f4334277
 Hu Chunming
提交3rdparty
|
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
|
# To use Inference Engine backend, specify location of plugins:
# source /opt/intel/computer_vision_sdk/bin/setupvars.sh
import cv2 as cv
import numpy as np
import argparse
parser = argparse.ArgumentParser(
description='This script is used to demonstrate OpenPose human pose estimation network '
'from https://github.com/CMU-Perceptual-Computing-Lab/openpose project using OpenCV. '
'The sample and model are simplified and could be used for a single person on the frame.')
parser.add_argument('--input', help='Path to image or video. Skip to capture frames from camera')
parser.add_argument('--proto', help='Path to .prototxt')
parser.add_argument('--model', help='Path to .caffemodel')
parser.add_argument('--dataset', help='Specify what kind of model was trained. '
'It could be (COCO, MPI, HAND) depends on dataset.')
parser.add_argument('--thr', default=0.1, type=float, help='Threshold value for pose parts heat map')
parser.add_argument('--width', default=368, type=int, help='Resize input to specific width.')
parser.add_argument('--height', default=368, type=int, help='Resize input to specific height.')
parser.add_argument('--scale', default=0.003922, type=float, help='Scale for blob.')
args = parser.parse_args()
if args.dataset == 'COCO':
BODY_PARTS = { "Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,
"LEye": 15, "REar": 16, "LEar": 17, "Background": 18 }
POSE_PAIRS = [ ["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],
["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],
["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],
["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"] ]
elif args.dataset == 'MPI':
BODY_PARTS = { "Head": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "Chest": 14,
"Background": 15 }
POSE_PAIRS = [ ["Head", "Neck"], ["Neck", "RShoulder"], ["RShoulder", "RElbow"],
["RElbow", "RWrist"], ["Neck", "LShoulder"], ["LShoulder", "LElbow"],
["LElbow", "LWrist"], ["Neck", "Chest"], ["Chest", "RHip"], ["RHip", "RKnee"],
["RKnee", "RAnkle"], ["Chest", "LHip"], ["LHip", "LKnee"], ["LKnee", "LAnkle"] ]
elif args.dataset == 'HAND':
BODY_PARTS = { "Wrist": 0,
"ThumbMetacarpal": 1, "ThumbProximal": 2, "ThumbMiddle": 3, "ThumbDistal": 4,
"IndexFingerMetacarpal": 5, "IndexFingerProximal": 6, "IndexFingerMiddle": 7, "IndexFingerDistal": 8,
"MiddleFingerMetacarpal": 9, "MiddleFingerProximal": 10, "MiddleFingerMiddle": 11, "MiddleFingerDistal": 12,
"RingFingerMetacarpal": 13, "RingFingerProximal": 14, "RingFingerMiddle": 15, "RingFingerDistal": 16,
"LittleFingerMetacarpal": 17, "LittleFingerProximal": 18, "LittleFingerMiddle": 19, "LittleFingerDistal": 20,
}
POSE_PAIRS = [ ["Wrist", "ThumbMetacarpal"], ["ThumbMetacarpal", "ThumbProximal"],
["ThumbProximal", "ThumbMiddle"], ["ThumbMiddle", "ThumbDistal"],
["Wrist", "IndexFingerMetacarpal"], ["IndexFingerMetacarpal", "IndexFingerProximal"],
["IndexFingerProximal", "IndexFingerMiddle"], ["IndexFingerMiddle", "IndexFingerDistal"],
["Wrist", "MiddleFingerMetacarpal"], ["MiddleFingerMetacarpal", "MiddleFingerProximal"],
["MiddleFingerProximal", "MiddleFingerMiddle"], ["MiddleFingerMiddle", "MiddleFingerDistal"],
["Wrist", "RingFingerMetacarpal"], ["RingFingerMetacarpal", "RingFingerProximal"],
["RingFingerProximal", "RingFingerMiddle"], ["RingFingerMiddle", "RingFingerDistal"],
["Wrist", "LittleFingerMetacarpal"], ["LittleFingerMetacarpal", "LittleFingerProximal"],
["LittleFingerProximal", "LittleFingerMiddle"], ["LittleFingerMiddle", "LittleFingerDistal"] ]
else:
raise(Exception("you need to specify either 'COCO', 'MPI', or 'Hand' in args.dataset"))
inWidth = args.width
inHeight = args.height
inScale = args.scale
net = cv.dnn.readNet(cv.samples.findFile(args.proto), cv.samples.findFile(args.model))
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
inp = cv.dnn.blobFromImage(frame, inScale, (inWidth, inHeight),
(0, 0, 0), swapRB=False, crop=False)
net.setInput(inp)
out = net.forward()
assert(len(BODY_PARTS) <= out.shape[1])
points = []
for i in range(len(BODY_PARTS)):
# Slice heatmap of corresponding body's part.
heatMap = out[0, i, :, :]
# Originally, we try to find all the local maximums. To simplify a sample
# we just find a global one. However only a single pose at the same time
# could be detected this way.
_, conf, _, point = cv.minMaxLoc(heatMap)
x = (frameWidth * point[0]) / out.shape[3]
y = (frameHeight * point[1]) / out.shape[2]
# Add a point if it's confidence is higher than threshold.
points.append((int(x), int(y)) if conf > args.thr else None)
for pair in POSE_PAIRS:
partFrom = pair[0]
partTo = pair[1]
assert(partFrom in BODY_PARTS)
assert(partTo in BODY_PARTS)
idFrom = BODY_PARTS[partFrom]
idTo = BODY_PARTS[partTo]
if points[idFrom] and points[idTo]:
cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
t, _ = net.getPerfProfile()
freq = cv.getTickFrequency() / 1000
cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv.imshow('OpenPose using OpenCV', frame)
|
