Recherche avancée

Sur d’autres sites (7261)

• ppc : reduce overreads when loading 8 pixels in altivec dsp functions

  13 février 2014, par Janne Grunau

  ppc : reduce overreads when loading 8 pixels in altivec dsp functions
  Altivec can only load naturally aligned vectors. To handle possibly
  
  unaligned data a second vector is loaded from an offset of the original
  
  location and the data is recovered through a vector permutation.
  
  Overreads are minimal if the offset for second load points to the last
  
  element of data. This is 7 for loading eight 8-bit pixels and overreads
  
  are reduced from 16 bytes to 8 bytes if the pixels are 64-bit aligned.
  
  For unaligned pixels the overread is reduced from 23 bytes to 15 bytes
  
  in the worst case.
  

  • [DBH] libavcodec/ppc/dsputil_altivec.c

• Streaming a webcam to a web server to be streamed on web

  19 octobre 2012, par gazzwi86

  I intend on streaming a web cam from a Raspberry Pi to a server, which can then serve the stream up to users over the web. I would ideally like the stream to work across all browsers with minimal complication, so the current mjpeg format I presume would not be ideal.

  Firstly, I would like to know if ffmpeg is the right tool for the job as its what I'm experimenting with at the moment ? I also looked at using ffmpeg and motion but didnt see the need for motion as I don't need motion detection. My config for ffmpeg is listed below :

  I installed via apt-get :

  apt-get install ffmpeg

  I have create a config file /etc/ffserver.conf containing the following :

  Port 80
  
  BindAddress 0.0.0.0
  
  MaxClients 10
  
  MaxBandwidth 50000
  
  NoDaemon
  
  
  
  <feed>
  
      file /tmp/webcam.ffm
  
      FileMaxSize 10M
  
  </feed>
  
  
  
  <stream>
  
      Feed webcam.ffm
  
      Format mpjpeg
  
      VideoSize 640x480
  
      VideoFrameRate 15
  
      VideoBitRate 2000
  
      VideoQMin 1
  
      VideoQMax 10
  
      strict -1
  
  </stream>

  I have created a file in the sbin called webcam.sh containing the following :

  ffserver -f /etc/ffserver.conf & ffmpeg -v verbose -r 5 -s 640x480 -f video4linux2 -i /dev/video0 http://localhost/webcam.ffm

  Running the above starts the stream but at the moment viewing http://webcam.mjpeg starts a file downloading which seems not to start in chrome and doing the same with and html file with the stream in a img tag doesnt work.

• What is the most performant way to render unmanaged video frames in WPF ?

  27 mai 2017, par superware

  I’m using FFmpeg library to receive and decode H.264/MPEG-TS over UDP with minimal latency (something MediaElement can’t handle).

  On a dedicated FFmpeg thread, I’m pulling PixelFormats.Bgr32 video frames for display. I’ve already tried InteropBitmap :

  _section = CreateFileMapping(INVALID_HANDLE_VALUE, IntPtr.Zero, PAGE_READWRITE, 0, size, null);
  
  _buffer = MapViewOfFile(_section, FILE_MAP_ALL_ACCESS, 0, 0, size);
  
  Dispatcher.Invoke((Action)delegate()
  
  {
  
      _interopBitmap = (InteropBitmap)Imaging.CreateBitmapSourceFromMemorySection(_section, width, height, PixelFormats.Bgr32, (int)size / height, 0);
  
      this.Source = _interopBitmap;
  
  });

  And then per frame update :

  Dispatcher.Invoke((Action)delegate()
  
  {
  
      _interopBitmap.Invalidate();
  
  });

  But performance is quite bad (skipping frames, high CPU usage etc).

  I’ve also tried WriteableBitmap : FFmpeg is placing frames in _writeableBitmap.BackBuffer and per frame update :

  Dispatcher.Invoke((Action)delegate()
  
  {
  
      _writeableBitmap.Lock();
  
  });
  
  try
  
  {
  
      ret = FFmpegInvoke.sws_scale(...);
  
  }
  
  finally
  
  {
  
      Dispatcher.Invoke((Action)delegate()
  
      {
  
          _writeableBitmap.AddDirtyRect(_rect);
  
          _writeableBitmap.Unlock();
  
      });
  
  }

  Experiencing almost the same performance issues (tested with various DispatcherPriority).

  Any help will be greatly appreciated.