/
webcam_3D.py
145 lines (122 loc) · 4.33 KB
/
webcam_3D.py
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
"""
3D pose estimation with tf open pose and pyopenGL
"""
import numpy as np
import pyqtgraph.opengl as gl
import pyqtgraph as pg
from pyqtgraph.Qt import QtCore, QtGui
import sys
import cv2
import time
import os
from tf_pose.estimator2 import TfPoseEstimator
from tf_pose.networks import get_graph_path, model_wh
from lifting.prob_model import Prob3dPose
import lifting.common
class Terrain(object):
def __init__(self):
"""
Initialize the graphics window and mesh surface
"""
# setup the view window
self.app = QtGui.QApplication(sys.argv)
self.window = gl.GLViewWidget()
self.window.setWindowTitle('Terrain')
self.window.setGeometry(0, 110, 1920, 1080)
self.window.setCameraPosition(distance=30, elevation=12)
self.window.show()
gx = gl.GLGridItem()
gy = gl.GLGridItem()
gz = gl.GLGridItem()
gx.rotate(90, 0, 1, 0)
gy.rotate(90, 1, 0, 0)
gx.translate(-10, 0, 0)
gy.translate(0, -10, 0)
gz.translate(0, 0, -10)
self.window.addItem(gx)
self.window.addItem(gy)
self.window.addItem(gz)
modeln = 'mobilenet_thin'
modelr = '432x368'
camera = 0
self.lines = {}
self.connection = [
[0, 1], [1, 2], [2, 3], [0, 4], [4, 5], [5, 6],
[0, 7], [7, 8], [8, 9], [9, 10], [8, 11], [11, 12],
[12, 13], [8, 14], [14, 15], [15, 16]
]
w, h = model_wh(modelr)
self.e = TfPoseEstimator(get_graph_path(modeln), target_size=(w, h))
self.cam = cv2.VideoCapture(camera)
ret_val, image = self.cam.read()
self.poseLifting = Prob3dPose('./skeleton_humanactivity/lifting/models/prob_model_params.mat')
keypoints = self.mesh(image)
self.points = gl.GLScatterPlotItem(
pos=keypoints,
color=pg.glColor((0, 255, 0)),
size=15
)
self.window.addItem(self.points)
for n, pts in enumerate(self.connection):
self.lines[n] = gl.GLLinePlotItem(
pos=np.array([keypoints[p] for p in pts]),
color=pg.glColor((0, 0, 255)),
width=3,
antialias=True
)
self.window.addItem(self.lines[n])
def mesh(self, image):
image_h, image_w = image.shape[:2]
width = 640
height = 480
pose_2d_mpiis = []
visibilities = []
humans = self.e.inference(image)
# humans = self.e.inference(image, scales=[None])
for human in humans:
pose_2d_mpii, visibility = lifting.common.MPIIPart.from_coco(human)
pose_2d_mpiis.append(
[(int(x * width + 0.5), int(y * height + 0.5)) for x, y in pose_2d_mpii]
)
visibilities.append(visibility)
pose_2d_mpiis = np.array(pose_2d_mpiis)
visibilities = np.array(visibilities)
transformed_pose2d, weights = self.poseLifting.transform_joints(
pose_2d_mpiis, visibilities
)
pose_3d = self.poseLifting.compute_3d(transformed_pose2d, weights)
keypoints = pose_3d[0].transpose()
return keypoints / 80
def update(self):
"""
update the mesh and shift the noise each time
"""
ret_val, image = self.cam.read()
try:
keypoints = self.mesh(image)
except AssertionError:
print('body not in image')
else:
self.points.setData(pos=keypoints)
for n, pts in enumerate(self.connection):
self.lines[n].setData(
pos=np.array([keypoints[p] for p in pts])
)
def start(self):
"""
get the graphics window open and setup
"""
if (sys.flags.interactive != 1) or not hasattr(QtCore, 'PYQT_VERSION'):
QtGui.QApplication.instance().exec_()
def animation(self, frametime=10):
"""
calls the update method to run in a loop
"""
timer = QtCore.QTimer()
timer.timeout.connect(self.update)
timer.start(frametime)
self.start()
if __name__ == '__main__':
os.chdir('..')
t = Terrain()
t.animation()