[英]Stream rtsp video from opencv in python in h.264 with low latency
[英]How to use pyav or opencv to decode a live stream of raw H.264 data?
數據是通過socket接收的,沒有更多的shell,它們是純IPB幀,以NAL Header開頭(類似於00 00 00 01)。 我現在正在使用 pyav 解碼幀,但我只能在接收到第二個 pps 信息(在關鍵幀中)之后解碼數據(所以我發送到我的解碼線程的數據塊可以以 pps 和 sps 開頭),否則decode() 或 demux() 將返回錯誤“non-existing PPS 0 referenced decode_slice_header error”。
我想將數據饋送到可以記住前一個 P 幀的持續解碼器,因此在饋送一個 B 幀后,解碼器返回一個解碼的視頻幀。 或者某種形式的 IO 可以作為容器打開並通過另一個線程繼續向其中寫入數據。
這是我的關鍵代碼:
#read thread... read until get a key frame, then make a new io.BytesIO() to store the new data.
rawFrames = io.BytesIO()
while flag_get_keyFrame:()
....
content= socket.recv(2048)
rawFrames.write(content)
....
#decode thread... decode content between two key frames
....
rawFrames.seek(0)
container = av.open(rawFrames)
for packet in container.demux():
for frame in packet.decode():
self.frames.append(frame)
....
我的代碼將播放視頻,但有 3~4 秒的延遲。 所以我不會把所有的東西都放在這里,因為我知道它實際上並沒有達到我想要實現的目標。 我想在收到第一個關鍵幀后播放視頻,並在收到后立即解碼以下幀。 Pyav opencv ffmpeg 或其他東西,我怎樣才能實現我的目標?
它通常會延遲 3~4 秒,因為您正在讀取編碼數據並通過 CPU 對其進行解碼需要時間。
經過數小時找到這個問題的答案。 我自己想通了。
對於單線程,您可以執行以下操作:
rawData = io.BytesIO()
container = av.open(rawData, format="h264", mode='r')
cur_pos = 0
while True:
data = await websocket.recv()
rawData.write(data)
rawData.seek(cur_pos)
for packet in container.demux():
if packet.size == 0:
continue
cur_pos += packet.size
for frame in packet.decode():
self.frames.append(frame)
這就是基本思想。 我已經制定了一個將接收線程和解碼線程分開的通用版本。 如果 CPU 跟不上解碼速度,代碼也會跳幀,並從下一個關鍵幀開始解碼(這樣就不會出現撕裂的綠屏效果)。 這是代碼的完整版本:
import asyncio
import av
import cv2
import io
from multiprocessing import Process, Queue, Event
import time
import websockets
def display_frame(frame, start_time, pts_offset, frame_rate):
if frame.pts is not None:
play_time = (frame.pts - pts_offset) * frame.time_base.numerator / frame.time_base.denominator
if start_time is not None:
current_time = time.time() - start_time
time_diff = play_time - current_time
if time_diff > 1 / frame_rate:
return False
if time_diff > 0:
time.sleep(time_diff)
img = frame.to_ndarray(format='bgr24')
cv2.imshow('Video', img)
return True
def get_pts(frame):
return frame.pts
def render(terminated, data_queue):
rawData = io.BytesIO()
cur_pos = 0
frames_buffer = []
start_time = None
pts_offset = None
got_key_frame = False
while not terminated.is_set():
try:
data = data_queue.get_nowait()
except:
time.sleep(0.01)
continue
rawData.write(data)
rawData.seek(cur_pos)
if cur_pos == 0:
container = av.open(rawData, mode='r')
original_codec_ctx = container.streams.video[0].codec_context
codec = av.codec.CodecContext.create(original_codec_ctx.name, 'r')
cur_pos += len(data)
dts = None
for packet in container.demux():
if packet.size == 0:
continue
dts = packet.dts
if pts_offset is None:
pts_offset = packet.pts
if not got_key_frame and packet.is_keyframe:
got_key_frame = True
if data_queue.qsize() > 8 and not packet.is_keyframe:
got_key_frame = False
continue
if not got_key_frame:
continue
frames = codec.decode(packet)
if start_time is None:
start_time = time.time()
frames_buffer += frames
frames_buffer.sort(key=get_pts)
for frame in frames_buffer:
if display_frame(frame, start_time, pts_offset, codec.framerate):
frames_buffer.remove(frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if dts is not None:
container.seek(25000)
rawData.seek(cur_pos)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
terminated.set()
cv2.destroyAllWindows()
async def receive_encoded_video(websocket, path):
data_queue = Queue()
terminated = Event()
p = Process(
target=render,
args=(terminated, data_queue)
)
p.start()
while not terminated.is_set():
try:
data = await websocket.recv()
except:
break
data_queue.put(data)
terminated.set()
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.