Recherche avancée

Sur d’autres sites (6385)

• seeking with av_seek_frame returns invalid data

  27 juin 2016, par mtadmk

  Based on dranger tutorial I’m trying to implement seeking in video file. Problem is with seeking to beginning milliseconds - it always returns 0 when seeking backward, or some place in file (based on file format).

  I.e. with this video file and seeking forward to 500 pts there is always 6163 pts returned. Seeking backward to 500 is always returning 0. I have no idea why.

  Code to do this :

  import java.util.Arrays;
  
  import java.util.List;
  
  import org.bytedeco.javacpp.BytePointer;
  
  import org.bytedeco.javacpp.DoublePointer;
  
  import org.bytedeco.javacpp.PointerPointer;
  
  import org.bytedeco.javacpp.avcodec;
  
  import org.bytedeco.javacpp.avformat;
  
  import org.bytedeco.javacpp.avutil;
  
  import org.bytedeco.javacpp.swscale;
  
  
  
  import static org.bytedeco.javacpp.avcodec.av_free_packet;
  
  import static org.bytedeco.javacpp.avcodec.avcodec_close;
  
  import static org.bytedeco.javacpp.avcodec.avcodec_decode_video2;
  
  import static org.bytedeco.javacpp.avcodec.avcodec_find_decoder;
  
  import static org.bytedeco.javacpp.avcodec.avcodec_flush_buffers;
  
  import static org.bytedeco.javacpp.avcodec.avcodec_open2;
  
  import static org.bytedeco.javacpp.avcodec.avpicture_fill;
  
  import static org.bytedeco.javacpp.avcodec.avpicture_get_size;
  
  import static org.bytedeco.javacpp.avformat.AVSEEK_FLAG_BACKWARD;
  
  import static org.bytedeco.javacpp.avformat.av_dump_format;
  
  import static org.bytedeco.javacpp.avformat.av_read_frame;
  
  import static org.bytedeco.javacpp.avformat.av_register_all;
  
  import static org.bytedeco.javacpp.avformat.av_seek_frame;
  
  import static org.bytedeco.javacpp.avformat.avformat_close_input;
  
  import static org.bytedeco.javacpp.avformat.avformat_find_stream_info;
  
  import static org.bytedeco.javacpp.avformat.avformat_open_input;
  
  import static org.bytedeco.javacpp.avutil.AVMEDIA_TYPE_VIDEO;
  
  import static org.bytedeco.javacpp.avutil.AV_PIX_FMT_RGB24;
  
  import static org.bytedeco.javacpp.avutil.AV_TIME_BASE;
  
  import static org.bytedeco.javacpp.avutil.av_frame_alloc;
  
  import static org.bytedeco.javacpp.avutil.av_frame_get_best_effort_timestamp;
  
  import static org.bytedeco.javacpp.avutil.av_free;
  
  import static org.bytedeco.javacpp.avutil.av_make_q;
  
  import static org.bytedeco.javacpp.avutil.av_malloc;
  
  import static org.bytedeco.javacpp.avutil.av_q2d;
  
  import static org.bytedeco.javacpp.avutil.av_rescale_q;
  
  import static org.bytedeco.javacpp.swscale.SWS_BILINEAR;
  
  import static org.bytedeco.javacpp.swscale.sws_getContext;
  
  import static org.bytedeco.javacpp.swscale.sws_scale;
  
  
  
  public class SeekTest1 {
  
      private avformat.AVFormatContext videoFile;
  
      private final avcodec.AVPacket framePacket = new avcodec.AVPacket();
  
      private avcodec.AVCodecContext videoCodec;
  
      private avutil.AVFrame yuvFrame;
  
      private swscale.SwsContext scalingContext;
  
      private avutil.AVFrame rgbFrame;
  
      private int streamId;
  
      private long lastTime;
  
  
  
      public static void main(String[] args) {
  
          if (args.length > 0) {
  
              new SeekTest1().start(args[0]);
  
          } else {
  
              new SeekTest1().start("/path/to/file");
  
          }
  
  
  
      }
  
  
  
      private void start(String path) {
  
          init(path);
  
          //test for forward
  
  //        List<integer> seekPos = Arrays.asList(0, 100, 0, 200, 0, 300, 0, 400, 0, 500, 0, 600, 0, 700);
  
          //test for backward
  
          List<integer> seekPos = Arrays.asList(10000, 8000, 10000, 7000, 10000, 6000, 10000, 4000, 10000, 2000, 10000, 1000, 10000, 200);
  
          seekPos.forEach(seekPosition -> {
  
              readFrame();
  
              seek(seekPosition);
  
          });
  
          readFrame();
  
          cleanUp();
  
      }
  
  
  
      long seek(long seekPosition) {
  
          final avutil.AVRational timeBase = fetchTimeBase();
  
          long timeInBaseUnit = fetchTimeInBaseUnit(seekPosition, timeBase);
  
  
  
          //changing flag to AVSEEK_FLAG_ANY does not change behavior
  
          int flag = 0;
  
          if (timeInBaseUnit &lt; lastTime) {
  
              flag = AVSEEK_FLAG_BACKWARD;
  
              System.out.println("seeking backward to " + timeInBaseUnit);
  
          } else {
  
              System.out.println("seeking forward to " + timeInBaseUnit);
  
          }
  
          avcodec_flush_buffers(videoCodec);
  
          av_seek_frame(videoFile, streamId, timeInBaseUnit, flag);
  
          return timeInBaseUnit;
  
      }
  
  
  
      private long fetchTimeInBaseUnit(long seekPositionMillis, avutil.AVRational timeBase) {
  
          return av_rescale_q((long) (seekPositionMillis / 1000.0 * AV_TIME_BASE), av_make_q(1, AV_TIME_BASE), timeBase);
  
      }
  
  
  
      private void readFrame() {
  
          while (av_read_frame(videoFile, framePacket) >= 0) {
  
              if (framePacket.stream_index() == streamId) {
  
                  // Decode video frame
  
                  final int[] frameFinished = new int[1];
  
                  avcodec_decode_video2(this.videoCodec, yuvFrame, frameFinished, framePacket);
  
  
  
                  if (frameFinished[0] != 0) {
  
                      av_free_packet(framePacket);
  
                      long millis = produceFinishedFrame();
  
                      System.out.println("produced time " + millis);
  
                      break;
  
                  }
  
              }
  
              av_free_packet(framePacket);
  
          }
  
      }
  
  
  
      private long produceFinishedFrame() {
  
          sws_scale(scalingContext, yuvFrame.data(), yuvFrame.linesize(), 0,
  
              videoCodec.height(), rgbFrame.data(), rgbFrame.linesize());
  
          final long pts = av_frame_get_best_effort_timestamp(yuvFrame);
  
          final double timeBase = av_q2d(fetchTimeBase());
  
          final long foundMillis = (long) (pts * 1000 * timeBase);
  
          lastTime = foundMillis;
  
          return foundMillis;
  
      }
  
  
  
      private avutil.AVRational fetchTimeBase() {
  
          return videoFile.streams(streamId).time_base();
  
      }
  
  
  
      private void init(String videoPath) {
  
          final avformat.AVFormatContext videoFile = new avformat.AVFormatContext(null);
  
  
  
          av_register_all();
  
          if (avformat_open_input(videoFile, videoPath, null, null) != 0) throw new RuntimeException("unable to open");
  
          if (avformat_find_stream_info(videoFile, (PointerPointer) null) &lt; 0) throw new RuntimeException("Couldn't find stream information");
  
  
  
          av_dump_format(videoFile, 0, videoPath, 0);
  
  
  
          final int streamId = findFirstVideoStream(videoFile);
  
  
  
          final avcodec.AVCodecContext codec = videoFile.streams(streamId).codec();
  
  
  
          final avcodec.AVCodec pCodec = avcodec_find_decoder(codec.codec_id());
  
          if (pCodec == null) throw new RuntimeException("Unsupported codec");
  
  
  
          if (avcodec_open2(codec, pCodec, (avutil.AVDictionary) null) &lt; 0) throw new RuntimeException("Could not open codec");
  
  
  
          final avutil.AVFrame yuvFrame = av_frame_alloc();
  
  
  
          final avutil.AVFrame rgbFrame = av_frame_alloc();
  
          if (rgbFrame == null) throw new RuntimeException("Can't allocate avframe");
  
  
  
          final int numBytes = avpicture_get_size(AV_PIX_FMT_RGB24, codec.width(), codec.height());
  
          final BytePointer frameBuffer = new BytePointer(av_malloc(numBytes));
  
  
  
          final swscale.SwsContext swsContext = sws_getContext(codec.width(), codec.height(), codec.pix_fmt(), codec.width(), codec.height(),
  
              AV_PIX_FMT_RGB24, SWS_BILINEAR, null, null, (DoublePointer) null);
  
  
  
          avpicture_fill(new avcodec.AVPicture(rgbFrame), frameBuffer, AV_PIX_FMT_RGB24, codec.width(), codec.height());
  
  
  
          this.videoFile = videoFile;
  
          this.videoCodec = codec;
  
          this.yuvFrame = yuvFrame;
  
          this.scalingContext = swsContext;
  
          this.rgbFrame = rgbFrame;
  
          this.streamId = streamId;
  
      }
  
  
  
      private static int findFirstVideoStream(avformat.AVFormatContext videoFile) {
  
          int videoStream = -1;
  
          for (int i = 0; i &lt; videoFile.nb_streams(); i++) {
  
              if (videoFile.streams(i).codec().codec_type() == AVMEDIA_TYPE_VIDEO) {
  
                  videoStream = i;
  
                  break;
  
              }
  
          }
  
          if (videoStream == -1) throw new RuntimeException("Didn't find video stream");
  
          return videoStream;
  
      }
  
  
  
      private void cleanUp() {
  
          av_free(this.rgbFrame);
  
          av_free(yuvFrame);
  
          avcodec_close(videoCodec);
  
          avformat_close_input(videoFile);
  
      }
  
  }
  
  </integer></integer>

  As input arg should be provided file from above.

• Revision 1161055129 : Be consistent with SAD values SAD returns unsigned values. Make all the declara

  26 juin 2012, par Johann

  Changed Paths : Modify /test/sad_test.cc Modify /vp8/common/mfqe.c Modify /vp8/common/rtcd_defs.sh Modify /vp8/common/sad_c.c Modify /vp8/common/variance.h Modify /vp8/common/x86/sad_sse2.asm Modify /vp8/encoder/mcomp.c Modify /vp8/encoder/rdopt.c Be consistent with SAD (...)

• Google Speech - Streaming Request Returns EOF

  9 octobre 2017, par Josh

  Using Go, I’m taking a RTMP stream, transcoding it to FLAC (using ffmpeg) and attempting to stream to Google’s Speech API to transcribe the audio. However, I keep getting EOF errors when sending the data. I can’t find any information on this error in the docs so I’m not exactly sure what’s causing it.

  I’m chunking the received data into 3s clips (length isn’t relevant as long as it’s less than the maximum length of a streaming recognition request).

  Here is the core of my code :

  func main() {
  
  
  
      done := make(chan os.Signal)
  
      received := make(chan []byte)
  
  
  
      go receive(received)
  
      go transcribe(received)
  
  
  
      signal.Notify(done, os.Interrupt, syscall.SIGTERM)
  
  
  
      select {
  
      case <-done:
  
          os.Exit(0)
  
      }
  
  }
  
  
  
  func receive(received chan<- []byte) {
  
      var b bytes.Buffer
  
      stdout := bufio.NewWriter(&b)
  
  
  
      cmd := exec.Command("ffmpeg", "-i", "rtmp://127.0.0.1:1935/live/key", "-f", "flac", "-ar", "16000", "-")
  
      cmd.Stdout = stdout
  
  
  
      if err := cmd.Start(); err != nil {
  
          log.Fatal(err)
  
      }
  
  
  
      duration, _ := time.ParseDuration("3s")
  
      ticker := time.NewTicker(duration)
  
  
  
      for {
  
          select {
  
          case <-ticker.C:
  
              stdout.Flush()
  
              log.Printf("Received %d bytes", b.Len())
  
              received <- b.Bytes()
  
              b.Reset()
  
          }
  
      }
  
  }
  
  
  
  func transcribe(received <-chan []byte) {
  
      ctx := context.TODO()
  
  
  
      client, err := speech.NewClient(ctx)
  
      if err != nil {
  
          log.Fatal(err)
  
      }
  
  
  
      stream, err := client.StreamingRecognize(ctx)
  
      if err != nil {
  
          log.Fatal(err)
  
      }
  
  
  
      // Send the initial configuration message.
  
      if err = stream.Send(&speechpb.StreamingRecognizeRequest{
  
          StreamingRequest: &speechpb.StreamingRecognizeRequest_StreamingConfig{
  
              StreamingConfig: &speechpb.StreamingRecognitionConfig{
  
                  Config: &speechpb.RecognitionConfig{
  
                      Encoding:        speechpb.RecognitionConfig_FLAC,
  
                      LanguageCode:    "en-GB",
  
                      SampleRateHertz: 16000,
  
                  },
  
              },
  
          },
  
      }); err != nil {
  
          log.Fatal(err)
  
      }
  
  
  
      for {
  
          select {
  
          case data := <-received:
  
              if len(data) > 0 {
  
                  log.Printf("Sending %d bytes", len(data))
  
                  if err := stream.Send(&speechpb.StreamingRecognizeRequest{
  
                      StreamingRequest: &speechpb.StreamingRecognizeRequest_AudioContent{
  
                          AudioContent: data,
  
                      },
  
                  }); err != nil {
  
                      log.Printf("Could not send audio: %v", err)
  
                  }
  
              }
  
          }
  
      }
  
  }

  Running this code gives this output :

  2017/10/09 16:05:00 Received 191704 bytes
  
  2017/10/09 16:05:00 Saving 191704 bytes
  
  2017/10/09 16:05:00 Sending 191704 bytes
  
  2017/10/09 16:05:00 Could not send audio: EOF
  
  
  
  2017/10/09 16:05:03 Received 193192 bytes
  
  2017/10/09 16:05:03 Saving 193192 bytes
  
  2017/10/09 16:05:03 Sending 193192 bytes
  
  2017/10/09 16:05:03 Could not send audio: EOF
  
  
  
  2017/10/09 16:05:06 Received 193188 bytes
  
  2017/10/09 16:05:06 Saving 193188 bytes
  
  2017/10/09 16:05:06 Sending 193188 bytes // Notice that this doesn't error
  
  
  
  2017/10/09 16:05:09 Received 191704 bytes
  
  2017/10/09 16:05:09 Saving 191704 bytes
  
  2017/10/09 16:05:09 Sending 191704 bytes
  
  2017/10/09 16:05:09 Could not send audio: EOF

  Notice that not all of the Sends fail.

  Could anyone point me in the right direction here ? Is it something to do with the FLAC headers or something ? I also wonder if maybe resetting the buffer causes some of the data to be dropped (i.e. it’s a non-trivial operation that actually takes some time to complete) and it doesn’t like this missing information ?

  Any help would be really appreciated.