.load_state_dict(torch.load(f'EfficientDet/weights/efficientdet-d{opt.compound_coef}.pth'))
self.detetection_model.eval()
device = torch.device('cuda:0')
self.detetection_model = self.detetection_model.to(device)
elif opt.detection_model=='FasterRcnn' :
config_file = "Drone_FasterRCNN/drone_demo/e2e_faster_rcnn_X_101_32x8d_FPN_1x_visdrone.yaml"
cfg.merge_from_file(config_file)
cfg.merge_from_list(["MODEL.WEIGHT", "Drone_FasterRCNN/drone_demo/visdrone_model_0360000.pth"])
self.detetection_model = COCODemo(
cfg,
min_image_size=opt.min_img_size,
confidence_threshold=opt.conf_thres,
)
label_of_interest=[
# "__background",
# "unused",
# "pedestrian",
# "person",
# "bicycle",
"car",
"van",
"truck",
# "tricycle",
# "awning-tricycle",
"bus",
"motor"
]
self.person_or_motorcycle=["motor"]
#'bicycle'
self.obj_interest=[ 'motor', 'bus', 'truck','car','van', "tricycle"] if self.person_or_motorcycle[0]!='person' else [ 'person', 'bus', 'truck','car','van', "tricycle"]
else:
raise('Not supported detector model')
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.kalman_filter = KalmanFilter()
self.polygon=polygon
self.paths=paths
self.polygon2=polygon2
self.line1=[polygon[0],polygon[1]]
self.line2=[polygon[1],polygon[2]]
self.line3=[polygon[2],polygon[3]]
self.line4=[polygon[0],polygon[4]]
self.two_polygon_system=True
self.warmup_frame=0
self.virtual_polygon= [
[
0,
680
],
[
0,
149
],
[
1270,
149
],
[
1270,
680
]
]
class STrack(BaseTrack):
shared_kalman = KalmanFilter()
out_of_frame_patience=5
num_cluster=5
type_infer_patience=4
score_infer_type_thres=0.6
def __init__(self, tlwh, score, vehicle_type, buffer_size=30,temp_feat=None,huge_vehicle=False):
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.tracklet_len = 0
self.smooth_feat = None
# self.update_features(temp_feat,None)
self.features = deque([], maxlen=buffer_size)
self.alpha = 0.6
self.num_out_frame=0
self.cluster_features={'centers':[],'cluster':[]}
self.track_frames=[]
self.w_hs=[]
self.occlusion_status=False # use for bbox only
self.iou_box=None #use for bbox only
self.box_hist=[]
self.vehicle_types_list=[]
self.vehicle_types_list.append(vehicle_type)
self.track_trajectory=[]
self.track_trajectory.append(self.tlwh_to_tlbr(tlwh))
self.huge_vehicle=huge_vehicle
def update_cluster(self,feat):
feat /= np.linalg.norm(feat)
if len(self.cluster_features['cluster'])<STrack.num_cluster:
self.cluster_features['cluster'].append([feat])
self.cluster_features['centers'].append(feat)
else:
min_center=np.argmin(np.squeeze(cdist(self.cluster_features['centers'], [feat], metric='cosine')))
self.cluster_features['cluster'][min_center].append(feat)
self.cluster_features['centers'][min_center]=np.mean(self.cluster_features['cluster'][min_center],axis=0)
self.cluster_features['centers']/=np.linalg.norm( self.cluster_features['centers'])
def update_features(self, feat,iou_box):
#feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
if iou_box==None: iou_box=0
update_param=(1-self.alpha)*iou_box+self.alpha
#self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat
self.smooth_feat = update_param * self.smooth_feat + (1 -update_param) * feat
self.box_hist.append(update_param)
self.features.append(feat)
#self.smooth_feat /= np.linalg.norm(self.smooth_feat)
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
@staticmethod
def multi_predict(stracks):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
def activate(self, kalman_filter, frame_id):
"""Start a new tracklet"""
# self.track_trajectory.append(self.tlbr)
self.kalman_filter = kalman_filter
self.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(self.tlwh_to_xyah(self._tlwh))
self.tracklet_len = 0
self.state = TrackState.Tracked
#self.is_activated = True
self.frame_id = frame_id
self.start_frame = frame_id
self.track_frames.append(frame_id)
def re_activate(self, new_track, frame_id, new_id=False):
new_tlwh = new_track.tlwh
self.track_trajectory.append(self.tlwh_to_tlbr(new_tlwh))
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh)
)
#self.update_features(new_track.curr_feat,new_track.iou_box)
#self.update_cluster(new_track.curr_feat)
self.tracklet_len = 0
self.state = TrackState.Tracked
self.is_activated = True
self.frame_id = frame_id
if new_id:
self.track_id = self.next_id()
self.track_frames.append(frame_id)
def update(self, new_track, frame_id, update_feature=False):
"""
Update a matched track
:type new_track: STrack
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id
self.tracklet_len += 1
self.vehicle_types_list.append(new_track.vehicle_types_list[-1])
new_tlwh = new_track.tlwh
self.track_trajectory.append(self.tlwh_to_tlbr(new_tlwh))
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh))
self.state = TrackState.Tracked
self.is_activated = True
self.score = new_track.score
if update_feature:
self.update_features(new_track.curr_feat,new_track.iou_box) ###########
#self.update_cluster(new_track.curr_feat)
self.track_frames.append(frame_id)
def infer_type(self):
def most_frequent(List):
return max(set(List), key = List.count)
types=most_frequent(self.vehicle_types_list)
return types
# if classes in ['bicycle', 'motorcycle']:
# return 1
# elif classes =='car':
# return 2
# elif classes=='bus':
# return 3
# else:
# return 4
@property
def vehicle_type(self):
def most_frequent(List):
return max(set(List), key = List.count)
if len(self.track_frames)>=self.type_infer_patience:
return most_frequent(self.vehicle_types_list)
elif self.score >=self.score_infer_type_thres:
return most_frequent(self.vehicle_types_list)
else:
return 'Undetermine'
@property
# @jit(nopython=True)
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
# @jit(nopython=True)
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
# @jit(nopython=True)
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy()
ret[2:] -= ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame)
class JDETracker(object):
def __init__(self, opt, polygon, paths, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2**0, 2**(1.0 / 3.0), 2**(2.0 / 3.0)]
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
self.input_size = input_sizes[opt.compound_coef]
self.obj_list = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
'train', 'truck', 'boat', 'traffic light', 'fire hydrant', '',
'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
'', 'backpack', 'umbrella', '', '', 'handbag', 'tie', 'suitcase',
'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork',
'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair',
'couch', 'potted plant', 'bed', '', 'dining table', '', '',
'toilet', '', 'tv', 'laptop', 'mouse', 'remote', 'keyboard',
'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors',
'teddy bear', 'hair drier', 'toothbrush'
]
self.person_or_motorcycle = ['person']
self.obj_interest = [
'motorcycle', 'bicycle', 'bus', 'train', 'truck', 'car'
] if self.person_or_motorcycle[0] != 'person' else [
'person', 'bus', 'train', 'truck', 'car'
]
print(self.obj_interest)
self.detetection_model = EfficientDetBackbone(
compound_coef=opt.compound_coef,
num_classes=len(self.obj_list),
ratios=anchor_ratios,
scales=anchor_scales)
self.detetection_model.load_state_dict(
torch.load(
f'EfficientDet/weights/efficientdet-d{opt.compound_coef}.pth'))
self.detetection_model.eval()
device = torch.device('cuda:0')
self.detetection_model = self.detetection_model.to(device)
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.kalman_filter = KalmanFilter()
self.polygon = polygon
self.paths = paths
# self.line_of_interest=[self.paths[0][1],self.paths[0][2]]
def merge_outputs(self, detections):
results = {}
for j in range(1, self.opt.num_classes + 1):
results[j] = np.concatenate(
[detection[j] for detection in detections],
axis=0).astype(np.float32)
scores = np.hstack(
[results[j][:, 4] for j in range(1, self.opt.num_classes + 1)])
if len(scores) > self.max_per_image:
kth = len(scores) - self.max_per_image
thresh = np.partition(scores, kth)[kth]
for j in range(1, self.opt.num_classes + 1):
keep_inds = (results[j][:, 4] >= thresh)
results[j] = results[j][keep_inds]
return results
def update(self, im_blob, img0):
self.frame_id += 1
activated_starcks = []
refind_stracks = []
lost_stracks = []
removed_stracks = []
width = img0.shape[1]
height = img0.shape[0]
''' Step 1: Network forward, get detections & embeddings'''
with torch.no_grad():
ori_imgs, framed_imgs, framed_metas = preprocess(
[img0], max_size=self.input_size)
device = torch.device('cuda:0')
x = torch.stack(
[torch.from_numpy(fi).to(device) for fi in framed_imgs], 0)
x = x.to(torch.float32).permute(0, 3, 1, 2)
features, regression, classification, anchors = self.detetection_model(
x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(x, anchors, regression, classification,
regressBoxes, clipBoxes, self.opt.det_thres,
self.opt.nms_thres)
out = invert_affine(framed_metas, out)
bbox = []
score = []
types = []
for j in range(len(out[0]['rois'])):
obj = self.obj_list[out[0]['class_ids'][j]]
if obj in self.obj_interest:
x1, y1, x2, y2 = out[0]['rois'][j].astype(np.int)
#bike,bicycle
if (y1 + y2) / 2 > height / 2 and float(
out[0]['scores'][j]) < 0.35:
continue
if obj not in self.person_or_motorcycle and float(
out[0]['scores'][j]) >= 0.3:
bbox.append([x1, y1, x2, y2])
score.append(float(out[0]['scores'][j]))
types.append(obj)
elif obj in self.person_or_motorcycle: #['bicycle', 'motorcycle']
bbox.append([x1, y1, x2, y2])
score.append(float(out[0]['scores'][j]))
types.append(obj)
# vis
# print(len(bbox))
# print(img0.shape)
# print(self.polygon)
# for i in range(len(bbox)):
# bb = bbox[i]
# cv2.rectangle(img0, (bb[0], bb[1]),
# (bb[2], bb[3]),
# (0, 255, 0), 2)
# cv2.polylines(img0,[np.asarray(self.polygon)],True,(0,255,255))
# cv2.imshow('dets', img0)
# cv2.waitKey(0)
if len(bbox) > 0:
'''Detections'''
detections = [
STrack(STrack.tlbr_to_tlwh(tlbr), sco, clas, 30)
for (tlbr, sco, clas) in zip(bbox, score, types)
]
else:
detections = []
detections_plot = detections.copy()
''' Add newly detected tracklets to tracked_stracks'''
unconfirmed = []
tracked_stracks = [] # type: list[STrack]
for track in self.tracked_stracks:
if not track.is_activated:
unconfirmed.append(track)
else:
tracked_stracks.append(track)
''' Step 2: First association, with gating distance'''
strack_pool, lost_map_tracks = joint_stracks(tracked_stracks,
self.lost_stracks)
# Predict the current location with KF
#for strack in strack_pool:
#strack.predict()
STrack.multi_predict(strack_pool)
#dists = matching.embedding_distance(strack_pool, detections)
occlusion_map = heuristic_occlusion_detection(detections)
match_thres = 850
dists = np.zeros(shape=(len(strack_pool), len(detections)))
dists = matching.gate_cost_matrix(self.kalman_filter,
dists,
strack_pool,
detections,
type_diff=True)
#dists = matching.fuse_motion(self.opt,self.kalman_filter, dists, strack_pool, detections,lost_map=lost_map_tracks,occlusion_map=occlusion_map,thres=match_thres)
matches, u_track, u_detection = matching.linear_assignment(
dists, thresh=match_thres)
for itracked, idet in matches:
track = strack_pool[itracked]
det = detections[idet]
if track.state == TrackState.Tracked:
track.update(detections[idet], self.frame_id)
activated_starcks.append(track)
else:
track.re_activate(det, self.frame_id, new_id=False)
refind_stracks.append(track)
''' Step 3: Second association, with IOU'''
detections = [detections[i] for i in u_detection]
r_tracked_stracks = [
strack_pool[i] for i in u_track
if strack_pool[i].state == TrackState.Tracked
]
dists = matching.iou_distance(r_tracked_stracks, detections)
matches, u_track, u_detection = matching.linear_assignment(dists,
thresh=0.5)
for itracked, idet in matches:
track = r_tracked_stracks[itracked]
det = detections[idet]
if track.state == TrackState.Tracked:
track.update(det, self.frame_id)
activated_starcks.append(track)
else:
track.re_activate(det, self.frame_id, new_id=False)
refind_stracks.append(track)
''' '''
for it in u_track:
track = r_tracked_stracks[it]
if not track.state == TrackState.Lost:
track.mark_lost()
lost_stracks.append(track)
'''Deal with unconfirmed tracks, usually tracks with only one beginning frame'''
detections = [detections[i] for i in u_detection]
dists = matching.iou_distance(unconfirmed, detections)
matches, u_unconfirmed, u_detection = matching.linear_assignment(
dists, thresh=0.6)
for itracked, idet in matches:
unconfirmed[itracked].update(detections[idet], self.frame_id)
activated_starcks.append(unconfirmed[itracked])
for it in u_unconfirmed:
track = unconfirmed[it]
track.mark_removed()
removed_stracks.append(track)
""" Step 4: Init new stracks"""
for inew in u_detection:
track = detections[inew]
#print('score :'+str(track.score))
if track.score < self.det_thresh or track.occlusion_status == True or check_bbox_outside_polygon(
self.polygon, track.tlbr):
continue
if self.frame_id >= 5 and track.infer_type(
) in self.person_or_motorcycle and not check_bbox_inside_polygon(
self.polygon, track.tlbr): #person, motorcycle
continue
track.activate(self.kalman_filter, self.frame_id)
activated_starcks.append(track)
""" Step 5: Update state and getting out of interest tracklet if have"""
out_of_polygon_tracklet = []
out_of_polygon_tracklet = []
refind_stracks_copy = []
activated_starcks_copy = []
for idx, current_tracked_tracks in enumerate(
[refind_stracks, activated_starcks]): #
for track in current_tracked_tracks:
if check_bbox_outside_polygon(self.polygon, track.tlbr):
track.mark_removed()
removed_stracks.append(track)
if (
(len(track.track_frames) >= 2 and self.frame_id <= 5)
or len(track.track_frames) >= 4
) and idx == 1: ########## 4 is confident number of frame
if tlbrs_to_mean_area(track.track_trajectory) <= 800:
track_type = self.person_or_motorcycle[0] #person
else:
track_type = track.infer_type()
track_center = [[(x[0] + x[2]) / 2, (x[1] + x[3]) / 2]
for x in track.track_trajectory]
movement_id = counting_moi(
self.paths,
[(track_center[0], track_center[-1])])[0]
frame_id = self.frame_id + 1 if movement_id == '1' else self.frame_id + 2
out_of_polygon_tracklet.append(
(frame_id, track.track_id, track_type,
movement_id))
else:
refind_stracks_copy.append(
track) if idx == 0 else activated_starcks_copy.append(
track)
refind_stracks = refind_stracks_copy
activated_starcks = activated_starcks_copy
lost_stracks_copy = []
for track in lost_stracks:
if check_bbox_intersect_or_outside_polygon(self.polygon,
track.tlbr):
track.mark_removed()
removed_stracks.append(track)
if ((len(track.track_frames) >= 2 and self.frame_id <= 5)
or len(track.track_frames) >= 4):
# print(track.track_id,tlbrs_to_mean_area(track.track_trajectory))
if tlbrs_to_mean_area(track.track_trajectory) <= 800:
track_type = self.person_or_motorcycle[0]
else:
track_type = track.infer_type()
track_center = [[(x[0] + x[2]) / 2, (x[1] + x[3]) / 2]
for x in track.track_trajectory]
movement_id = counting_moi(
self.paths, [(track_center[0], track_center[-1])])[0]
frame_id = self.frame_id + 3 if str(
movement_id) == '2' else self.frame_id + 3
out_of_polygon_tracklet.append(
(frame_id, track.track_id, track_type, movement_id))
else:
lost_stracks_copy.append(track)
lost_stracks = lost_stracks_copy
for track in self.lost_stracks:
if self.frame_id - track.end_frame > self.max_time_lost:
track.mark_removed()
removed_stracks.append(track)
#Remove out of screen tracklet
elif track.tlwh[0] + track.tlwh[2] // 2 > width or track.tlwh[
1] + track.tlwh[3] // 2 > height or min(
track.tlwh[0] + track.tlwh[2] // 2,
track.tlwh[1] + track.tlwh[3] // 2) < 0:
track.num_out_frame += 1
if track.num_out_frame > STrack.out_of_frame_patience:
track.mark_removed()
removed_stracks.append(track)
# print('Ramained match {} s'.format(t4-t3))
# print(out_of_polygon_tracklet)
self.tracked_stracks = [
t for t in self.tracked_stracks if t.state == TrackState.Tracked
]
self.tracked_stracks, _ = joint_stracks(self.tracked_stracks,
activated_starcks)
self.tracked_stracks, _ = joint_stracks(self.tracked_stracks,
refind_stracks)
self.lost_stracks = sub_stracks(self.lost_stracks,
self.tracked_stracks)
self.lost_stracks.extend(lost_stracks)
self.lost_stracks = sub_stracks(self.lost_stracks,
self.removed_stracks)
self.removed_stracks.extend(removed_stracks)
self.tracked_stracks, self.lost_stracks = remove_duplicate_stracks(
self.tracked_stracks, self.lost_stracks)
#self.merge_track()
output_stracks = [
track for track in self.tracked_stracks if track.is_activated
]
logger.debug('===========Frame {}=========='.format(self.frame_id))
logger.debug('Activated: {}'.format(
[track.track_id for track in activated_starcks]))
logger.debug('Refind: {}'.format(
[track.track_id for track in refind_stracks]))
logger.debug('Lost: {}'.format(
[track.track_id for track in lost_stracks]))
logger.debug('Removed: {}'.format(
[track.track_id for track in removed_stracks]))
return output_stracks, detections_plot, out_of_polygon_tracklet
#can paralel,current bottleneck of model
def merge_track(self,
min_thres=0.2,
distance_thres=15,
consitence_thres=10):
def is_overlap(lost_track, tracked_track):
if tracked_track.start_frame > lost_track.end_frame or lost_track.start_frame > tracked_track.end_frame:
return False
def predict_future(lost_track, num_frame):
mean, cov = lost_track.mean, lost_track.covariance
for _ in range(num_frame):
mean, cov = lost_track.kalman_filter.predict(mean, cov)
return mean, cov
def cluster_compare(lost_track, tracked_track):
return np.min(
cdist(lost_track.cluster_features['centers'],
tracked_track.cluster_features['centers'],
metric='cosine'))
def distance(lost_track,
tracked_track,
min_thres=min_thres,
distance_thres=distance_thres):
if is_overlap(lost_track, tracked_track):
return np.inf
else:
pred_mean, pred_cov = predict_future(
lost_track,
tracked_track.start_frame - lost_track.end_frame)
tracked_xyah = STrack.tlwh_to_xyah(tracked_track._tlwh)
if self.kalman_filter.gating_distance(
pred_mean, pred_cov, tracked_xyah) > distance_thres:
return np.inf
else:
return cluster_compare(lost_track, tracked_track)
cost_matrix = np.zeros(shape=(len(self.lost_stracks),
len(self.tracked_stracks)))
for i in range(cost_matrix.shape[0]):
for j in range(cost_matrix.shape[1]):
if min(len(self.lost_stracks[i].track_frames),
len(self.tracked_stracks[j].track_frames)
) <= consitence_thres:
cost_matrix[i][j] = np.inf
else:
cost_matrix[i][j] = distance(self.lost_stracks[i],
self.tracked_stracks[j])
matches, _, _ = matching.linear_assignment(cost_matrix,
thresh=min_thres)
map_lost_track = np.ones_like(self.lost_stracks, dtype=np.int)
for i in range(cost_matrix.shape[0]):
for j in range(cost_matrix.shape[1]):
if cost_matrix[i][j] <= 1:
print('sim of ' + str(self.lost_stracks[i].track_id) +
' and ' + str(self.tracked_stracks[j].track_id) +
' : ' + str(cost_matrix[i][j]))
if len(matches) == 0:
return
for ilost_track, i_tracked_track in matches:
print('------------------------------------')
print('merge ' +
str(self.tracked_stracks[i_tracked_track].track_id) +
' to ' + str(self.lost_stracks[ilost_track].track_id))
map_lost_track[ilost_track] = 0 # pylint: disable=unsupported-assignment-operation
for num_clus in range(
len(self.tracked_stracks[i_tracked_track].
cluster_features['cluster'])):
for clus in self.tracked_stracks[
i_tracked_track].cluster_features['cluster'][num_clus]:
self.lost_stracks[ilost_track].update_cluster(clus)
self.lost_stracks[ilost_track].mean, self.lost_stracks[
ilost_track].covariance = self.tracked_stracks[
i_tracked_track].mean, self.tracked_stracks[
i_tracked_track].covariance
self.lost_stracks[
ilost_track].track_frames += self.tracked_stracks[
i_tracked_track].track_frames
self.lost_stracks[ilost_track].frame_id = self.tracked_stracks[
i_tracked_track].frame_id
self.tracked_stracks[i_tracked_track] = self.lost_stracks[
ilost_track]
new_lost_tracks = []
for ilost_track in range(len(map_lost_track)):
if map_lost_track[ilost_track] == 1:
new_lost_tracks.append(self.lost_stracks[ilost_track])
self.lost_stracks = new_lost_tracks
class JDETracker(object):
def __init__(self, opt,polygon, paths, polygon2=None,frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
self.input_size = input_sizes[opt.compound_coef]
if opt.detection_model=='Efficient' :
self.obj_list =['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', '', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', '', 'backpack', 'umbrella', '', '', 'handbag', 'tie',
'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
'skateboard', 'surfboard', 'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut',
'cake', 'chair', 'couch', 'potted plant', 'bed', '', 'dining table', '', '', 'toilet', '', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
'toothbrush']
self.person_or_motorcycle=['person']
self.obj_interest=[ 'motorcycle','bicycle', 'bus', 'truck','car'] if self.person_or_motorcycle[0]!='person' else [ 'person', 'bus', 'truck','car']
self.detetection_model= EfficientDetBackbone(compound_coef=opt.compound_coef, num_classes=len(self.obj_list),
ratios=anchor_ratios, scales=anchor_scales)
self.detetection_model.load_state_dict(torch.load(f'EfficientDet/weights/efficientdet-d{opt.compound_coef}.pth'))
self.detetection_model.eval()
device = torch.device('cuda:0')
self.detetection_model = self.detetection_model.to(device)
elif opt.detection_model=='FasterRcnn' :
config_file = "Drone_FasterRCNN/drone_demo/e2e_faster_rcnn_X_101_32x8d_FPN_1x_visdrone.yaml"
cfg.merge_from_file(config_file)
cfg.merge_from_list(["MODEL.WEIGHT", "Drone_FasterRCNN/drone_demo/visdrone_model_0360000.pth"])
self.detetection_model = COCODemo(
cfg,
min_image_size=opt.min_img_size,
confidence_threshold=opt.conf_thres,
)
label_of_interest=[
# "__background",
# "unused",
# "pedestrian",
# "person",
# "bicycle",
"car",
"van",
"truck",
# "tricycle",
# "awning-tricycle",
"bus",
"motor"
]
self.person_or_motorcycle=["motor"]
#'bicycle'
self.obj_interest=[ 'motor', 'bus', 'truck','car','van', "tricycle"] if self.person_or_motorcycle[0]!='person' else [ 'person', 'bus', 'truck','car','van', "tricycle"]
else:
raise('Not supported detector model')
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.kalman_filter = KalmanFilter()
self.polygon=polygon
self.paths=paths
self.polygon2=polygon2
self.line1=[polygon[0],polygon[1]]
self.line2=[polygon[1],polygon[2]]
self.line3=[polygon[2],polygon[3]]
self.line4=[polygon[0],polygon[4]]
self.two_polygon_system=True
self.warmup_frame=0
self.virtual_polygon= [
[
0,
680
],
[
0,
149
],
[
1270,
149
],
[
1270,
680
]
]
def box_cross_line(self,bbox_list,line):
for bbox in bbox_list:
if box_line_relative(bbox,line)=='cross' :
return True
return False
def heusristic_mov_refinement(self,track,predict_mov):
#5,2,9 corection
if str(predict_mov)=='5':
if self.box_cross_line(track.track_trajectory[-3:],self.line1):
return '5'
elif self.box_cross_line(track.track_trajectory[-3:],self.line2):
if track.track_trajectory[0][3]>=350:
return '2'
elif track.track_trajectory[0][2]>=750:
return '9'
else:
return 'undetermine'
else:
return 'undetermine'
if str(predict_mov) in ['2','9']:
if self.box_cross_line(track.track_trajectory[-3:],self.line2):
return predict_mov
elif self.box_cross_line(track.track_trajectory[-3:],self.line1):
if track.track_trajectory[0][3]>=350:
return '5'
else:
return 'undetermine'
else:
return predict_mov
def heusristic_mov_detection(self,track,track_center):
if track.track_id==57:
print(track_center)
if self.box_cross_line(track.track_trajectory[-4:],self.line1) and track_center[-1][1]<=470:
paths={'3':self.paths['3'],'5':self.paths['5'],'11':self.paths['11']}
if track.track_trajectory[-4][1]<=265 and abs(track.track_trajectory[0][0]-track.track_trajectory[-1][0])<=175 and track.track_trajectory[-1][3]<=295:
return 3
mov_id= counting_moi(paths,[(track_center[0],track_center[-1])])
if str(mov_id[0])=='3' and not(track.track_trajectory[-4][1]<=265 and abs(track.track_trajectory[0][0]-track.track_trajectory[-1][0])<=175 and track.track_trajectory[-1][3]<=295):
return 'undetermine'
return mov_id[0]
elif self.box_cross_line(track.track_trajectory[-4:] , self.line2) and track_center[-1][0]>=550:
paths={'2':self.paths['2'],'4':self.paths['4'],'9':self.paths['9']}
mov_id= counting_moi(paths,[(track_center[0],track_center[-1])])
return mov_id[0]
elif self.box_cross_line(track.track_trajectory[-4:],self.line3):
paths={'7':self.paths['7'],'8':self.paths['8'],'10':self.paths['10']}
mov_id= counting_moi(paths,[(track_center[0],track_center[-1])])
return mov_id[0]
elif self.box_cross_line(track.track_trajectory[-4:],self.line4):
paths={'6':self.paths['6'],'1':self.paths['1'],'12':self.paths['12']}
mov_id= counting_moi(paths,[(track_center[0],track_center[-1])])
if str(mov_id[0])=='12' and track.track_trajectory[0][0]<=500:
return 1 if track.track_trajectory[0][3]<=350 else 'undetermine'
return mov_id[0]
else:
return 'undetermine'
def merge_outputs(self, detections):
results = {}
for j in range(1, self.opt.num_classes + 1):
results[j] = np.concatenate(
[detection[j] for detection in detections], axis=0).astype(np.float32)
scores = np.hstack(
[results[j][:, 4] for j in range(1, self.opt.num_classes + 1)])
if len(scores) > self.max_per_image:
kth = len(scores) - self.max_per_image
thresh = np.partition(scores, kth)[kth]
for j in range(1, self.opt.num_classes + 1):
keep_inds = (results[j][:, 4] >= thresh)
results[j] = results[j][keep_inds]
return results
def update(self, im_blob, img0):
self.frame_id += 1
activated_starcks = []
refind_stracks = []
lost_stracks = []
removed_stracks = []
width = img0.shape[1]
height = img0.shape[0]
init_polygon=self.polygon2 if self.two_polygon_system and self.frame_id>= self.warmup_frame else self.polygon
two_wheel_polygon=self.polygon
four_wheel_polygon=self.polygon
virtual_polygon=self.virtual_polygon
huge_box_thres=150
bbox=[]
score=[]
types=[]
huge_vehicles=[]
''' Step 1: Network forward, get detections & embeddings'''
if self.opt.detection_model=='Efficient':
with torch.no_grad():
ori_imgs, framed_imgs, framed_metas = preprocess([img0], max_size=self.input_size)
device = torch.device('cuda:0')
x = torch.stack([torch.from_numpy(fi).to(device) for fi in framed_imgs], 0)
x = x.to(torch.float32 ).permute(0, 3, 1, 2)
features, regression, classification, anchors = self.detetection_model(x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(x,
anchors, regression, classification,
regressBoxes, clipBoxes,
self.opt.det_thres, self.opt.nms_thres)
out = invert_affine(framed_metas, out)
bbox=[]
score=[]
types=[]
huge_vehicles=[]
for j in range(len(out[0]['rois'])):
obj = self.obj_list[out[0]['class_ids'][j]]
if obj in self.obj_interest:
x1, y1, x2, y2 = out[0]['rois'][j].astype(np.int)
#bike,bicycle
if (y1+y2)/2>height/2 and float(out[0]['scores'][j])<=0.25:
continue
if (y2-y1)*(x2-x1)<=200:
continue
if obj not in self.person_or_motorcycle and float(out[0]['scores'][j])>=0.3:
bbox.append([x1, y1, x2, y2])
score.append( float(out[0]['scores'][j]))
types.append(obj)
huge_vehicles.append(False if ((y2-y1)<=huge_box_thres and (x2-x1)<=180) else True )
elif obj in self.person_or_motorcycle: #['bicycle', 'motorcycle']
bbox.append([x1, y1, x2, y2])
score.append( float(out[0]['scores'][j]))
types.append(obj)
huge_vehicles.append(False)
elif self.opt.detection_model=='FasterRcnn':
predictions= self.detetection_model.compute_prediction(img0)
top_predictions=self.detetection_model.select_top_predictions(predictions)
scores = top_predictions.get_field("scores").tolist()
labels = top_predictions.get_field("labels").tolist()
labels = [self.detetection_model.CATEGORIES[i] for i in labels]
boxes = top_predictions.bbox.tolist()
for j in range(len(labels)):
obj = labels[j]
if obj in self.obj_interest:
x1, y1, x2, y2 = boxes[j]
if (y1+y2)/2>0.5*height and float(scores[j])<=0.25:
continue
if (y2-y1)*(x2-x1)<=200:
continue
if obj not in self.person_or_motorcycle and float(scores[j])>=0.3:
bbox.append([x1, y1, x2, y2])
score.append( float(scores[j]))
types.append(obj)
huge_vehicles.append(False if ((y2-y1)<=huge_box_thres and (x2-x1)<=180) else True )
elif obj in self.person_or_motorcycle and float(scores[j])>=self.opt.det_thres: #['bicycle', 'motorcycle']
bbox.append([x1, y1, x2, y2])
score.append( float(scores[j]))
types.append(obj)
huge_vehicles.append(False)
# vis
# print(len(bbox))
# print(img0.shape)
# print(self.polygon)
# for i in range(len(bbox)):
# bb = bbox[i]
# cv2.rectangle(img0, (bb[0], bb[1]),
# (bb[2], bb[3]),
# (0, 255, 0), 2)
# cv2.polylines(img0,[np.asarray(self.polygon)],True,(0,255,255))
# cv2.imshow('dets', img0)
# cv2.waitKey(0)
if len(bbox) > 0:
'''Detections'''
detections = [STrack(STrack.tlbr_to_tlwh(tlbr), sco, clas, 30,huge_vehicle=hv) for
(tlbr, sco,clas,hv) in zip(bbox,score,types,huge_vehicles)]
else:
detections = []
detections_plot=copy.deepcopy(detections)
''' Add newly detected tracklets to tracked_stracks'''
unconfirmed = []
tracked_stracks = [] # type: list[STrack]
for track in self.tracked_stracks:
if not track.is_activated:
unconfirmed.append(track)
else:
tracked_stracks.append(track)
''' Step 2: First association, with gating distance'''
strack_pool,lost_map_tracks = joint_stracks(tracked_stracks, self.lost_stracks)
# Predict the current location with KF
#for strack in strack_pool:
#strack.predict()
STrack.multi_predict(strack_pool)
#dists = matching.embedding_distance(strack_pool, detections)
detections=heuristic_occlusion_detection(detections)
match_thres=100
dists=np.zeros(shape=(len(strack_pool),len(detections)))
dists = matching.gate_cost_matrix3(self.kalman_filter, dists, strack_pool, detections,type_diff=True)
#dists = matching.fuse_motion(self.opt,self.kalman_filter, dists, strack_pool, detections,lost_map=lost_map_tracks,occlusion_map=occlusion_map,thres=match_thres)
matches, u_track, u_detection = matching.linear_assignment(dists, thresh=match_thres)
for itracked, idet in matches:
track = strack_pool[itracked]
det = detections[idet]
if track.state == TrackState.Tracked:
track.update(detections[idet], self.frame_id)
activated_starcks.append(track)
else:
track.re_activate(det, self.frame_id, new_id=False)
refind_stracks.append(track)
''' Step 3: Second association, with IOU'''
detections = [detections[i] for i in u_detection]
r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
dists = matching.iou_distance(r_tracked_stracks, detections)
matches, u_track, u_detection = matching.linear_assignment(dists, thresh=0.5)
for itracked, idet in matches:
track = r_tracked_stracks[itracked]
det = detections[idet]
if track.state == TrackState.Tracked:
track.update(det, self.frame_id)
activated_starcks.append(track)
else:
track.re_activate(det, self.frame_id, new_id=False)
refind_stracks.append(track)
''' '''
for it in u_track:
track = r_tracked_stracks[it]
if not track.state == TrackState.Lost:
track.mark_lost()
lost_stracks.append(track)
'''Deal with unconfirmed tracks, usually tracks with only one beginning frame'''
detections = [detections[i] for i in u_detection]
dists = matching.iou_distance(unconfirmed, detections)
matches, u_unconfirmed, u_detection = matching.linear_assignment(dists, thresh=0.6)
for itracked, idet in matches:
unconfirmed[itracked].update(detections[idet], self.frame_id)
activated_starcks.append(unconfirmed[itracked])
for it in u_unconfirmed:
track = unconfirmed[it]
track.mark_removed()
removed_stracks.append(track)
""" Step 4: Init new stracks"""
for inew in u_detection:
track = detections[inew]
track_init_polygon=init_polygon if not track.huge_vehicle else virtual_polygon
if track.score < self.det_thresh or track.occlusion_status==True or check_bbox_outside_polygon(track_init_polygon,track.tlbr):
continue
# track_types=self.person_or_motorcycle[0] if tlbrs_to_mean_area(track.track_trajectory) <=1500 else track.infer_type()
if self.frame_id>=1 and not check_bbox_inside_polygon(track_init_polygon,track.tlbr):#and track_types in self.person_or_motorcycle #person, motorcycle
continue
track.activate(self.kalman_filter, self.frame_id)
activated_starcks.append(track)
""" Step 5: Update state and getting out of interest tracklet if have"""
out_of_polygon_tracklet=[]
refind_stracks_copy=[]
activated_starcks_copy=[]
for idx,current_tracked_tracks in enumerate([refind_stracks,activated_starcks]) :#
for track in current_tracked_tracks:
if tlbrs_to_mean_area(track.track_trajectory) <=1000 :
track_type= self.person_or_motorcycle[0] #person
else:
track_type=track.infer_type()
if track_type in self.person_or_motorcycle:
out_polygon=two_wheel_polygon
p_type='two_wheel'
else:
out_polygon=four_wheel_polygon #if not track.huge_vehicle else virtual_polygon
p_type='four_wheel'
if check_bbox_outside_polygon(out_polygon,track.tlbr) :
track.mark_removed()
removed_stracks.append(track)
if ((len(track.track_frames)>=4 and self.frame_id <=5) or (len(track.track_frames)>=5 and self.frame_id>=self.warmup_frame+5)) and idx==1:########## 4 is confident number of frame
track_center=[ [(x[0]+x[2])/2,(x[1]+x[3])/2] for x in track.track_trajectory]
# movement_id=counting_moi(self.paths,[(track_center[0],track_center[-1])])[0]
# movement_id=self.heusristic_mov_refinement(track,movement_id)
movement_id=self.heusristic_mov_detection(track,track_center)
frame_id=self.frame_id
out_of_polygon_tracklet.append((frame_id,track.track_id,track_type,movement_id))
else:
refind_stracks_copy.append(track) if idx ==0 else activated_starcks_copy.append(track)
refind_stracks=refind_stracks_copy
activated_starcks=activated_starcks_copy
lost_stracks_copy=[]
for track in lost_stracks:
if tlbrs_to_mean_area(track.track_trajectory) <=1000 :
track_type= self.person_or_motorcycle[0] #person
else:
track_type=track.infer_type()
if track_type in self.person_or_motorcycle:
out_polygon=two_wheel_polygon
p_type='two_wheel'
else:
out_polygon=four_wheel_polygon
p_type='four_wheel'
if check_bbox_intersect_or_outside_polygon(out_polygon,track.tlbr) :
track.mark_removed()
removed_stracks.append(track)
if ((len(track.track_frames)>=4 and self.frame_id <=5) or (len(track.track_frames)>=6 and self.frame_id>=self.warmup_frame+5)):
track_center=[ [(x[0]+x[2])/2,(x[1]+x[3])/2] for x in track.track_trajectory]
# movement_id=counting_moi(self.paths,[(track_center[0],track_center[-1])])[0]
# movement_id=self.heusristic_mov_refinement(track,movement_id)
movement_id=self.heusristic_mov_detection(track,track_center)
# line_interest=self.line1 if str(movement_id)=='1' else self.line2
# out_direction='bottom' if str(movement_id)=='1' else 'up'
frame_id=self.frame_id if track_type in self.person_or_motorcycle else self.frame_id+5#kalman_predict_out_line(track,line_interest,out_direction)
out_of_polygon_tracklet.append((frame_id,track.track_id,track_type,movement_id))
else:
lost_stracks_copy.append(track)
lost_stracks=lost_stracks_copy
for track in self.lost_stracks:
if self.frame_id - track.end_frame > self.max_time_lost :
track.mark_removed()
removed_stracks.append(track)
#Remove out of screen tracklet
elif track.tlwh[0]+track.tlwh[2]//2>width or track.tlwh[1]+track.tlwh[3]//2>height or min(track.tlwh[0]+track.tlwh[2]//2,track.tlwh[1]+track.tlwh[3]//2)<0:
track.num_out_frame+=1
if track.num_out_frame>STrack.out_of_frame_patience:
track.mark_removed()
removed_stracks.append(track)
# print('Ramained match {} s'.format(t4-t3))
# print(out_of_polygon_tracklet)
self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked]
self.tracked_stracks,_ = joint_stracks(self.tracked_stracks, activated_starcks)
self.tracked_stracks,_ = joint_stracks(self.tracked_stracks, refind_stracks)
self.lost_stracks = sub_stracks(self.lost_stracks, self.tracked_stracks)
self.lost_stracks.extend(lost_stracks)
self.lost_stracks = sub_stracks(self.lost_stracks, self.removed_stracks)
self.removed_stracks.extend(removed_stracks)
self.tracked_stracks, self.lost_stracks = remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
#self.merge_track()
output_stracks = [track for track in self.tracked_stracks if track.is_activated]
# logger.debug('===========Frame {}=========='.format(self.frame_id))
# logger.debug('Activated: {}'.format([track.track_id for track in activated_starcks]))
# logger.debug('Refind: {}'.format([track.track_id for track in refind_stracks]))
# logger.debug('Lost: {}'.format([track.track_id for track in lost_stracks]))
# logger.debug('Removed: {}'.format([track.track_id for track in removed_stracks]))
return output_stracks,detections_plot,out_of_polygon_tracklet
#can paralel,current bottleneck of model
def merge_track(self,min_thres=0.2,distance_thres=15, consitence_thres=10):
def is_overlap(lost_track,tracked_track):
if tracked_track.start_frame>lost_track.end_frame or lost_track.start_frame>tracked_track.end_frame:
return False
def predict_future(lost_track,num_frame):
mean,cov=lost_track.mean,lost_track.covariance
for _ in range(num_frame):
mean,cov=lost_track.kalman_filter.predict(mean,cov)
return mean,cov
def cluster_compare(lost_track,tracked_track):
return np.min(cdist(lost_track.cluster_features['centers'],tracked_track.cluster_features['centers'],metric='cosine'))
def distance(lost_track,tracked_track,min_thres=min_thres,distance_thres=distance_thres):
if is_overlap(lost_track,tracked_track):
return np.inf
else:
pred_mean,pred_cov=predict_future(lost_track,tracked_track.start_frame-lost_track.end_frame)
tracked_xyah=STrack.tlwh_to_xyah(tracked_track._tlwh)
if self.kalman_filter.gating_distance(pred_mean,pred_cov,tracked_xyah) > distance_thres:
return np.inf
else:
return cluster_compare(lost_track,tracked_track)
cost_matrix=np.zeros(shape=(len(self.lost_stracks),len(self.tracked_stracks)))
for i in range(cost_matrix.shape[0]):
for j in range(cost_matrix.shape[1]):
if min(len(self.lost_stracks[i].track_frames),len(self.tracked_stracks[j].track_frames))<=consitence_thres:
cost_matrix[i][j]=np.inf
else:
cost_matrix[i][j]=distance(self.lost_stracks[i],self.tracked_stracks[j])
matches,_,_=matching.linear_assignment(cost_matrix,thresh=min_thres)
map_lost_track=np.ones_like(self.lost_stracks,dtype=np.int)
for i in range(cost_matrix.shape[0]):
for j in range(cost_matrix.shape[1]):
if cost_matrix[i][j]<=1:
print('sim of ' +str(self.lost_stracks[i].track_id) + ' and ' +str(self.tracked_stracks[j].track_id) +' : '+str(cost_matrix[i][j]) )
if len(matches)==0:
return
for ilost_track,i_tracked_track in matches:
print('------------------------------------')
print('merge ' + str(self.tracked_stracks[i_tracked_track].track_id)+' to '+str(self.lost_stracks[ilost_track].track_id))
map_lost_track[ilost_track]=0 # pylint: disable=unsupported-assignment-operation
for num_clus in range(len(self.tracked_stracks[i_tracked_track].cluster_features['cluster'])):
for clus in self.tracked_stracks[i_tracked_track].cluster_features['cluster'][num_clus]:
self.lost_stracks[ilost_track].update_cluster(clus)
self.lost_stracks[ilost_track].mean,self.lost_stracks[ilost_track].covariance=self.tracked_stracks[i_tracked_track].mean,self.tracked_stracks[i_tracked_track].covariance
self.lost_stracks[ilost_track].track_frames+=self.tracked_stracks[i_tracked_track].track_frames
self.lost_stracks[ilost_track].frame_id=self.tracked_stracks[i_tracked_track].frame_id
self.tracked_stracks[i_tracked_track]=self.lost_stracks[ilost_track]
new_lost_tracks=[]
for ilost_track in range(len(map_lost_track)):
if map_lost_track[ilost_track] ==1:
new_lost_tracks.append(self.lost_stracks[ilost_track])
self.lost_stracks=new_lost_tracks
class STrack(BaseTrack):
shared_kalman = KalmanFilter()
def __init__(self, tlwh, score, temp_feat, buffer_size=30):
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.tracklet_len = 0
self.smooth_feat = None
self.update_features(temp_feat)
self.features = deque([], maxlen=buffer_size)
self.alpha = 0.9
self.history = []
def update_features(self, feat):
feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat
self.features.append(feat)
self.smooth_feat /= np.linalg.norm(self.smooth_feat)
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
@staticmethod
def multi_predict(stracks):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
stracks[i].mean = mean
stracks[i].covariance = cov
def activate(self, kalman_filter, frame_id):
"""Start a new tracklet"""
self.kalman_filter = kalman_filter
self.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(self.tlwh_to_xyah(self._tlwh))
self.tracklet_len = 0
self.state = TrackState.Tracked
if frame_id == 1:
self.is_activated = True
#self.is_activated = True
self.frame_id = frame_id
self.start_frame = frame_id
def re_activate(self, new_track, frame_id, new_id=False):
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh)
)
self.update_features(new_track.curr_feat)
self.tracklet_len = 0
self.state = TrackState.Tracked
self.is_activated = True
self.frame_id = frame_id
if new_id:
self.track_id = self.next_id()
def update(self, new_track, frame_id, update_feature=True):
"""
Update a matched track
:type new_track: STrack
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id
self.tracklet_len += 1
new_tlwh = new_track.tlwh
# log historical track up to previous 10 frames
if len(self.history) == 10:
self.history = self.history[1:]
self.history.append(new_tlwh.copy())
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh))
self.state = TrackState.Tracked
self.is_activated = True
self.score = new_track.score
if update_feature:
self.update_features(new_track.curr_feat)
@property
def tlwh_raw(self):
if len(self.history) > 0:
return self.history[-1]
return self._tlwh.copy()
@property
# @jit(nopython=True)
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
# @jit(nopython=True)
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
# @jit(nopython=True)
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy()
ret[2:] -= ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame)
class STrack(BaseTrack):
shared_kalman = KalmanFilter() # 类变量
def __init__(self, tlwh, score, temp_feat, buffer_size=30):
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.tracklet_len = 0
self.smooth_feat = None
self.update_features(temp_feat)
self.features = deque([], maxlen=buffer_size)
self.alpha = 0.9
def update_features(self, feat): # 增加新的feature，添加到self.feature、self.curr_feat
feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat # 指数移动加权平均，self.smooth_feat综合了过去一定量的feature
self.features.append(feat)
self.smooth_feat /= np.linalg.norm(self.smooth_feat) # 归一化处理
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
@staticmethod
def multi_predict(stracks):
if len(stracks) > 0:
multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance) # 返回预测状态的均值向量和协方差矩阵
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): # 然后再将各自的均值向量、协方差矩阵分别分配给对应的stracks
stracks[i].mean = mean
stracks[i].covariance = cov
def activate(self, kalman_filter, frame_id): # 创建一个新的 track
"""Start a new tracklet"""
self.kalman_filter = kalman_filter
self.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(self.tlwh_to_xyah(self._tlwh))
# 使用当前位置状态进行初始化
self.tracklet_len = 0
self.state = TrackState.Tracked
#self.is_activated = True
self.frame_id = frame_id
self.start_frame = frame_id
def re_activate(self, new_track, frame_id, new_id=False): # 新创建一个 track
self.mean, self.covariance = self.kalman_filter.update(
self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh)
)
self.update_features(new_track.curr_feat)
self.tracklet_len = 0
self.state = TrackState.Tracked
self.is_activated = True
self.frame_id = frame_id
if new_id:
self.track_id = self.next_id()
def update(self, new_track, frame_id, update_feature=True): # 更新对应的 KF 中的均值向量、协方差矩阵
"""
Update a matched track
:type new_track: STrack
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id # 当前的帧id
self.tracklet_len += 1 # 追踪片段长度增加 1
new_tlwh = new_track.tlwh
self.mean, self.covariance = self.kalman_filter.update( # 卡尔曼滤波器
self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh))
self.state = TrackState.Tracked
self.is_activated = True
self.score = new_track.score
if update_feature:
self.update_features(new_track.curr_feat)
@property
# @jit(nopython=True)
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
# @jit(nopython=True)
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
# @jit(nopython=True)
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy()
ret[2:] -= ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame)
class Track(BaseTrack):
shared_kalman = KalmanFilter()
def __init__(self, tlwh, score, temp_feat, buff_size=30):
"""
:param tlwh:
:param score:
:param temp_feat:
:param buff_size:
"""
# wait activate
self._tlwh = np.asarray(tlwh, dtype=np.float)
self.kalman_filter = None
self.mean, self.covariance = None, None
self.is_activated = False
self.score = score
self.track_len = 0
self.smooth_feat = None
self.update_features(temp_feat)
self.features = deque([], maxlen=buff_size) # 指定了限制长度
self.alpha = 0.9
def update_features(self, feat):
# L2 normalizing
feat /= np.linalg.norm(feat)
self.curr_feat = feat
if self.smooth_feat is None:
self.smooth_feat = feat
else:
self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat
self.features.append(feat)
self.smooth_feat /= np.linalg.norm(self.smooth_feat)
def predict(self):
mean_state = self.mean.copy()
if self.state != TrackState.Tracked:
mean_state[7] = 0
self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
@staticmethod
def multi_predict(tracks):
if len(tracks) > 0:
multi_mean = np.asarray([track.mean.copy() for track in tracks])
multi_covariance = np.asarray([track.covariance for track in tracks])
for i, st in enumerate(tracks):
if st.state != TrackState.Tracked:
multi_mean[i][7] = 0
multi_mean, multi_covariance = Track.shared_kalman.multi_predict(multi_mean, multi_covariance)
for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
tracks[i].mean = mean
tracks[i].covariance = cov
def reset_track_id(self):
self.reset_track_count()
def activate(self, kalman_filter, frame_id):
"""Start a new tracklet"""
self.kalman_filter = kalman_filter # assign a filter to each tracklet?
# update the track id
self.track_id = self.next_id()
self.mean, self.covariance = self.kalman_filter.initiate(self.tlwh_to_xyah(self._tlwh))
self.track_len = 0
self.state = TrackState.Tracked # set flag 'tracked'
# self.is_activated = True
if frame_id == 1: # to record the first frame's detection result
self.is_activated = True
self.frame_id = frame_id
self.start_frame = frame_id
def re_activate(self, new_track, frame_id, new_id=False):
self.mean, self.covariance = self.kalman_filter.update(self.mean,
self.covariance,
self.tlwh_to_xyah(new_track.tlwh))
self.update_features(new_track.curr_feat)
self.track_len = 0
self.state = TrackState.Tracked # set flag 'tracked'
self.is_activated = True
self.frame_id = frame_id
if new_id: # update the track id
self.track_id = self.next_id()
def update(self, new_track, frame_id, update_feature=True):
"""
Update a matched track
:type new_track: Track
:type frame_id: int
:type update_feature: bool
:return:
"""
self.frame_id = frame_id
self.track_len += 1
new_tlwh = new_track.tlwh
self.mean, self.covariance = self.kalman_filter.update(self.mean,
self.covariance,
self.tlwh_to_xyah(new_tlwh))
self.state = TrackState.Tracked # set flag 'tracked'
self.is_activated = True # set flag 'activated'
self.score = new_track.score
if update_feature:
self.update_features(new_track.curr_feat)
@property
# @jit(nopython=True)
def tlwh(self):
"""Get current position in bounding box format `(top left x, top left y,
width, height)`.
"""
if self.mean is None:
return self._tlwh.copy()
ret = self.mean[:4].copy()
ret[2] *= ret[3]
ret[:2] -= ret[2:] / 2
return ret
@property
# @jit(nopython=True)
def tlbr(self):
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
`(top left, bottom right)`.
"""
ret = self.tlwh.copy()
ret[2:] += ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_xyah(tlwh):
"""Convert bounding box to format `(center x, center y, aspect ratio,
height)`, where the aspect ratio is `width / height`.
"""
ret = np.asarray(tlwh).copy()
ret[:2] += ret[2:] / 2
ret[2] /= ret[3]
return ret
def to_xyah(self):
return self.tlwh_to_xyah(self.tlwh)
@staticmethod
# @jit(nopython=True)
def tlbr_to_tlwh(tlbr):
ret = np.asarray(tlbr).copy() # numpy中的.copy()是深拷贝
ret[2:] -= ret[:2]
return ret
@staticmethod
# @jit(nopython=True)
def tlwh_to_tlbr(tlwh):
ret = np.asarray(tlwh).copy()
ret[2:] += ret[:2]
return ret
def __repr__(self):
return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame)
def __init__(self, opt, polygon, paths, polygon2=None, frame_rate=30):
self.opt = opt
if opt.gpus[0] >= 0:
opt.device = torch.device('cuda')
else:
opt.device = torch.device('cpu')
print('Creating model...')
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2**0, 2**(1.0 / 3.0), 2**(2.0 / 3.0)]
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
self.input_size = input_sizes[opt.compound_coef]
self.obj_list = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
'train', 'truck', 'boat', 'traffic light', 'fire hydrant', '',
'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
'', 'backpack', 'umbrella', '', '', 'handbag', 'tie', 'suitcase',
'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork',
'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair',
'couch', 'potted plant', 'bed', '', 'dining table', '', '',
'toilet', '', 'tv', 'laptop', 'mouse', 'remote', 'keyboard',
'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors',
'teddy bear', 'hair drier', 'toothbrush'
]
self.person_or_motorcycle = ['motorcycle', 'bicycle']
self.obj_interest = [
'motorcycle', 'bicycle', 'bus', 'truck', 'car'
] if self.person_or_motorcycle[0] != 'person' else [
'person', 'bus', 'truck', 'car'
]
print(self.obj_interest)
self.detetection_model = EfficientDetBackbone(
compound_coef=opt.compound_coef,
num_classes=len(self.obj_list),
ratios=anchor_ratios,
scales=anchor_scales)
self.detetection_model.load_state_dict(
torch.load(
f'EfficientDet/weights/efficientdet-d{opt.compound_coef}.pth'))
self.detetection_model.eval()
device = torch.device('cuda:0')
self.detetection_model = self.detetection_model.to(device)
self.tracked_stracks = [] # type: list[STrack]
self.lost_stracks = [] # type: list[STrack]
self.removed_stracks = [] # type: list[STrack]
self.frame_id = 0
self.det_thresh = opt.conf_thres
self.buffer_size = int(frame_rate / 30.0 * opt.track_buffer)
self.max_time_lost = self.buffer_size
self.max_per_image = opt.K
self.kalman_filter = KalmanFilter()
self.polygon = polygon
self.paths = paths
self.polygon2 = polygon2
self.line2 = [self.polygon[1], self.polygon[2]]
self.line1 = [self.polygon[4], self.polygon[3]] if len(
self.polygon) == 5 else [self.polygon[0], self.polygon[3]] if len(
self.polygon) == 4 else None
self.two_polygon_system = False
self.warmup_frame = 6 if self.two_polygon_system else 0
self.virtual_polygon = [[0, 573], [0, 109], [1270, 109], [1270, 573]]
def __init__(self, opt):
self.opt = opt
self.tracked_stracks = [] # type: list[STrack]
self.frame_id = 0
self.kalman_filter = KalmanFilter()
