-
Notifications
You must be signed in to change notification settings - Fork 0
/
ocv.py
281 lines (218 loc) · 8.32 KB
/
ocv.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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
import cv2
import argparse
import asyncio
import json
import logging
import os
import platform
import ssl
import fractions
import time
from threading import Thread
from typing import Tuple, Union
from aiohttp import web
from aiortc import MediaStreamTrack
from aiortc import RTCPeerConnection, RTCSessionDescription
from aiortc.contrib.media import MediaRelay
from aiortc.rtcrtpsender import RTCRtpSender
from av import VideoFrame
ROOT = os.path.dirname(__file__)
VIDEO_CLOCK_RATE = 90000
VIDEO_PTIME = 1 / 30 # 1/fps
VIDEO_TIME_BASE = fractions.Fraction(1, VIDEO_CLOCK_RATE)
relay = None
webcam = None
fetched_frame = None
class VideoTransformTrack(MediaStreamTrack):
"""
A video stream track that transforms frames from an another track.
"""
kind = "video"
def __init__(self, transform):
super().__init__() # don't forget this!
self.transform = transform
self.myframe = None
self.fnum = 0
async def next_timestamp(self) -> Tuple[int, fractions.Fraction]:
if self.readyState != "live":
raise MediaStreamError
if hasattr(self, "_timestamp"):
self._timestamp += int((VIDEO_PTIME * VIDEO_CLOCK_RATE)*1.0)
curtime = time.time()
#self._timestamp += int((curtime - self._ptime)*VIDEO_CLOCK_RATE)
self._ptime = curtime
wait = self._start + (self._timestamp / VIDEO_CLOCK_RATE) - curtime
await asyncio.sleep(wait)
else:
self._start = time.time()
self._ptime = self._start
self._timestamp = 0
return self._timestamp, VIDEO_TIME_BASE
async def recv(self):
global fetched_frame
pts, time_base = await self.next_timestamp()
print('frame %d'%self.fnum)
frame = VideoFrame.from_ndarray(last_frame, format="bgr24")
self.fnum += 1
frame.pts = pts
frame.time_base = time_base
if self.transform == "cartoon":
img = frame.to_ndarray(format="bgr24")
# prepare color
img_color = cv2.pyrDown(cv2.pyrDown(img))
for _ in range(6):
img_color = cv2.bilateralFilter(img_color, 9, 9, 7)
img_color = cv2.pyrUp(cv2.pyrUp(img_color))
# prepare edges
img_edges = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
img_edges = cv2.adaptiveThreshold(
cv2.medianBlur(img_edges, 7),
255,
cv2.ADAPTIVE_THRESH_MEAN_C,
cv2.THRESH_BINARY,
9,
2,
)
img_edges = cv2.cvtColor(img_edges, cv2.COLOR_GRAY2RGB)
# combine color and edges
img = cv2.bitwise_and(img_color, img_edges)
# rebuild a VideoFrame, preserving timing information
new_frame = VideoFrame.from_ndarray(img, format="bgr24")
new_frame.pts = frame.pts
new_frame.time_base = frame.time_base
return new_frame
elif self.transform == "edges":
# perform edge detection
img = frame.to_ndarray(format="bgr24")
img = cv2.cvtColor(cv2.Canny(img, 100, 200), cv2.COLOR_GRAY2BGR)
# rebuild a VideoFrame, preserving timing information
new_frame = VideoFrame.from_ndarray(img, format="bgr24")
new_frame.pts = frame.pts
new_frame.time_base = frame.time_base
return new_frame
elif self.transform == "rotate":
# rotate image
img = frame.to_ndarray(format="bgr24")
rows, cols, _ = img.shape
M = cv2.getRotationMatrix2D((cols / 2, rows / 2), frame.time * 45, 1)
img = cv2.warpAffine(img, M, (cols, rows))
# rebuild a VideoFrame, preserving timing information
new_frame = VideoFrame.from_ndarray(img, format="bgr24")
new_frame.pts = frame.pts
new_frame.time_base = frame.time_base
return new_frame
else:
return frame
def create_local_tracks():
global relay, webcam
relay = MediaRelay()
sub = relay.subscribe(webcam)
return None, sub
def force_codec(pc, sender, forced_codec):
kind = forced_codec.split("/")[0]
codecs = RTCRtpSender.getCapabilities(kind).codecs
transceiver = next(t for t in pc.getTransceivers() if t.sender == sender)
transceiver.setCodecPreferences(
[codec for codec in codecs if codec.mimeType == forced_codec]
)
async def index(request):
content = open(os.path.join(ROOT, "index.html"), "r").read()
return web.Response(content_type="text/html", text=content)
async def javascript(request):
content = open(os.path.join(ROOT, "client.js"), "r").read()
return web.Response(content_type="application/javascript", text=content)
async def offer(request):
params = await request.json()
offer = RTCSessionDescription(sdp=params["sdp"], type=params["type"])
pc = RTCPeerConnection()
pcs.add(pc)
@pc.on("connectionstatechange")
async def on_connectionstatechange():
print("Connection state is %s" % pc.connectionState)
if pc.connectionState == "failed":
await pc.close()
pcs.discard(pc)
# open media source
audio, video = create_local_tracks()
if audio:
audio_sender = pc.addTrack(audio)
if args.audio_codec:
force_codec(pc, audio_sender, args.audio_codec)
elif args.play_without_decoding:
raise Exception("You must specify the audio codec using --audio-codec")
if video:
video_sender = pc.addTrack(video)
print('added track')
if args.video_codec:
force_codec(pc, video_sender, args.video_codec)
elif args.play_without_decoding:
raise Exception("You must specify the video codec using --video-codec")
await pc.setRemoteDescription(offer)
answer = await pc.createAnswer()
await pc.setLocalDescription(answer)
return web.Response(
content_type="application/json",
text=json.dumps(
{"sdp": pc.localDescription.sdp, "type": pc.localDescription.type}
),
)
pcs = set()
async def on_shutdown(app):
# close peer connections
coros = [pc.close() for pc in pcs]
await asyncio.gather(*coros)
pcs.clear()
running = True
def fetch_frames(cap):
global last_frame
global running
while running:
ok, last_frame = cap.read()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="WebRTC webcam demo")
parser.add_argument("--cert-file", help="SSL certificate file (for HTTPS)")
parser.add_argument("--key-file", help="SSL key file (for HTTPS)")
parser.add_argument("--play-from", help="Read the media from a file and sent it."),
parser.add_argument(
"--play-without-decoding",
help=(
"Read the media without decoding it (experimental). "
"For now it only works with an MPEGTS container with only H.264 video."
),
action="store_true",
)
parser.add_argument(
"--host", default="0.0.0.0", help="Host for HTTP server (default: 0.0.0.0)"
)
parser.add_argument(
"--port", type=int, default=8080, help="Port for HTTP server (default: 8080)"
)
parser.add_argument("--verbose", "-v", action="count")
parser.add_argument(
"--audio-codec", help="Force a specific audio codec (e.g. audio/opus)"
)
parser.add_argument(
"--video-codec", help="Force a specific video codec (e.g. video/H264)"
)
args = parser.parse_args()
if args.verbose:
logging.basicConfig(level=logging.DEBUG)
else:
logging.basicConfig(level=logging.INFO)
if args.cert_file:
ssl_context = ssl.SSLContext()
ssl_context.load_cert_chain(args.cert_file, args.key_file)
else:
ssl_context = None
opencv_cap = cv2.VideoCapture(0)
thr = Thread(target=fetch_frames, args=(opencv_cap,))
thr.start()
webcam = VideoTransformTrack('')
app = web.Application()
app.on_shutdown.append(on_shutdown)
app.router.add_get("/", index)
app.router.add_get("/client.js", javascript)
app.router.add_post("/offer", offer)
web.run_app(app, host=args.host, port=args.port, ssl_context=ssl_context)
running = False
thr.join()