Recherche avancée

Sur d’autres sites (8165)

• Using ffprobe to get number of keyframes in raw AVI file *without* processing entire file ?

  26 juillet 2018, par aggieNick02

  This question and answer cover how to get the framecount and keyframe count from an AVI file, which is very useful. I’ve got a raw AVI file and want to count the number of keyframes (equivalent to non-dropped frames for raw AVI), but it takes a long time to process through a raw AVI file.

  There is some way to get this information without fully processing the file, as VirtualDub provides both framecount and key framecount in the file information, as well as total keyframe size, almost instantly for a 25-second raw 1920x1080 AVI. But ffprobe requires count_frames to populate nb_read_frames, which takes some good processing time.

  I can do some math with the file’s size and the frame’s width/height/format to get a fairly good estimate of the number of frames, but I’m worried the overhead of the container could be enough to throw the math off for very short clips. (For my 25 second clip, I get 1286.12 frames, when there are really 1286.)

  Any thoughts on if there is a way to get this information programatically with ffprobe or ffmpeg without processing the whole file ? Or with another API on windows ?

• Android. Problems with AudioTrack class. Sound sometimes lost

  6 juin 2018, par bukka.wh

  I have found open source video player for Android, which uses ffmpeg to decode video.
  I have some problems with audio, that sometimes plays with jerks, but video picture is shown well. The basic idea of player is that audio and video are decoded in two different streams, and then in the third stream the are passed back, video picture is shown on SurfaceView and video sound is passed in byte array to AudioTrack and then plays. But sometimes sound is lost or playing with jerks. Can anyone give me start point for what to do (some basic concepts). May be I should change buffer size for AudioTrack or add some flags to it. Here is a piece of code, where AudioTrack class is created.

  private AudioTrack prepareAudioTrack(int sampleRateInHz,
  
          int numberOfChannels) {
  
  
  
      for (;;) {
  
          int channelConfig;
  
          if (numberOfChannels == 1) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_MONO;
  
          } else if (numberOfChannels == 2) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_STEREO;
  
          } else if (numberOfChannels == 3) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_FRONT_CENTER
  
                      | AudioFormat.CHANNEL_OUT_FRONT_RIGHT
  
                      | AudioFormat.CHANNEL_OUT_FRONT_LEFT;
  
          } else if (numberOfChannels == 4) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_QUAD;
  
          } else if (numberOfChannels == 5) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_QUAD
  
                      | AudioFormat.CHANNEL_OUT_LOW_FREQUENCY;
  
          } else if (numberOfChannels == 6) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_5POINT1;
  
          } else if (numberOfChannels == 8) {
  
              channelConfig = AudioFormat.CHANNEL_OUT_7POINT1;
  
          } else {
  
              channelConfig = AudioFormat.CHANNEL_OUT_STEREO;
  
          }
  
          try {
  
              Log.d("MyLog","Creating Audio player");
  
              int minBufferSize = AudioTrack.getMinBufferSize(sampleRateInHz,
  
                      channelConfig, AudioFormat.ENCODING_PCM_16BIT);
  
              AudioTrack audioTrack = new AudioTrack(
  
                      AudioManager.STREAM_MUSIC, sampleRateInHz,
  
                      channelConfig, AudioFormat.ENCODING_PCM_16BIT,
  
                      minBufferSize, AudioTrack.MODE_STREAM);
  
              return audioTrack;
  
          } catch (IllegalArgumentException e) {
  
              if (numberOfChannels > 2) {
  
                  numberOfChannels = 2;
  
              } else if (numberOfChannels > 1) {
  
                  numberOfChannels = 1;
  
              } else {
  
                  throw e;
  
              }
  
          }
  
      }
  
  }

  And this is a piece of native code where sound bytes are written to AudioTrack

  int player_write_audio(struct DecoderData *decoder_data, JNIEnv *env,
  
      int64_t pts, uint8_t *data, int data_size, int original_data_size) {
  
  struct Player *player = decoder_data->player;
  
  int stream_no = decoder_data->stream_no;
  
  int err = ERROR_NO_ERROR;
  
  int ret;
  
  AVCodecContext * c = player->input_codec_ctxs[stream_no];
  
  AVStream *stream = player->input_streams[stream_no];
  
  LOGI(10, "player_write_audio Writing audio frame")
  
  
  
  jbyteArray samples_byte_array = (*env)->NewByteArray(env, data_size);
  
  if (samples_byte_array == NULL) {
  
      err = -ERROR_NOT_CREATED_AUDIO_SAMPLE_BYTE_ARRAY;
  
      goto end;
  
  }
  
  
  
  if (pts != AV_NOPTS_VALUE) {
  
      player->audio_clock = av_rescale_q(pts, stream->time_base, AV_TIME_BASE_Q);
  
      LOGI(9, "player_write_audio - read from pts")
  
  } else {
  
      int64_t sample_time = original_data_size;
  
      sample_time *= 1000000ll;
  
      sample_time /= c->channels;
  
      sample_time /= c->sample_rate;
  
      sample_time /= av_get_bytes_per_sample(c->sample_fmt);
  
      player->audio_clock += sample_time;
  
      LOGI(9, "player_write_audio - added")
  
  }
  
  enum WaitFuncRet wait_ret = player_wait_for_frame(player,
  
          player->audio_clock + AUDIO_TIME_ADJUST_US, stream_no);
  
  if (wait_ret == WAIT_FUNC_RET_SKIP) {
  
      goto end;
  
  }
  
  
  
  LOGI(10, "player_write_audio Writing sample data")
  
  
  
  jbyte *jni_samples = (*env)->GetByteArrayElements(env, samples_byte_array,
  
          NULL);
  
  memcpy(jni_samples, data, data_size);
  
  (*env)->ReleaseByteArrayElements(env, samples_byte_array, jni_samples, 0);
  
  
  
  LOGI(10, "player_write_audio playing audio track");
  
  ret = (*env)->CallIntMethod(env, player->audio_track,
  
          player->audio_track_write_method, samples_byte_array, 0, data_size);
  
  jthrowable exc = (*env)->ExceptionOccurred(env);
  
  if (exc) {
  
      err = -ERROR_PLAYING_AUDIO;
  
      LOGE(3, "Could not write audio track: reason in exception");
  
      // TODO maybe release exc
  
      goto free_local_ref;
  
  }
  
  if (ret < 0) {
  
      err = -ERROR_PLAYING_AUDIO;
  
      LOGE(3,
  
              "Could not write audio track: reason: %d look in AudioTrack.write()", ret);
  
      goto free_local_ref;
  
  }
  
  
  
  free_local_ref:
  
  LOGI(10, "player_write_audio releasing local ref");
  
  (*env)->DeleteLocalRef(env, samples_byte_array);
  
  
  
  end: return err;

  }

  I will be pleased for any help !!!! Thank you very much !!!!

• Unity : Converting Texture2D to YUV420P using FFmpeg

  23 juillet 2021, par strong_kobayashi

  I'm trying to create a game in Unity where each frame is rendered into a texture and then put together into a video using FFmpeg. The output created by FFmpeg should eventually be sent over the network to a client UI. However, I'm struggling mainly with the part where a frame is caught, and passed to an unsafe method as a byte array where it should be processed further by FFmpeg. The wrapper I'm using is FFmpeg.AutoGen.

  



  The render to texture method :

  



  private IEnumerator CaptureFrame()
{
    yield return new WaitForEndOfFrame();

    RenderTexture.active = rt;
    frame.ReadPixels(rect, 0, 0);
    frame.Apply();

    bytes = frame.GetRawTextureData();

    EncodeAndWrite(bytes, bytes.Length);
}


  



  The unsafe encoding method so far :

  



  private unsafe void EncodeAndWrite(byte[] bytes, int size)
{
    GCHandle pinned = GCHandle.Alloc(bytes, GCHandleType.Pinned);
    IntPtr address = pinned.AddrOfPinnedObject();

    sbyte** inData = (sbyte**)address;
    fixed(int* lineSize = new int[1])
    {
        lineSize[0] = 4 * textureWidth;
        // Convert RGBA to YUV420P
        ffmpeg.sws_scale(sws, inData, lineSize, 0, codecContext->width, inputFrame->extended_data, inputFrame->linesize);
    }

    inputFrame->pts = frameCounter++;

    if(ffmpeg.avcodec_send_frame(codecContext, inputFrame) < 0)
        throw new ApplicationException("Error sending a frame for encoding!");

    pkt = new AVPacket();
    fixed(AVPacket* packet = &pkt)
        ffmpeg.av_init_packet(packet);
    pkt.data = null;
    pkt.size = 0;

    pinned.Free();
    ...
}


  



  sws_scale takes a sbyte** as the second parameter, therefore I'm trying to convert the input byte array to sbyte** by first pinning it with GCHandle and doing an explicit type conversion afterwards. I don't know if that's the correct way, though.

  



  Moreover, the condition if(ffmpeg.avcodec_send_frame(codecContext, inputFrame) < 0) alwasy throws an ApplicationException, where I also really don't know why this happens. codecContext and inputFrame are my AVCodecContext and AVFrame objects, respectively, and the fields are defined as the following :

  



  codecContext

  



  codecContext = ffmpeg.avcodec_alloc_context3(codec);
codecContext->bit_rate = 400000;
codecContext->width = textureWidth;
codecContext->height = textureHeight;

AVRational timeBase = new AVRational();
timeBase.num = 1;
timeBase.den = (int)fps;
codecContext->time_base = timeBase;
videoAVStream->time_base = timeBase;

AVRational frameRate = new AVRational();
frameRate.num = (int)fps;
frameRate.den = 1;
codecContext->framerate = frameRate;

codecContext->gop_size = 10;
codecContext->max_b_frames = 1;
codecContext->pix_fmt = AVPixelFormat.AV_PIX_FMT_YUV420P;


  



  inputFrame

  



  inputFrame = ffmpeg.av_frame_alloc();
inputFrame->format = (int)codecContext->pix_fmt;
inputFrame->width = textureWidth;
inputFrame->height = textureHeight;
inputFrame->linesize[0] = inputFrame->width;


  



  Any help in fixing the issue would be greatly appreciated :)