This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 758
/
visualization.py
209 lines (174 loc) · 8.06 KB
/
visualization.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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
# Copyright (c) 2018-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
#
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation, writers
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
import subprocess as sp
def get_resolution(filename):
command = ['ffprobe', '-v', 'error', '-select_streams', 'v:0',
'-show_entries', 'stream=width,height', '-of', 'csv=p=0', filename]
with sp.Popen(command, stdout=sp.PIPE, bufsize=-1) as pipe:
for line in pipe.stdout:
w, h = line.decode().strip().split(',')
return int(w), int(h)
def get_fps(filename):
command = ['ffprobe', '-v', 'error', '-select_streams', 'v:0',
'-show_entries', 'stream=r_frame_rate', '-of', 'csv=p=0', filename]
with sp.Popen(command, stdout=sp.PIPE, bufsize=-1) as pipe:
for line in pipe.stdout:
a, b = line.decode().strip().split('/')
return int(a) / int(b)
def read_video(filename, skip=0, limit=-1):
w, h = get_resolution(filename)
command = ['ffmpeg',
'-i', filename,
'-f', 'image2pipe',
'-pix_fmt', 'rgb24',
'-vsync', '0',
'-vcodec', 'rawvideo', '-']
i = 0
with sp.Popen(command, stdout = sp.PIPE, bufsize=-1) as pipe:
while True:
data = pipe.stdout.read(w*h*3)
if not data:
break
i += 1
if i > limit and limit != -1:
continue
if i > skip:
yield np.frombuffer(data, dtype='uint8').reshape((h, w, 3))
def downsample_tensor(X, factor):
length = X.shape[0]//factor * factor
return np.mean(X[:length].reshape(-1, factor, *X.shape[1:]), axis=1)
def render_animation(keypoints, keypoints_metadata, poses, skeleton, fps, bitrate, azim, output, viewport,
limit=-1, downsample=1, size=6, input_video_path=None, input_video_skip=0):
"""
TODO
Render an animation. The supported output modes are:
-- 'interactive': display an interactive figure
(also works on notebooks if associated with %matplotlib inline)
-- 'html': render the animation as HTML5 video. Can be displayed in a notebook using HTML(...).
-- 'filename.mp4': render and export the animation as an h264 video (requires ffmpeg).
-- 'filename.gif': render and export the animation a gif file (requires imagemagick).
"""
plt.ioff()
fig = plt.figure(figsize=(size*(1 + len(poses)), size))
ax_in = fig.add_subplot(1, 1 + len(poses), 1)
ax_in.get_xaxis().set_visible(False)
ax_in.get_yaxis().set_visible(False)
ax_in.set_axis_off()
ax_in.set_title('Input')
ax_3d = []
lines_3d = []
trajectories = []
radius = 1.7
for index, (title, data) in enumerate(poses.items()):
ax = fig.add_subplot(1, 1 + len(poses), index+2, projection='3d')
ax.view_init(elev=15., azim=azim)
ax.set_xlim3d([-radius/2, radius/2])
ax.set_zlim3d([0, radius])
ax.set_ylim3d([-radius/2, radius/2])
try:
ax.set_aspect('equal')
except NotImplementedError:
ax.set_aspect('auto')
ax.set_xticklabels([])
ax.set_yticklabels([])
ax.set_zticklabels([])
ax.dist = 7.5
ax.set_title(title) #, pad=35
ax_3d.append(ax)
lines_3d.append([])
trajectories.append(data[:, 0, [0, 1]])
poses = list(poses.values())
# Decode video
if input_video_path is None:
# Black background
all_frames = np.zeros((keypoints.shape[0], viewport[1], viewport[0]), dtype='uint8')
else:
# Load video using ffmpeg
all_frames = []
for f in read_video(input_video_path, skip=input_video_skip, limit=limit):
all_frames.append(f)
effective_length = min(keypoints.shape[0], len(all_frames))
all_frames = all_frames[:effective_length]
keypoints = keypoints[input_video_skip:] # todo remove
for idx in range(len(poses)):
poses[idx] = poses[idx][input_video_skip:]
if fps is None:
fps = get_fps(input_video_path)
if downsample > 1:
keypoints = downsample_tensor(keypoints, downsample)
all_frames = downsample_tensor(np.array(all_frames), downsample).astype('uint8')
for idx in range(len(poses)):
poses[idx] = downsample_tensor(poses[idx], downsample)
trajectories[idx] = downsample_tensor(trajectories[idx], downsample)
fps /= downsample
initialized = False
image = None
lines = []
points = None
if limit < 1:
limit = len(all_frames)
else:
limit = min(limit, len(all_frames))
parents = skeleton.parents()
def update_video(i):
nonlocal initialized, image, lines, points
for n, ax in enumerate(ax_3d):
ax.set_xlim3d([-radius/2 + trajectories[n][i, 0], radius/2 + trajectories[n][i, 0]])
ax.set_ylim3d([-radius/2 + trajectories[n][i, 1], radius/2 + trajectories[n][i, 1]])
# Update 2D poses
joints_right_2d = keypoints_metadata['keypoints_symmetry'][1]
colors_2d = np.full(keypoints.shape[1], 'black')
colors_2d[joints_right_2d] = 'red'
if not initialized:
image = ax_in.imshow(all_frames[i], aspect='equal')
for j, j_parent in enumerate(parents):
if j_parent == -1:
continue
if len(parents) == keypoints.shape[1] and keypoints_metadata['layout_name'] != 'coco':
# Draw skeleton only if keypoints match (otherwise we don't have the parents definition)
lines.append(ax_in.plot([keypoints[i, j, 0], keypoints[i, j_parent, 0]],
[keypoints[i, j, 1], keypoints[i, j_parent, 1]], color='pink'))
col = 'red' if j in skeleton.joints_right() else 'black'
for n, ax in enumerate(ax_3d):
pos = poses[n][i]
lines_3d[n].append(ax.plot([pos[j, 0], pos[j_parent, 0]],
[pos[j, 1], pos[j_parent, 1]],
[pos[j, 2], pos[j_parent, 2]], zdir='z', c=col))
points = ax_in.scatter(*keypoints[i].T, 10, color=colors_2d, edgecolors='white', zorder=10)
initialized = True
else:
image.set_data(all_frames[i])
for j, j_parent in enumerate(parents):
if j_parent == -1:
continue
if len(parents) == keypoints.shape[1] and keypoints_metadata['layout_name'] != 'coco':
lines[j-1][0].set_data([keypoints[i, j, 0], keypoints[i, j_parent, 0]],
[keypoints[i, j, 1], keypoints[i, j_parent, 1]])
for n, ax in enumerate(ax_3d):
pos = poses[n][i]
lines_3d[n][j-1][0].set_xdata(np.array([pos[j, 0], pos[j_parent, 0]]))
lines_3d[n][j-1][0].set_ydata(np.array([pos[j, 1], pos[j_parent, 1]]))
lines_3d[n][j-1][0].set_3d_properties(np.array([pos[j, 2], pos[j_parent, 2]]), zdir='z')
points.set_offsets(keypoints[i])
print('{}/{} '.format(i, limit), end='\r')
fig.tight_layout()
anim = FuncAnimation(fig, update_video, frames=np.arange(0, limit), interval=1000/fps, repeat=False)
if output.endswith('.mp4'):
Writer = writers['ffmpeg']
writer = Writer(fps=fps, metadata={}, bitrate=bitrate)
anim.save(output, writer=writer)
elif output.endswith('.gif'):
anim.save(output, dpi=80, writer='imagemagick')
else:
raise ValueError('Unsupported output format (only .mp4 and .gif are supported)')
plt.close()