Recherche avancée

Sur d’autres sites (4455)

• FFmpeg + OpenAL - playback streaming sound from video won't work

  28 janvier 2014, par TheSHEEEP

  I am decoding an OGG video (theora & vorbis as codecs) and want to show it on the screen (using Ogre 3D) while playing its sound. I can decode the image stream just fine and the video plays perfectly with the correct frame rate, etc.

  However, I cannot get the sound to play at all with OpenAL.

  Edit : I managed to make the playing sound resemble the actual audio in the video at least somewhat. Updated sample code.

  Edit 2 : I was able to get "almost" correct sound now. I had to set OpenAL to use AL_FORMAT_STEREO_FLOAT32 (after initializing the extension) instead of just STEREO16. Now the sound is "only" extremely high pitched and stuttering, but at the correct speed.

  Here is how I decode audio packets (in a background thread, the equivalent works just fine for the image stream of the video file) :

  //------------------------------------------------------------------------------
  
  int decodeAudioPacket(  AVPacket& p_packet, AVCodecContext* p_audioCodecContext, AVFrame* p_frame,
  
                          FFmpegVideoPlayer* p_player, VideoInfo& p_videoInfo)
  
  {
  
      // Decode audio frame
  
      int got_frame = 0;
  
      int decoded = avcodec_decode_audio4(p_audioCodecContext, p_frame, &got_frame, &p_packet);
  
      if (decoded < 0) 
  
      {
  
          p_videoInfo.error = "Error decoding audio frame.";
  
          return decoded;
  
      }
  
  
  
      // Frame is complete, store it in audio frame queue
  
      if (got_frame)
  
      {
  
          int bufferSize = av_samples_get_buffer_size(NULL, p_audioCodecContext->channels, p_frame->nb_samples, 
  
                                                      p_audioCodecContext->sample_fmt, 0);
  
  
  
          int64_t duration = p_frame->pkt_duration;
  
          int64_t dts = p_frame->pkt_dts;
  
  
  
          if (staticOgreLog)
  
          {
  
              staticOgreLog->logMessage("Audio frame bufferSize / duration / dts: " 
  
                      + boost::lexical_cast(bufferSize) + " / "
  
                      + boost::lexical_cast(duration) + " / "
  
                      + boost::lexical_cast(dts), Ogre::LML_NORMAL);
  
          }
  
  
  
          // Create the audio frame
  
          AudioFrame* frame = new AudioFrame();
  
          frame->dataSize = bufferSize;
  
          frame->data = new uint8_t[bufferSize];
  
          if (p_frame->channels == 2)
  
          {
  
              memcpy(frame->data, p_frame->data[0], bufferSize >> 1);
  
              memcpy(frame->data + (bufferSize >> 1), p_frame->data[1], bufferSize >> 1);
  
          }
  
          else
  
          {
  
              memcpy(frame->data, p_frame->data, bufferSize);
  
          }
  
          double timeBase = ((double)p_audioCodecContext->time_base.num) / (double)p_audioCodecContext->time_base.den;
  
          frame->lifeTime = duration * timeBase;
  
  
  
          p_player->addAudioFrame(frame);
  
      }
  
  
  
      return decoded;
  
  }

  So, as you can see, I decode the frame, memcpy it to my own struct, AudioFrame. Now, when the sound is played, I use these audio frame like this :

      int numBuffers = 4;
  
      ALuint buffers[4];
  
      alGenBuffers(numBuffers, buffers);
  
      ALenum success = alGetError();
  
      if(success != AL_NO_ERROR)
  
      {
  
          CONSOLE_LOG("Error on alGenBuffers : " + Ogre::StringConverter::toString(success) + alGetString(success));
  
          return;
  
      }
  
  
  
      // Fill a number of data buffers with audio from the stream
  
      std::vector audioBuffers;
  
      std::vector<unsigned int="int"> audioBufferSizes;
  
      unsigned int numReturned = FFMPEG_PLAYER->getDecodedAudioFrames(numBuffers, audioBuffers, audioBufferSizes);
  
  
  
      // Assign the data buffers to the OpenAL buffers
  
      for (unsigned int i = 0; i &lt; numReturned; ++i)
  
      {
  
          alBufferData(buffers[i], _streamingFormat, audioBuffers[i]->data, audioBufferSizes[i], _streamingFrequency);
  
  
  
          success = alGetError();
  
          if(success != AL_NO_ERROR)
  
          {
  
              CONSOLE_LOG("Error on alBufferData : " + Ogre::StringConverter::toString(success) + alGetString(success)
  
                              + " size: " + Ogre::StringConverter::toString(audioBufferSizes[i]));
  
              return;
  
          }
  
      }
  
  
  
      // Queue the buffers into OpenAL
  
      alSourceQueueBuffers(_source, numReturned, buffers);
  
      success = alGetError();
  
      if(success != AL_NO_ERROR)
  
      {
  
          CONSOLE_LOG("Error queuing streaming buffers: " + Ogre::StringConverter::toString(success) + alGetString(success));
  
          return;
  
      }
  
  }
  
  
  
  alSourcePlay(_source);
  
  </unsigned>

  The format and frequency I give to OpenAL are AL_FORMAT_STEREO_FLOAT32 (it is a stereo sound stream, and I did initialize the FLOAT32 extension) and 48000 (which is the sample rate of the AVCodecContext of the audio stream).

  And during playback, I do the following to refill OpenAL's buffers :

  ALint numBuffersProcessed;
  
  
  
  // Check if OpenAL is done with any of the queued buffers
  
  alGetSourcei(_source, AL_BUFFERS_PROCESSED, &numBuffersProcessed);
  
  if(numBuffersProcessed <= 0)
  
      return;
  
  
  
  // Fill a number of data buffers with audio from the stream
  
  std::vector audioBuffers;
  
  std::vector<unsigned int="int"> audioBufferSizes;
  
  unsigned int numFilled = FFMPEG_PLAYER->getDecodedAudioFrames(numBuffersProcessed, audioBuffers, audioBufferSizes);
  
  
  
  // Assign the data buffers to the OpenAL buffers
  
  ALuint buffer;
  
  for (unsigned int i = 0; i &lt; numFilled; ++i)
  
  {
  
      // Pop the oldest queued buffer from the source, 
  
      // fill it with the new data, then re-queue it
  
      alSourceUnqueueBuffers(_source, 1, &amp;buffer);
  
  
  
      ALenum success = alGetError();
  
      if(success != AL_NO_ERROR)
  
      {
  
          CONSOLE_LOG("Error Unqueuing streaming buffers: " + Ogre::StringConverter::toString(success));
  
          return;
  
      }
  
  
  
      alBufferData(buffer, _streamingFormat, audioBuffers[i]->data, audioBufferSizes[i], _streamingFrequency);
  
  
  
      success = alGetError();
  
      if(success != AL_NO_ERROR)
  
      {
  
          CONSOLE_LOG("Error on re- alBufferData: " + Ogre::StringConverter::toString(success));
  
          return;
  
      }
  
  
  
      alSourceQueueBuffers(_source, 1, &amp;buffer);
  
  
  
      success = alGetError();
  
      if(success != AL_NO_ERROR)
  
      {
  
          CONSOLE_LOG("Error re-queuing streaming buffers: " + Ogre::StringConverter::toString(success) + " "
  
                      + alGetString(success));
  
          return;
  
      }
  
  }
  
  
  
  // Make sure the source is still playing, 
  
  // and restart it if needed.
  
  ALint playStatus;
  
  alGetSourcei(_source, AL_SOURCE_STATE, &amp;playStatus);
  
  if(playStatus != AL_PLAYING)
  
      alSourcePlay(_source);
  
  </unsigned>

  As you can see, I do quite heavy error checking. But I do not get any errors, neither from OpenAL nor from FFmpeg.
  Edit : What I hear somewhat resembles the actual audio from the video, but VERY high pitched and stuttering VERY much. Also, it seems to be playing on top of TV noise. Very strange. Plus, it is playing much slower than the correct audio would.
  Edit : 2 After using AL_FORMAT_STEREO_FLOAT32, the sound plays at the correct speed, but is still very high pitched and stuttering (though less than before).

  The video itself is not broken, it can be played fine on any player. OpenAL can also play *.way files just fine in the same application, so it is also working.

  Any ideas what could be wrong here or how to do this correctly ?

  My only guess is that somehow, FFmpeg's decode function does not produce data OpenGL can read. But this is as far as the FFmpeg decode example goes, so I don't know what's missing. As I understand it, the decode_audio4 function decodes the frame to raw data. And OpenAL should be able to work with RAW data (or rather, doesn't work with anything else).

• swresample : change COMMON_CORE_INT16 asm from SSSE3 to SSE2

  17 mars 2014, par James Almer

  swresample : change COMMON_CORE_INT16 asm from SSSE3 to SSE2
  pshuf+paddd is slightly faster than phaddd.
  
  The real gain is in pre-ssse3 processors like AMD K8 and K10, which get
  
  a big boost in performance compared to the mmxext version
  Signed-off-by : James Almer <jamrial@gmail.com>
  
  Signed-off-by : Michael Niedermayer <michaelni@gmx.at>
  

  • [DH] libswresample/resample.c
  • [DH] libswresample/resample_template.c
  • [DH] libswresample/x86/resample_mmx.h

• OpenCV : in search for less CPU intensive frame capture+resize and into buffer way : how to optimize my code ?

  18 septembre 2014, par Rella

  So I created a function (C++)

  void CaptureFrame(char* buffer, int w, int h, int bytespan)
  
  {
  
   /* get a frame */
  
   if(!cvGrabFrame(capture)){              // capture a frame 
  
    printf("Could not grab a frame\n\7");
  
    //exit(0);
  
   }
  
   CVframe =cvRetrieveFrame(capture);           // retrieve the captured frame
  
  
  
   /* always check */
  
   if (!CVframe)
  
   {
  
    printf("No CV frame captured!\n");
  
    cin.get();
  
   }
  
  
  
   /* resize buffer for current frame */
  
   IplImage* destination = cvCreateImage(cvSize(w, h), CVframe->depth, CVframe->nChannels);
  
  
  
   //use cvResize to resize source to a destination image
  
   cvResize(CVframe, destination);
  
  
  
   IplImage* redchannel = cvCreateImage(cvGetSize(destination), 8, 1);
  
   IplImage* greenchannel = cvCreateImage(cvGetSize(destination), 8, 1);
  
   IplImage* bluechannel = cvCreateImage(cvGetSize(destination), 8, 1);
  
  
  
   cvSplit(destination, bluechannel, greenchannel, redchannel, NULL);
  
   for(int y = 0; y < destination->height; y++)
  
   {
  
    char* line = buffer + y * bytespan;
  
    for(int x = 0; x < destination->width; x++)
  
    {
  
     line[0] = cvGetReal2D(redchannel, y, x);
  
     line[1] = cvGetReal2D(greenchannel, y, x);
  
     line[2] = cvGetReal2D(bluechannel, y, x);
  
     line += 3;
  
    }
  
   }
  
   cvReleaseImage(&redchannel);
  
   cvReleaseImage(&greenchannel);
  
   cvReleaseImage(&bluechannel);
  
   cvReleaseImage(&destination);
  
  }

  So generally it captures a frame from device, creates a frame to resize into and copies it into buffer (RGB or YUV420P is requirement for me).

  So I wonder what I do wrong, because my function is way 2 cpu intensive, and what can be done to fix it ?

  Update :

  My function is runed in thread :

       void ThreadCaptureFrame()
  
      {
  
          while(1){
  
          t.restart();
  
          CaptureFrame((char *)frame->data[0], videoWidth, videoHeight, frame->linesize[0]);
  
          AVFrame* swap = frame;
  
          frame = readyFrame;
  
          readyFrame = swap;
  
          spendedTime = t.elapsed();
  
          if(spendedTime < desiredTime){
  
              Sleep(desiredTime - spendedTime);
  
          }
  
      }
  
   }

  which is started at the beginning of int main ( after some initialization) :

  boost::thread workerThread(ThreadCaptureFrame);

  So if it can it runs 24 times per second, it eats 28% of core quad. cam resolution I capture is like 320x240. So : how to optimize it ?