run_motion_video.py
2.85 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
import argparse
import logging
import time
import cv2
import numpy as np
from tf_pose.estimator import TfPoseEstimator
from tf_pose.networks import get_graph_path, model_wh
logger = logging.getLogger('TfPoseEstimator-WebCam')
logger.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
formatter = logging.Formatter(
'[%(asctime)s] [%(name)s] [%(levelname)s] %(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)
fps_time = 0
def str2bool(v):
return v.lower() in ("yes", "true", "t", "1")
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='tf-pose-estimation motion Video')
parser.add_argument('--video', type=str, default='')
parser.add_argument('--resize', type=str, default='0x0',
help='if provided, resize images before they are processed. default=0x0, Recommends : 432x368 or 656x368 or 1312x736 ')
parser.add_argument('--resize-out-ratio', type=float, default=4.0,
help='if provided, resize heatmaps before they are post-processed. default=1.0')
parser.add_argument('--model', type=str, default='mobilenet_thin',
help='cmu / mobilenet_thin / mobilenet_v2_large / mobilenet_v2_small')
parser.add_argument('--show-process', type=bool, default=False,
help='for debug purpose, if enabled, speed for inference is dropped.')
parser.add_argument('--tensorrt', type=str, default="False",
help='for tensorrt process.')
args = parser.parse_args()
logger.debug('initialization %s : %s' %
(args.model, get_graph_path(args.model)))
w, h = model_wh(args.resize)
if w > 0 and h > 0:
e = TfPoseEstimator(get_graph_path(args.model), target_size=(
w, h), trt_bool=str2bool(args.tensorrt))
else:
e = TfPoseEstimator(get_graph_path(args.model), target_size=(
432, 368), trt_bool=str2bool(args.tensorrt))
logger.debug('cam read+')
cam = cv2.VideoCapture(args.video)
ret_val, image = cam.read()
logger.info('cam image=%dx%d' % (image.shape[1], image.shape[0]))
while True:
ret_val, image = cam.read()
logger.debug('image process+')
humans = e.inference(image, resize_to_default=(
w > 0 and h > 0), upsample_size=args.resize_out_ratio)
logger.debug('postprocess+')
image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
logger.debug('show+')
cv2.putText(image,
"FPS: %f" % (1.0 / (time.time() - fps_time)),
(10, 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 0), 2)
cv2.imshow('tf-pose-estimation result', image)
fps_time = time.time()
if cv2.waitKey(1) == 27:
break
logger.debug('finished+')
cv2.destroyAllWindows()