def demo(opt):
result_root = opt.output_root if opt.output_root != '' else '.'
mkdir_if_missing(result_root)
logger.info('Starting tracking...')
dataloader = datasets.LoadVideo(opt.input_video, opt.img_size)
dataloader.cap.set(cv2.CAP_PROP_POS_MSEC, round(1000 * 120))
result_filename = os.path.join(result_root, 'results.txt')
frame_rate = dataloader.frame_rate
frame_dir = None if opt.output_format == 'text' else osp.join(
result_root, 'frame')
eval_seq(opt,
dataloader,
'mot',
result_filename,
save_dir=frame_dir,
show_image=False,
frame_rate=frame_rate)
if opt.output_format == 'video':
output_video_path = osp.join(result_root, 'result.mp4')
cmd_str = 'ffmpeg -f image2 -i {}/%05d.jpg -b 5000k -c:v mpeg4 {}'.format(
osp.join(result_root, 'frame'), output_video_path)
os.system(cmd_str)
def demo(opt):
tracker = JDETracker(opt, frame_rate=30) # What is JDE Tracker?
result_root = opt.output_root if opt.output_root != '' else '.'
mkdir_if_missing(result_root)
logger.info('Starting detection...')
root_dir = '/datanew/hwb/data/Football/SoftWare/0'
channels = regular_videoName(root_dir)
for channel in channels.keys():
video_name = channels[channel]
print('Starting to detect {}/{}'.format(root_dir, video_name))
input_video = os.path.join(root_dir, video_name)
dataloader = datasets.LoadVideo(input_video, opt.img_size, gap=1000)
dataloader.cap.set(cv2.CAP_PROP_POS_MSEC, round(1000 * 120))
result_filename = os.path.join(result_root, 'results.txt')
# frame_rate = dataloader.frame_rate
frame_dir = os.path.join(root_dir, 'detection', video_name[0:4])
os.makedirs(frame_dir, exist_ok=True)
# detect(opt,tracker,dataloader, 'mot', result_filename, save_dir=frame_dir, show_image=False)
detect(opt,
tracker,
dataloader,
dir_id=1,
save_dir=frame_dir,
show_image=True)
def eval_seq(opt,
dataloader,
data_type,
result_filename,
save_dir=None,
show_image=True,
Input_tracker=None,
frame_rate=30):
if save_dir:
mkdir_if_missing(save_dir)
if Input_tracker == None:
tracker = JDETracker(opt,
frame_rate=frame_rate) # What is JDE Tracker?
else:
tracker = Input_tracker
timer = Timer()
results = []
frame_id = 0
for path, img, img0 in dataloader:
timer.tic()
blob = torch.from_numpy(img).cuda().unsqueeze(0)
online_targets = tracker.update(blob, img0)
online_tlwhs = []
online_ids = []
for t in online_targets:
tlwh = t.tlwh
tid = t.track_id
vertical = tlwh[2] / tlwh[3] > 1.6
if tlwh[2] * tlwh[3] > opt.min_box_area and not vertical:
online_tlwhs.append(tlwh)
online_ids.append(tid)
timer.toc()
# save results
results.append((frame_id + 1, online_tlwhs, online_ids))
if show_image or save_dir is not None:
online_im = vis.plot_tracking(img0,
online_tlwhs,
online_ids,
frame_id=frame_id,
fps=1. / timer.average_time)
if show_image:
cv2.imshow('online_im', online_im)
if save_dir is not None:
cv2.imwrite(os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)),
online_im)
frame_id += 1
logger.info('Processing frame {} ({:.2f} fps)'.format(
frame_id, 1. / max(1e-5, timer.average_time)))
# save results
write_results(result_filename, results, data_type)
return frame_id, timer.average_time, timer.calls
def detect(opt, tracker, dataloader, dir_id, save_dir=None, show_image=True):
if save_dir:
mkdir_if_missing(save_dir)
timer = Timer()
results = []
frame_id = 0
save_dir_subimgs = os.path.join(save_dir, 'subimg')
os.makedirs(save_dir_subimgs, exist_ok=True)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(os.path.join(save_dir, 'out_put.avi'), fourcc, 20.0,
(1920, 1080), True)
for path, img, img0 in dataloader:
if frame_id % 20 == 0:
logger.info('Processing frame {} ({:.2f} fps)'.format(
frame_id, 1. / max(1e-5, timer.average_time)))
# run tracking
timer.tic()
blob = torch.from_numpy(img).cuda().unsqueeze(0)
[dets,
id_feature] = tracker.update_for_detection(blob, img0, save_dir,
frame_id)
timer.toc()
# save results
results.append((frame_id + 1, dets, id_feature))
if show_image or save_dir is not None:
online_im = vis.plot_detections(img0, dets, save_dir, dir_id,
frame_id)
if show_image:
cv2.imshow('online_im', online_im)
if save_dir is not None:
cv2.imwrite(os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)),
online_im)
frame_id += 1
# save results
# write_results(result_filename, results, data_type)
return frame_id, timer.average_time, timer.calls
def main(opt,
data_root='/data/MOT16/train',
det_root=None,
seqs=('MOT16-05', ),
exp_name='demo',
save_images=False,
save_videos=False,
show_image=True):
logger.setLevel(logging.INFO)
result_root = os.path.join(data_root, '..', 'results', exp_name)
mkdir_if_missing(result_root)
data_type = 'mot'
# run tracking
accs = []
n_frame = 0
timer_avgs, timer_calls = [], []
for seq in seqs:
output_dir = os.path.join(data_root, '..', 'outputs', exp_name,
seq) if save_images or save_videos else None
logger.info('start seq: {}'.format(seq))
dataloader = datasets.LoadImages(osp.join(data_root, seq, 'img1'),
opt.img_size)
result_filename = os.path.join(result_root, '{}.txt'.format(seq))
meta_info = open(os.path.join(data_root, seq, 'seqinfo.ini')).read()
frame_rate = int(meta_info[meta_info.find('frameRate') +
10:meta_info.find('\nseqLength')])
nf, ta, tc = eval_seq(opt,
dataloader,
data_type,
result_filename,
save_dir=output_dir,
show_image=show_image,
frame_rate=frame_rate)
n_frame += nf
timer_avgs.append(ta)
timer_calls.append(tc)
# eval
logger.info('Evaluate seq: {}'.format(seq))
evaluator = Evaluator(data_root, seq, data_type)
accs.append(evaluator.eval_file(result_filename))
if save_videos:
output_video_path = osp.join(output_dir, '{}.mp4'.format(seq))
cmd_str = 'ffmpeg -f image2 -i {}/%05d.jpg -c:v copy {}'.format(
output_dir, output_video_path)
os.system(cmd_str)
timer_avgs = np.asarray(timer_avgs)
timer_calls = np.asarray(timer_calls)
all_time = np.dot(timer_avgs, timer_calls)
avg_time = all_time / np.sum(timer_calls)
logger.info('Time elapsed: {:.2f} seconds, FPS: {:.2f}'.format(
all_time, 1.0 / avg_time))
# get summary
metrics = mm.metrics.motchallenge_metrics
mh = mm.metrics.create()
summary = Evaluator.get_summary(accs, seqs, metrics)
strsummary = mm.io.render_summary(summary,
formatters=mh.formatters,
namemap=mm.io.motchallenge_metric_names)
print(strsummary)
Evaluator.save_summary(
summary, os.path.join(result_root, 'summary_{}.xlsx'.format(exp_name)))
def Short_track_eval(opt,
dataloader,
data_type,
result_filename,
target_frame,
reference_point,
save_dir=None,
show_image=True,
Input_tracker=None,
frame_rate=30):
if save_dir:
mkdir_if_missing(save_dir)
if Input_tracker == None:
tracker = JDETracker(opt,
frame_rate=frame_rate) # What is JDE Tracker?
else:
tracker = Input_tracker
timer = Timer()
results = []
frame_id = 0
img0_array = []
for path, img, img0 in dataloader:
timer.tic()
blob = torch.from_numpy(img).cuda().unsqueeze(0)
online_targets = tracker.update(blob, img0)
online_tlwhs = []
online_ids = []
online_ReID_features = []
for t in online_targets:
tlwh = t.tlwh
tid = t.track_id
ReID_feature = t.curr_feat
vertical = tlwh[2] / tlwh[3] > 1.6 # w / h > 1.6
if tlwh[2] * tlwh[3] > opt.min_box_area and not vertical:
online_tlwhs.append(tlwh)
online_ids.append(tid)
online_ReID_features.append(ReID_feature)
timer.toc()
# save results
results.append(
(frame_id + 1, online_tlwhs, online_ids, online_ReID_features))
img0_array.append(img0)
# if show_image or save_dir is not None:
# online_im = vis.plot_tracking(img0, online_tlwhs, online_ids, frame_id=frame_id,
# fps=1. / timer.average_time)
# if show_image:
# cv2.imshow('online_im', online_im)
# if save_dir is not None:
# cv2.imwrite(os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)), online_im)
frame_id += 1
for bias in [0, 2, -2]: # 总能检测到的?
input_result = results[target_frame + bias]
if len(input_result[1]) == 0: # 有可能目标帧没有检测到，一个目标都没有。
target_id = None
continue
new_reference_point, target_id = sort_by_point(
results[target_frame + bias], reference_point)
if target_id != None:
break
# 如果前中后三帧都没有检测到，那就说明这个动作区分不开了。 放弃了。
if target_id == None:
# 目标不存在
return None
# 把每个sub_box提取出来。
for r_index, result in enumerate(results):
img0 = img0_array[r_index]
I_h, I_w, _ = img0.shape
bboxes = result[1]
ids = result[2]
for id_index, id in enumerate(ids):
if id != target_id:
continue
box = bboxes[id_index]
x1, y1, w, h = box
intbox = tuple(
map(int,
(max(0, x1), max(0, y1), min(x1 + w, I_w), min(
y1 + h, I_h))))
# print(intbox)
sub_img = img0[intbox[1]:intbox[3], intbox[0]:intbox[2]]
cv2.imwrite(
os.path.join(save_dir, '{}_{}.jpg'.format(r_index, id)),
sub_img)
logger.info('Processing frame {} ({:.2f} fps)'.format(
frame_id, 1. / max(1e-5, timer.average_time)))
# save results
write_results(result_filename, results, data_type)
return frame_id, timer.average_time, timer.calls