Advanced search

On other websites (4027)

• Decoding MediaRecorder produced webm stream

  15 August 2019, by sgmg

  I am trying to decode a video stream from the browser using the ffmpeg API. The stream is produced by the webcam and recorded with MediaRecorder as webm format. What I ultimately need is a vector of opencv cv::Mat objects for further processing.

  I have written a C++ webserver using the uWebsocket library. The video stream is sent via websocket from the browser to the server once per second. On the server, I append the received data to my custom buffer and decode it with the ffmpeg API.

  If I just save the data on the disk and later I play it with a media player, it works fine. So, whatever the browser sends is a valid video.

  I do not think that I correctly understand how should the custom IO behave with network streaming as nothing seems to be working.

  The custom buffer:

   struct Buffer
  
      {
  
          std::vector data;
  
          int currentPos = 0;
  
      };

  The readAVBuffer method for custom IO

  int MediaDecoder::readAVBuffer(void* opaque, uint8_t* buf, int buf_size)
  
  {
  
      MediaDecoder::Buffer* mbuf = (MediaDecoder::Buffer*)opaque;
  
      int count = 0;
  
      for(int i=0;icurrentPos;
  
          if(index >= (int)mbuf->data.size())
  
          {
  
              break;
  
          }
  
          count++;
  
          buf[i] = mbuf->data.at(index);
  
      }
  
      if(count > 0) mbuf->currentPos+=count;
  
  
  
      std::cout << "read : "<currentPos<<", buff size:"<data.size() << std::endl;
  
      if(count <= 0) return AVERROR(EAGAIN); //is this error that should be returned? It cannot be EOF since we're not done yet, most likely
  
      return count;
  
  }

  The big decode method, that’s supposed to return whatever frames it could read

  std::vector MediaDecoder::decode(const char* data, size_t length)
  
  {
  
      std::vector frames;
  
      //add data to the buffer
  
      for(size_t i=0;i/do not invoke the decoders until we have 1MB of data
  
      if(((buf.data.size() - buf.currentPos) < 1*1024*1024) && !initializedCodecs) return frames;
  
  
  
      std::cout << "decoding data length "</initialize ffmpeg objects. Custom I/O, format, decoder, etc.
  
      {       
  
          //these are just members of the class 
  
          avioCtxPtr = std::unique_ptr(
  
                      avio_alloc_context((uint8_t*)av_malloc(4096),4096,0,&buf,&readAVBuffer,nullptr,nullptr),
  
                      avio_context_deleter());
  
          if(!avioCtxPtr)
  
          {
  
              std::cerr << "Could not create IO buffer" << std::endl;
  
              return frames;
  
          }                
  
  
  
          fmt_ctx = std::unique_ptr(avformat_alloc_context(),
  
                                                                            avformat_context_deleter());
  
          fmt_ctx->pb = avioCtxPtr.get();
  
          fmt_ctx->flags |= AVFMT_FLAG_CUSTOM_IO ;
  
          //fmt_ctx->max_analyze_duration = 2 * AV_TIME_BASE; // read 2 seconds of data
  
          {
  
              AVFormatContext *fmtCtxRaw = fmt_ctx.get();            
  
              if (avformat_open_input(&fmtCtxRaw, "", nullptr, nullptr) < 0) {
  
                  std::cerr << "Could not open movie" << std::endl;
  
                  return frames;
  
              }
  
          }
  
          if (avformat_find_stream_info(fmt_ctx.get(), nullptr) < 0) {
  
              std::cerr << "Could not find stream information" << std::endl;
  
              return frames;
  
          }
  
          if((video_stream_idx = av_find_best_stream(fmt_ctx.get(), AVMEDIA_TYPE_VIDEO, -1, -1, nullptr, 0)) < 0)
  
          {
  
              std::cerr << "Could not find video stream" << std::endl;
  
              return frames;
  
          }
  
          AVStream *video_stream = fmt_ctx->streams[video_stream_idx];
  
          AVCodec *dec = avcodec_find_decoder(video_stream->codecpar->codec_id);
  
  
  
          video_dec_ctx = std::unique_ptr (avcodec_alloc_context3(dec),
  
                                                                                avcodec_context_deleter());
  
          if (!video_dec_ctx)
  
          {
  
              std::cerr << "Failed to allocate the video codec context" << std::endl;
  
              return frames;
  
          }
  
          avcodec_parameters_to_context(video_dec_ctx.get(),video_stream->codecpar);
  
          video_dec_ctx->thread_count = 1;
  
         /* video_dec_ctx->max_b_frames = 0;
  
          video_dec_ctx->frame_skip_threshold = 10;*/
  
  
  
          AVDictionary *opts = nullptr;
  
          av_dict_set(&opts, "refcounted_frames", "1", 0);
  
          av_dict_set(&opts, "deadline", "1", 0);
  
          av_dict_set(&opts, "auto-alt-ref", "0", 0);
  
          av_dict_set(&opts, "lag-in-frames", "1", 0);
  
          av_dict_set(&opts, "rc_lookahead", "1", 0);
  
          av_dict_set(&opts, "drop_frame", "1", 0);
  
          av_dict_set(&opts, "error-resilient", "1", 0);
  
  
  
          int width = video_dec_ctx->width;
  
          videoHeight = video_dec_ctx->height;
  
  
  
          if(avcodec_open2(video_dec_ctx.get(), dec, &opts) < 0)
  
          {
  
              std::cerr << "Failed to open the video codec context" << std::endl;
  
              return frames;
  
          }
  
  
  
          AVPixelFormat  pFormat = AV_PIX_FMT_BGR24;
  
          img_convert_ctx = std::unique_ptr(sws_getContext(width, videoHeight,
  
                                           video_dec_ctx->pix_fmt,   width, videoHeight, pFormat,
  
                                           SWS_BICUBIC, nullptr, nullptr,nullptr),swscontext_deleter());
  
  
  
          frame = std::unique_ptr(av_frame_alloc(),avframe_deleter());
  
          frameRGB = std::unique_ptr(av_frame_alloc(),avframe_deleter());
  
  
  
  
  
          int numBytes = av_image_get_buffer_size(pFormat, width, videoHeight,32 /*https://stackoverflow.com/questions/35678041/what-is-linesize-alignment-meaning*/);
  
          std::unique_ptr imageBuffer((uint8_t *) av_malloc(numBytes*sizeof(uint8_t)),avbuffer_deleter());
  
          av_image_fill_arrays(frameRGB->data,frameRGB->linesize,imageBuffer.get(),pFormat,width,videoHeight,32);
  
          frameRGB->width = width;
  
          frameRGB->height = videoHeight;
  
  
  
          initializedCodecs = true;
  
      }    
  
      AVPacket pkt;
  
      av_init_packet(&pkt);
  
      pkt.data = nullptr;
  
      pkt.size = 0;
  
  
  
      int read_frame_return = 0;
  
      while ( (read_frame_return=av_read_frame(fmt_ctx.get(), &pkt)) >= 0)
  
      {
  
          readFrame(&frames,&pkt,video_dec_ctx.get(),frame.get(),img_convert_ctx.get(),
  
                    videoHeight,frameRGB.get());
  
          //if(cancelled) break;
  
      }
  
      avioCtxPtr->eof_reached = 0;
  
      avioCtxPtr->error = 0;
  
  
  
  
  
      //flush
  
     // readFrame(frames.get(),nullptr,video_dec_ctx.get(),frame.get(),
  
       //         img_convert_ctx.get(),videoHeight,frameRGB.get());
  
  
  
      avioCtxPtr->eof_reached = 0;
  
      avioCtxPtr->error = 0;
  
  
  
      if(frames->size() <= 0)
  
      {
  
          std::cout << "buffer pos: "<code>

  What I would expect to happen would be for a continuous extraction of cv::Mat frames as I feed it more and more data. What actually happens is that after the the buffer is fully read I see:

  [matroska,webm @ 0x507b450] Read error at pos. 1278266 (0x13813a)
  
  [matroska,webm @ 0x507b450] Seek to desired resync point failed. Seeking to earliest point available instead.

  And then no more bytes are read from the buffer even if later I increase the size of it.

  There is something terribly wrong I’m doing here and I don’t understand what.

• Changing x264 settings on the fly

  22 December 2018, by S Red

  I am curious to know if anyone has experience with modifying x264 settings during encoding (this is for testing live streaming hence I need to be able to modify settings based on cpu and upload characteristics).

  



  I saw an API for encoder_reconfig() in x264.h, curious if folks have used that, and if its accessible from ffmpeg? Is it possible to modify a high-level option like 'preset', or do I need to modify individual options like chroma-me, trellis etc.

  


• Changing x264 settings on the fly

  22 December 2018, by S Red

  I am curious to know if anyone has experience with modifying x264 settings during encoding (this is for testing live streaming hence I need to be able to modify settings based on cpu and upload characteristics).

  I saw an API for encoder_reconfig() in x264.h, curious if folks have used that, and if its accessible from ffmpeg? Is it possible to modify a high-level option like ’preset’, or do I need to modify individual options like chroma-me, trellis etc.