def main():
args = parse_args()
update_config(cfg, args)
# cudnn related setting
cudnn.benchmark = cfg.CUDNN.BENCHMARK
torch.backends.cudnn.deterministic = cfg.CUDNN.DETERMINISTIC
torch.backends.cudnn.enabled = cfg.CUDNN.ENABLED
########## 加载human detecotor model
from lib.detector.mmdetection.high_api import load_model
human_model = load_model()
from lib.detector.mmdetection.high_api import human_boxes_get as mmd_detector
bboxs, scores = mmd_detector(human_model, args.img_input) # bboxes (N, 4) [x0, y0, x1, y1]
# bbox is coordinate location
inputs, origin_img, center, scale = PreProcess(args.img_input, bboxs, scores, cfg)
# load HRNET MODEL
model = model_load(cfg)
with torch.no_grad():
# compute output heatmap
# inputs = inputs[:,[2,1,0]]
# inputs = cv2.cvtColor(inputs, cv2.COLOR_BGR2RGB)
output = model(inputs)
# compute coordinate
preds, maxvals = get_final_preds(
cfg, output.clone().cpu().numpy(), np.asarray(center), np.asarray(scale))
image = plot_keypoint(origin_img, preds, maxvals, 0.3)
cv2.imwrite(args.img_output, image)
if args.display:
cv2.namedWindow("enhanced", cv2.WINDOW_GUI_NORMAL);
cv2.resizeWindow("enhanced", 960, 480);
cv2.imshow('enhanced', image)
cv2.waitKey(5000)
def main():
args = parse_args()
update_config(cfg, args)
if not args.camera:
# handle video
cam = cv2.VideoCapture(args.video_input)
video_length = int(cam.get(cv2.CAP_PROP_FRAME_COUNT))
else:
cam = cv2.VideoCapture(0)
video_length = 30000
ret_val, input_image = cam.read()
# Video writer
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
input_fps = cam.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter(args.video_output, fourcc, input_fps,
(input_image.shape[1], input_image.shape[0]))
#### load pose-hrnet MODEL
pose_model = model_load(cfg)
# pose_model = torch.nn.DataParallel(pose_model, device_ids=[0,1]).cuda()
pose_model.cuda()
item = 0
for i in tqdm(range(video_length - 1)):
x0 = ckpt_time()
ret_val, input_image = cam.read()
# if args.camera:
# # 为取得实时速度，每两帧取一帧预测
# if item == 0:
# item = 1
# continue
item = 0
try:
bboxs, scores = mm_det(human_model, input_image)
# bbox is coordinate location
inputs, origin_img, center, scale = PreProcess(
input_image, bboxs, scores, cfg)
except:
out.write(input_image)
cv2.namedWindow("enhanced", 0)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', input_image)
cv2.waitKey(2)
continue
with torch.no_grad():
# compute output heatmap
inputs = inputs[:, [2, 1, 0]]
output = pose_model(inputs.cuda())
# compute coordinate
preds, maxvals = get_final_preds(cfg,
output.clone().cpu().numpy(),
np.asarray(center),
np.asarray(scale))
image = plot_keypoint(origin_img, preds, maxvals, 0.1)
out.write(image)
if args.display:
######### 全屏
# out_win = "output_style_full_screen"
# cv2.namedWindow(out_win, cv2.WINDOW_NORMAL)
# cv2.setWindowProperty(out_win, cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN)
# cv2.imshow(out_win, image)
########### 指定屏幕大小
cv2.namedWindow("enhanced", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', image)
cv2.waitKey(1)
def main():
json_data = {}
args = parse_args()
update_config(cfg, args)
if not args.camera:
# handle video
cam = cv2.VideoCapture(args.video_input)
video_length = int(cam.get(cv2.CAP_PROP_FRAME_COUNT))
else:
cam = cv2.VideoCapture(1)
video_length = 30
ret_val, input_image = cam.read()
# Video writer
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
input_fps = cam.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter(args.video_output, fourcc, input_fps,
(input_image.shape[1], input_image.shape[0]))
#### load pose-hrnet MODEL
pose_model = model_load(cfg)
# pose_model = torch.nn.DataParallel(pose_model, device_ids=[0,1]).cuda()
pose_model.to(device)
item = 0
index = 0
for i in tqdm(range(video_length - 1)):
x0 = ckpt_time()
ret_val, input_image = cam.read()
# if args.camera:
# # 为取得实时速度，每两帧取一帧预测
# if item == 0:
# item = 1
# continue
item = 0
try:
detections = yolov5_model(input_image)
# print(detections)
scores = []
bboxs = []
if detections is not None:
for i, det in enumerate(detections.pred):
inputs = inputs[:, [2, 1, 0]]
output = pose_model(inputs.to(device))
for bbox in complete_bbox:
if bbox[4] > 0.25 and bbox[5] == 0:
# print("detections", complete_bbox[:4])
bboxs.append(bbox[:4])
# print("Our scores", bbox[4])
scores.append(bbox[4])
#print("Our scores", complete_bbox[4])
# bbox is coordinate location
# print("boxes", bboxs)
# print("scores", scores)
inputs, origin_img, center, scale = PreProcess(
input_image, bboxs, scores, cfg)
except:
out.write(input_image)
cv2.namedWindow("enhanced", 0)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', input_image)
cv2.waitKey(2)
continue
with torch.no_grad():
# compute output heatmap
print("We here babby ")
inputs = inputs[:, [2, 1, 0]]
output = pose_model(inputs.to(device))
# print("Output from pose mode", output)
# compute coordinate
preds, maxvals = get_final_preds(cfg,
output.clone().cpu().numpy(),
np.asarray(center),
np.asarray(scale))
json_data[index] = list()
json_data[index].append(preds.tolist())
print("Key points", preds)
index += 1
image = plot_keypoint(origin_img, preds, maxvals, 0.25)
out.write(image)
if args.display:
######### 全屏
# out_win = "output_style_full_screen"
# cv2.namedWindow(out_win, cv2.WINDOW_NORMAL)
# cv2.setWindowProperty(out_win, cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN)
# cv2.imshow(out_win, image)
########### 指定屏幕大小
cv2.namedWindow("enhanced", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', image)
cv2.waitKey(1)
with open('outputs/output.json', 'w') as json_file:
print(json_data)
json.dump(json_data, json_file)
def main():
args = parse_args()
update_config(cfg, args)
if not args.camera:
# handle video
cam = cv2.VideoCapture(args.video_input)
video_length = int(cam.get(cv2.CAP_PROP_FRAME_COUNT))
else:
cam = cv2.VideoCapture(0)
video_length = 30000
ret_val, input_image = cam.read()
# 保持长宽都是64的倍数
resize_W = int(input_image.shape[1] / 64) * 64
resize_H = int((input_image.shape[0] / input_image.shape[1] * resize_W) / 64 ) * 64
print(resize_W, resize_H)
input_image = cv2.resize(input_image, (resize_W, resize_H))
# Video writer
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
input_fps = cam.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter(args.video_output,fourcc, input_fps, (input_image.shape[1],input_image.shape[0]))
#### load optical flow model
flow_model = load_model()
#### load pose-hrnet MODEL
pose_model = model_load(cfg)
pose_model.cuda()
first_frame = 1
flow_boxs = 0
flow_kpts = 0
item = 0
for i in tqdm(range(video_length-1)):
x0 = ckpt_time()
ret_val, input_image = cam.read()
input_image = cv2.resize(input_image, (resize_W, resize_H))
if first_frame == 0:
try:
t0 = ckpt_time()
flow_result = flow_net(pre_image, input_image, flow_model)
flow_boxs, flow_kpts = flow_propagation(keypoints, flow_result)
print('每次flownet耗时：{:0.3f}'.format(time.time()- t0))
except Exception as e:
print(e)
continue
pre_image = input_image
first_frame = 0
try:
bboxs, scores = yolo_det(input_image, human_model)
# 第一帧
if i == 0:
inputs, origin_img, center, scale = PreProcess(input_image, bboxs, scores, cfg)
else:
# 本帧、上一帧 边框置信度NMS
if not (flow_bbox_scores>scores).tolist()[0][0]:
flow_boxs = bboxs
inputs, origin_img, center, scale = PreProcess(input_image, flow_boxs, scores, cfg)
except:
out.write(input_image)
cv2.namedWindow("enhanced",0);
cv2.resizeWindow("enhanced", 960, 480);
cv2.imshow('enhanced', input_image)
cv2.waitKey(2)
continue
with torch.no_grad():
# compute output heatmap
inputs = inputs[:,[2,1,0]]
output = pose_model(inputs.cuda())
# compute coordinate
preds, maxvals = get_final_preds(
cfg, output.clone().cpu().numpy(), np.asarray(center), np.asarray(scale))
# 当前帧边框置信度, 作为下一帧流边框的置信度
flow_bbox_scores = scores.copy()
if i != 1:
preds = (preds + flow_kpts) / 2
image = plot_keypoint(origin_img, preds, maxvals, 0.1)
out.write(image)
keypoints = np.concatenate((preds, maxvals), 2)
if args.display:
########### 指定屏幕大小
cv2.namedWindow("enhanced", cv2.WINDOW_GUI_NORMAL);
cv2.resizeWindow("enhanced", 960, 480);
cv2.imshow('enhanced', image)
cv2.waitKey(1)
def main():
tick = 0
args = parse_args()
update_config(cfg, args)
if not args.camera:
# handle video
cam = cv2.VideoCapture(args.video_input)
video_length = int(cam.get(cv2.CAP_PROP_FRAME_COUNT))
else:
cam = cv2.VideoCapture(0)
video_length = 30000
ret_val, input_image = cam.read()
# Video writer
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
input_fps = cam.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter(args.video_output, fourcc, input_fps,
(input_image.shape[1], input_image.shape[0]))
#### load pose-hrnet MODEL
pose_model = model_load(cfg)
pose_model.cuda()
item = 0
for i in tqdm(range(video_length - 1)):
x0 = ckpt_time()
ret_val, input_image = cam.read()
if args.camera:
# 为取得实时速度，每两帧取一帧预测
if item == 0:
item = 1
continue
item = 0
try:
bboxs, scores = yolo_det(input_image, human_model)
# bbox is coordinate location
inputs, origin_img, center, scale = PreProcess(
input_image, bboxs, scores, cfg)
except:
out.write(input_image)
cv2.namedWindow("enhanced", 0)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', input_image)
cv2.waitKey(2)
continue
with torch.no_grad():
# compute output heatmap
inputs = inputs[:, [2, 1, 0]]
output = pose_model(inputs.cuda())
# compute coordinate
preds, maxvals = get_final_preds(cfg,
output.clone().cpu().numpy(),
np.asarray(center),
np.asarray(scale))
# 平滑点
preds = smooth_filter(preds)
image = plot_keypoint(origin_img, preds, maxvals, 0.3)
if i >= 9:
out.write(image)
if args.display:
########### 指定屏幕大小
cv2.namedWindow("enhanced", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("enhanced", 960, 480)
cv2.imshow('enhanced', image)
cv2.waitKey(1)