Recherche avancée

Sur d’autres sites (8072)

• How to render two videos with alpha channel in real time in pygame with synched audio ?

  21 décembre 2024, par Francesco Calderone

  I need to play two videos with synched sound in real-time with Pygame.
Pygame does not currently support video streams, so I am using a ffmpeg subprocess.
The first video is a prores422_hq. This is a background video with no alpha channel.
The second video is a prores4444 overlay video with an alpha channel, and it needs to be played in real-tim on top of the first video (with transparency).
All of this needs synched sound from the first base video only.

  


  I have tried many libraries, including pymovie pyav and opencv. The best result so far is to use a subprocess with ffmpeg.

  


  ffmpeg -i testing/stefano_prores422_hq.mov -stream_loop -1 -i testing/key_prores4444.mov -filter_complex "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];[0:v][overlay]overlay" -f nut pipe:1 | ffplay -

  


  When running this in the terminal and playing with ffplay, everything is perfect, the overlay looks good, no dropped frames, and the sound is in synch.

  


  However, trying to feed that to pygame via a subprocess creates either video delays and drop frames or audio not in synch.

  


  EXAMPLE ONE :

  


  # SOUND IS NOT SYNCHED - sound is played via ffplay
import pygame
import subprocess
import numpy as np
import sys

def main():
    pygame.init()
    screen_width, screen_height = 1920, 1080
    screen = pygame.display.set_mode((screen_width, screen_height))
    pygame.display.set_caption("PyGame + FFmpeg Overlay with Audio")
    clock = pygame.time.Clock()

    # LAUNCH AUDIO-ONLY SUBPROCESS
    audio_cmd = [
        "ffplay",
        "-nodisp",          # no video window
        "-autoexit",        # exit when video ends
        "-loglevel", "quiet",
        "testing/stefano_prores422_hq.mov"
    ]
    audio_process = subprocess.Popen(audio_cmd)

    # LAUNCH VIDEO-OVERLAY SUBPROCESS
    ffmpeg_command = [
        "ffmpeg",
        "-re",                        # read at native frame rate
        "-i", "testing/stefano_prores422_hq.mov",
        "-stream_loop", "-1",         # loop alpha video
        "-i", "testing/key_prores4444.mov",
        "-filter_complex",
        "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];"  # ensure alpha channel
        "[0:v][overlay]overlay",      # overlay second input onto first
        "-f", "rawvideo",             # output raw video
        "-pix_fmt", "rgba",           # RGBA format
        "pipe:1"                      # write to STDOUT
    ]
    video_process = subprocess.Popen(
        ffmpeg_command,
        stdout=subprocess.PIPE,
        stderr=subprocess.DEVNULL
    )
    frame_size = screen_width * screen_height * 4  # RGBA = 4 bytes/pixel
    running = True
    while running:
        for event in pygame.event.get():
            if event.type == pygame.QUIT:
                running = False
                break

        raw_frame = video_process.stdout.read(frame_size)

        if len(raw_frame) < frame_size:
            running = False
            break
        # Convert raw bytes -> NumPy array -> PyGame surface
        frame_array = np.frombuffer(raw_frame, dtype=np.uint8)
        frame_array = frame_array.reshape((screen_height, screen_width, 4))
        frame_surface = pygame.image.frombuffer(frame_array.tobytes(), 
                                                (screen_width, screen_height), 
                                                "RGBA")
        screen.blit(frame_surface, (0, 0))
        pygame.display.flip()
        clock.tick(25)
    video_process.terminate()
    video_process.wait()
    audio_process.terminate()
    audio_process.wait()
    pygame.quit()
    sys.exit()

if __name__ == "__main__":
    main()



  


  EXAMPLE TWO

  


  # NO VIDEO OVERLAY - SOUND SYNCHED
import ffmpeg
import pygame
import sys
import numpy as np
import tempfile
import os

def extract_audio(input_file, output_file):
    """Extract audio from video file to temporary WAV file"""
    (
        ffmpeg
        .input(input_file)
        .output(output_file, acodec='pcm_s16le', ac=2, ar='44100')
        .overwrite_output()
        .run(capture_stdout=True, capture_stderr=True)
    )

def get_video_fps(input_file):
    probe = ffmpeg.probe(input_file)
    video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
    fps_str = video_info.get('r_frame_rate', '25/1')
    num, den = map(int, fps_str.split('/'))
    return num / den

input_file = "testing/stefano_prores422_hq.mov"

# Create temporary WAV file
temp_audio = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
temp_audio.close()
extract_audio(input_file, temp_audio.name)

probe = ffmpeg.probe(input_file)
video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
width = int(video_info['width'])
height = int(video_info['height'])
fps = get_video_fps(input_file)

process = (
    ffmpeg
    .input(input_file)
    .output('pipe:', format='rawvideo', pix_fmt='rgb24')
    .run_async(pipe_stdout=True)
)

pygame.init()
pygame.mixer.init(frequency=44100, size=-16, channels=2, buffer=4096)
clock = pygame.time.Clock()
screen = pygame.display.set_mode((width, height))

pygame.mixer.music.load(temp_audio.name)
pygame.mixer.music.play()

frame_count = 0
start_time = pygame.time.get_ticks()

while True:
    for event in pygame.event.get():
        if event.type == pygame.QUIT:
            pygame.mixer.music.stop()
            os.unlink(temp_audio.name)
            sys.exit()

    in_bytes = process.stdout.read(width * height * 3)
    if not in_bytes:
        break

    # Calculate timing for synchronization
    expected_frame_time = frame_count * (1000 / fps)
    actual_time = pygame.time.get_ticks() - start_time
    
    if actual_time < expected_frame_time:
        pygame.time.wait(int(expected_frame_time - actual_time))
    
    in_frame = (
        np.frombuffer(in_bytes, dtype="uint8")
        .reshape([height, width, 3])
    )
    out_frame = pygame.surfarray.make_surface(np.transpose(in_frame, (1, 0, 2)))
    screen.blit(out_frame, (0, 0))
    pygame.display.flip()
    
    frame_count += 1

pygame.mixer.music.stop()
process.wait()
pygame.quit()
os.unlink(temp_audio.name)


  


  I also tried using pygame mixer and a separate mp3 audio file, but that didn't work either. Any help on how to synch the sound while keeping the playback of both videos to 25 FPS would be greatly appreciated !!!

  


• How to render two videos with alpha channel in real time in pygame ?

  21 décembre 2024, par Francesco Calderone

  I need to play two videos with synched sound in real-time with Pygame.
Pygame does not currently support video streams, so I am using a ffmpeg subprocess.
The first video is a prores422_hq. This is a background video with no alpha channel.
The second video is a prores4444 overlay video with an alpha channel, and it needs to be played in real-tim on top of the first video (with transparency).
All of this needs synched sound from the first base video only.

  


  I have tried many libraries, including pymovie pyav and opencv. The best result so far is to use a subprocess with ffmpeg.

  


  ffmpeg -i testing/stefano_prores422_hq.mov -stream_loop -1 -i testing/key_prores4444.mov -filter_complex "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];[0:v][overlay]overlay" -f nut pipe:1 | ffplay -

  


  When running this in the terminal and playing with ffplay, everything is perfect, the overlay looks good, no dropped frames, and the sound is in synch.

  


  However, trying to feed that to pygame via a subprocess creates either video delays and drop frames or audio not in synch.

  


  EXAMPLE ONE :

  


  # SOUND IS NOT SYNCHED - sound is played via ffplay
import pygame
import subprocess
import numpy as np
import sys

def main():
    pygame.init()
    screen_width, screen_height = 1920, 1080
    screen = pygame.display.set_mode((screen_width, screen_height))
    pygame.display.set_caption("PyGame + FFmpeg Overlay with Audio")
    clock = pygame.time.Clock()

    # LAUNCH AUDIO-ONLY SUBPROCESS
    audio_cmd = [
        "ffplay",
        "-nodisp",          # no video window
        "-autoexit",        # exit when video ends
        "-loglevel", "quiet",
        "testing/stefano_prores422_hq.mov"
    ]
    audio_process = subprocess.Popen(audio_cmd)

    # LAUNCH VIDEO-OVERLAY SUBPROCESS
    ffmpeg_command = [
        "ffmpeg",
        "-re",                        # read at native frame rate
        "-i", "testing/stefano_prores422_hq.mov",
        "-stream_loop", "-1",         # loop alpha video
        "-i", "testing/key_prores4444.mov",
        "-filter_complex",
        "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];"  # ensure alpha channel
        "[0:v][overlay]overlay",      # overlay second input onto first
        "-f", "rawvideo",             # output raw video
        "-pix_fmt", "rgba",           # RGBA format
        "pipe:1"                      # write to STDOUT
    ]
    video_process = subprocess.Popen(
        ffmpeg_command,
        stdout=subprocess.PIPE,
        stderr=subprocess.DEVNULL
    )
    frame_size = screen_width * screen_height * 4  # RGBA = 4 bytes/pixel
    running = True
    while running:
        for event in pygame.event.get():
            if event.type == pygame.QUIT:
                running = False
                break

        raw_frame = video_process.stdout.read(frame_size)

        if len(raw_frame) < frame_size:
            running = False
            break
        # Convert raw bytes -> NumPy array -> PyGame surface
        frame_array = np.frombuffer(raw_frame, dtype=np.uint8)
        frame_array = frame_array.reshape((screen_height, screen_width, 4))
        frame_surface = pygame.image.frombuffer(frame_array.tobytes(), 
                                                (screen_width, screen_height), 
                                                "RGBA")
        screen.blit(frame_surface, (0, 0))
        pygame.display.flip()
        clock.tick(25)
    video_process.terminate()
    video_process.wait()
    audio_process.terminate()
    audio_process.wait()
    pygame.quit()
    sys.exit()

if __name__ == "__main__":
    main()



  


  EXAMPLE TWO

  


  # NO VIDEO OVERLAY - SOUND SYNCHED
import ffmpeg
import pygame
import sys
import numpy as np
import tempfile
import os

def extract_audio(input_file, output_file):
    """Extract audio from video file to temporary WAV file"""
    (
        ffmpeg
        .input(input_file)
        .output(output_file, acodec='pcm_s16le', ac=2, ar='44100')
        .overwrite_output()
        .run(capture_stdout=True, capture_stderr=True)
    )

def get_video_fps(input_file):
    probe = ffmpeg.probe(input_file)
    video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
    fps_str = video_info.get('r_frame_rate', '25/1')
    num, den = map(int, fps_str.split('/'))
    return num / den

input_file = "testing/stefano_prores422_hq.mov"

# Create temporary WAV file
temp_audio = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
temp_audio.close()
extract_audio(input_file, temp_audio.name)

probe = ffmpeg.probe(input_file)
video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
width = int(video_info['width'])
height = int(video_info['height'])
fps = get_video_fps(input_file)

process = (
    ffmpeg
    .input(input_file)
    .output('pipe:', format='rawvideo', pix_fmt='rgb24')
    .run_async(pipe_stdout=True)
)

pygame.init()
pygame.mixer.init(frequency=44100, size=-16, channels=2, buffer=4096)
clock = pygame.time.Clock()
screen = pygame.display.set_mode((width, height))

pygame.mixer.music.load(temp_audio.name)
pygame.mixer.music.play()

frame_count = 0
start_time = pygame.time.get_ticks()

while True:
    for event in pygame.event.get():
        if event.type == pygame.QUIT:
            pygame.mixer.music.stop()
            os.unlink(temp_audio.name)
            sys.exit()

    in_bytes = process.stdout.read(width * height * 3)
    if not in_bytes:
        break

    # Calculate timing for synchronization
    expected_frame_time = frame_count * (1000 / fps)
    actual_time = pygame.time.get_ticks() - start_time
    
    if actual_time < expected_frame_time:
        pygame.time.wait(int(expected_frame_time - actual_time))
    
    in_frame = (
        np.frombuffer(in_bytes, dtype="uint8")
        .reshape([height, width, 3])
    )
    out_frame = pygame.surfarray.make_surface(np.transpose(in_frame, (1, 0, 2)))
    screen.blit(out_frame, (0, 0))
    pygame.display.flip()
    
    frame_count += 1

pygame.mixer.music.stop()
process.wait()
pygame.quit()
os.unlink(temp_audio.name)


  


  I also tried using pygame mixer and a separate mp3 audio file, but that didn't work either. Any help on how to synch the sound while keeping the playback of both videos to 25 FPS would be greatly appreciated !!!

  


• GStreamer : How to set "stream-number" pad property of mpegtsmux element ? [closed]

  8 novembre 2024, par TishSerg

  Accroding to gst-inspect-1.0 mpegtsmux, mpegtsmux's sink pads have writable stream-number property :

  


  ...
Pad Templates:
  SINK template: 'sink_%d'
    Availability: On request
    Capabilities:
      ...
    Type: GstBaseTsMuxPad
    Pad Properties:
      ...

      stream-number       : stream number
                            flags: readable, writable
                            Integer. Range: 0 - 31 Default: 0


  


  But when I try to set it, GStreamer says there's no such property. The following listing shows I can run multi-stream pipeline without setting that property, but when I add that property it doesn't work.

  


  PS C:\gstreamer\1.0\msvc_x86_64\bin> ./gst-launch-1.0 mpegtsmux name=mux ! udpsink host=192.168.144.255 port=5600 sync=no `
>> videotestsrc is-live=true pattern=ball ! "video/x-raw, width=1920, height=1080, profile=main" ! x264enc ! mux.sink_300 `
>> videotestsrc is-live=true ! "video/x-raw, width=720, height=576" ! x264enc ! mux.sink_301
Use Windows high-resolution clock, precision: 1 ms
Setting pipeline to PAUSED ...
Pipeline is live and does not need PREROLL ...
Pipeline is PREROLLED ...
Setting pipeline to PLAYING ...
New clock: GstSystemClock
Redistribute latency...
Redistribute latency...
Redistribute latency...
handling interrupt.9.
Interrupt: Stopping pipeline ...
Execution ended after 0:00:03.773243400
Setting pipeline to NULL ...
Freeing pipeline ...
PS C:\gstreamer\1.0\msvc_x86_64\bin> ./gst-launch-1.0 mpegtsmux name=mux sink_300::stream-number=1 ! udpsink host=192.168.144.255 port=5600 sync=no `
>> videotestsrc is-live=true pattern=ball ! "video/x-raw, width=1920, height=1080, profile=main" ! x264enc ! mux.sink_300 `
>> videotestsrc is-live=true ! "video/x-raw, width=720, height=576" ! x264enc ! mux.sink_301
WARNING: erroneous pipeline: no property "sink_300::stream-number" in element "mpegtsmux"
PS C:\gstreamer\1.0\msvc_x86_64\bin> .\gst-launch-1.0.exe --version
gst-launch-1.0 version 1.24.8
GStreamer 1.24.8
Unknown package origin
PS C:\gstreamer\1.0\msvc_x86_64\bin> .\gst-launch-1.0.exe --version
gst-launch-1.0 version 1.24.9
GStreamer 1.24.9
Unknown package origin
PS C:\gstreamer\1.0\msvc_x86_64\bin> ./gst-launch-1.0 mpegtsmux name=mux sink_300::stream-number=1 ! udpsink host=192.168.144.255 port=5600 sync=no `
>> videotestsrc is-live=true pattern=ball ! "video/x-raw, width=1920, height=1080, profile=main" ! x264enc ! mux.sink_300 `
>> videotestsrc is-live=true ! "video/x-raw, width=720, height=576" ! x264enc ! mux.sink_301
WARNING: erroneous pipeline: no property "sink_300::stream-number" in element "mpegtsmux"


  


  I even updated GStreamer, but still no luck. I tried that because I found news saying there were updates regarding that property :

  


    397 ### MPEG-TS improvements
  398 
  399 -   mpegtsdemux gained support for
  400     -   segment seeking for seamless non-flushing looping, and
  401     -   synchronous KLV
  402 -   mpegtsmux now
  403     -   allows attaching PCR to non-PES streams
  404     -   allows setting of the PES stream number for AAC audio and AVC video streams via a new “stream-number” property on the
  405         muxer sink pads. Currently, the PES stream number is hard-coded to zero for these stream types.


  


  The syntax seems correct (pad_name::pad_prop_name on the element). I ran out of ideas about what I'm doing wrong with that property.

  


  Broader context :

  


  I want to set that property because I want an exact sequence of streams I mixing.

  


  When I feed mpegtsmux with two video streams and one audio stream (from capture devices) without specifying the stream numbers I get them muxed in a random sequence (checking it using ffprobe). Sometimes they are in the desired sequence, but sometimes they aren't. The worst case is when the audio stream is the first stream in the file, so video players get mad when trying to play such .ts file. I have to remux such files using -map key of ffmpeg. If I could set exact stream indices in mpegtsmux (not to be confused with stream PID) I could avoid analyzing actual stream layout and remuxing.

  


  Example of the real layout of the streams (ffprobe output) :

  


  Input #0, mpegts, from '████████████████████████████████████████':
  Duration: 00:20:09.64, start: 3870.816656, bitrate: 6390 kb/s
  Program 1
  Stream #0:2[0x41]: Video: h264 (Baseline) (HDMV / 0x564D4448), yuvj420p(pc, bt709, progressive), 1920x1080, 30 fps, 30 tbr, 90k tbn
  Stream #0:1[0x4b]: Audio: aac (LC) ([15][0][0][0] / 0x000F), 48000 Hz, mono, fltp, 130 kb/s
  Program 2
  Stream #0:0[0x42]: Video: h264 (High) (HDMV / 0x564D4448), yuv420p(progressive), 720x576, 25 fps, 25 tbr, 90k tbn


  


  You can see 3 streams :

  


  

  • FullHD video with PID 0x41 (defined by me as mpegtsmux0.sink_65) has index 2 while I want it to be 0

  


  • PAL video with PID 0x42 (defined by me as mpegtsmux0.sink_66) has index 0 while I want it to be 1

  


  • Audio with PID 0x4b (defined by me as mpegtsmux0.sink_75) has index 1 while I want it to be 2