Recherche avancée

Sur d’autres sites (8020)

• How to seek by msec with ffmpeg ?

  26 mai 2014, par Srv19

  I am trying to seek in video by milliseconds with ffmpeg. I have been trying to use code from this question, which uses avformat_seek_file (i use it with -1 for stream number and AVSEEK_FLAG_ANY flag).

  After that is called, i try to read next frames, that is :

  if (av_read_frame(fmt_ctx, &pkt) >= 0)
  
  {
  
      int ret = 0;
  
  
  
      if (pkt.stream_index == video_stream_idx) {
  
          /* decode video frame */
  
          ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
  
          if (ret < 0) {
  
              fprintf(stderr, "Error decoding video frame\n");
  
              return ret;
  
          }
  
  //do something with frame
  
  }

  However, the frame->pts of retrieved frame always holds the time of the frame that was immediatly after last frame that was read before seeking.

  Edit : In spite of frame->pts forming unbroken sequence, seeking does occur. For some bizarre reason next frame i read is the first one. In fact, after i run :

     int got_frame = 0;
  
     do
  
     if (av_read_frame(fmt_ctx, &pkt) >= 0) {
  
         decode_packet_ro(&got_frame, 0);
  
         av_free_packet(&pkt);
  
     }
  
     else
  
     {
  
         read_cache = true;
  
         pkt.data = NULL;
  
         pkt.size = 0;
  
         break;
  
     }
  
     while(!got_frame || this->frame->pts*av_q2d(video_dec_ctx->time_base) * 1000 < tsms);

  next frame i read is always the first one.

• Get frame time in ffmpeg

  30 mai 2013, par Srv19

  I am trying to make a little video player that has seek bar (with ffmpeg, of course). For that i need function that will, using data from frame and/or packet, get me current time in the video that should be set in seek slider.

  It should work like this :

  my_time = get_cur_time()
  
  seek(my_time + 10)
  
  assert(my_time+10 == get_cur_time())
  
  seek(my_time - 10)
  
  assert(my_time-10 == get_cur_time())

  I do understand thatffmpeg does not support precise seeking, so equality here means "something reasonably cloae).

  What code have i used for this thus far :

  frame_time = frame->pts*av_q2d(video_dec_ctx->time_base) * 1000;

  where frame is AVFrame and video_dec_ctx is AVCodecContext.

  And for seeking :

     int fn = ffmpeg::av_rescale(tsms,fmt_ctx->streams[video_stream->index]->time_base.den,
  
                                 fmt_ctx->streams[video_stream->index]->time_base.num);
  
     int frame = fn/1000;
  
  
  
     printf("\t avformat_seek_file to %d\n",frame);
  
     int flags = AVSEEK_FLAG_FRAME;
  
     if (frame < this->frame->pts)
  
         flags |= AVSEEK_FLAG_BACKWARD;
  
     if(ffmpeg::av_seek_frame(fmt_ctx,video_stream->index,frame,flags))
  
     {
  
         printf("\nFailed to seek for time %d",frame);
  
        return false;
  
     }
  
  
  
     avcodec_flush_buffers(video_dec_ctx);
  
     int got_frame = 0;
  
     do
  
     if (av_read_frame(fmt_ctx, &pkt) >= 0) {
  
         decode_packet_ro(&got_frame, 0);
  
         av_free_packet(&pkt);
  
     }
  
     else
  
     {
  
         read_cache = true;
  
         pkt.data = NULL;
  
         pkt.size = 0;
  
         break;
  
     }
  
     while(!(got_frame && this->frame->pts >= frame));

  The code does forward seeking passably, but after any attempt of backward seeking my second assertion fails. After seeking to previous position, my method of getting time does not return position less that one before seeking. That causes my seek slider to work grossly incorrectly.

• FFMPEG AAC encoding causes audio to be lower in pitch

  14 février 2017, par Paul Knopf

  I built a sample application that encodes AAC (from PortAudio) into a MP4 container (no video stream).

  The resulting audio is lower in pitch.

  #include "stdafx.h"
  
  #include "TestRecording.h"
  
  #include "libffmpeg.h"
  
  
  
  TestRecording::TestRecording()
  
  {
  
  }
  
  
  
  
  
  TestRecording::~TestRecording()
  
  {
  
  }
  
  
  
  struct RecordingContext
  
  {
  
      RecordingContext()
  
      {
  
          formatContext = NULL;
  
          audioStream = NULL;
  
          audioFrame = NULL;
  
          audioFrameframeNumber = 0;
  
      }
  
  
  
      libffmpeg::AVFormatContext* formatContext;
  
      libffmpeg::AVStream* audioStream;
  
      libffmpeg::AVFrame* audioFrame;
  
      int audioFrameframeNumber;
  
  };
  
  
  
  static int AudioRecordCallback(const void *inputBuffer, void *outputBuffer,
  
      unsigned long framesPerBuffer,
  
      const PaStreamCallbackTimeInfo* timeInfo,
  
      PaStreamCallbackFlags statusFlags,
  
      void *userData)
  
  {
  
      RecordingContext* recordingContext = (RecordingContext*)userData;
  
  
  
      libffmpeg::avcodec_fill_audio_frame(recordingContext->audioFrame,
  
          recordingContext->audioFrame->channels,
  
          recordingContext->audioStream->codec->sample_fmt,
  
          static_cast<const unsigned="unsigned">(inputBuffer),
  
          (framesPerBuffer * sizeof(float) * recordingContext->audioFrame->channels),
  
          0);
  
  
  
      libffmpeg::AVPacket pkt;
  
      libffmpeg::av_init_packet(&amp;pkt);
  
      pkt.data = NULL;
  
      pkt.size = 0;
  
  
  
      int gotpacket;
  
      int result = avcodec_encode_audio2(recordingContext->audioStream->codec, &amp;pkt, recordingContext->audioFrame, &amp;gotpacket);
  
  
  
      if (result &lt; 0)
  
      {
  
          LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't encode the audio frame to acc");
  
          return paContinue;
  
      }
  
  
  
      if (gotpacket)
  
      {
  
          pkt.stream_index = recordingContext->audioStream->index;
  
          recordingContext->audioFrameframeNumber++;
  
  
  
          // this codec requires no bitstream filter, just send it to the muxer!
  
          result = libffmpeg::av_write_frame(recordingContext->formatContext, &amp;pkt);
  
          if (result &lt; 0)
  
          {
  
              LOG(ERROR) &lt;&lt; "Couldn't write the encoded audio frame";
  
              libffmpeg::av_free_packet(&amp;pkt);
  
              return paContinue;
  
          }
  
  
  
          libffmpeg::av_free_packet(&amp;pkt);
  
      }
  
  
  
      return paContinue;
  
  }
  
  
  
  static bool InitializeRecordingContext(RecordingContext* recordingContext)
  
  {
  
      int result = libffmpeg::avformat_alloc_output_context2(&amp;recordingContext->formatContext, NULL, NULL, "C:\\Users\\Paul\\Desktop\\test.mp4");
  
      if (result &lt; 0)
  
      {
  
          LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't create output format context");
  
          return false;
  
      }
  
  
  
      libffmpeg::AVCodec *audioCodec;
  
      audioCodec = libffmpeg::avcodec_find_encoder(libffmpeg::AV_CODEC_ID_AAC);
  
      if (audioCodec == NULL)
  
      {
  
          LOG(ERROR) &lt;&lt; "Couldn't find the encoder for AAC";
  
      }
  
  
  
      recordingContext->audioStream = libffmpeg::avformat_new_stream(recordingContext->formatContext, audioCodec);
  
      if (!recordingContext->audioStream)
  
      {
  
          LOG(ERROR) &lt;&lt; "Couldn't create the audio stream";
  
          return false;
  
      }
  
  
  
      recordingContext->audioStream->codec->bit_rate = 64000;
  
      recordingContext->audioStream->codec->sample_fmt = libffmpeg::AV_SAMPLE_FMT_FLTP;
  
      recordingContext->audioStream->codec->sample_rate = 48000;
  
      recordingContext->audioStream->codec->channel_layout = AV_CH_LAYOUT_STEREO;
  
      recordingContext->audioStream->codec->channels = libffmpeg::av_get_channel_layout_nb_channels(recordingContext->audioStream->codec->channel_layout);
  
  
  
      recordingContext->audioStream->codecpar->bit_rate = recordingContext->audioStream->codec->bit_rate;
  
      recordingContext->audioStream->codecpar->format = recordingContext->audioStream->codec->sample_fmt;
  
      recordingContext->audioStream->codecpar->sample_rate = recordingContext->audioStream->codec->sample_rate;
  
      recordingContext->audioStream->codecpar->channel_layout = recordingContext->audioStream->codec->channel_layout;
  
      recordingContext->audioStream->codecpar->channels = recordingContext->audioStream->codec->channels;
  
  
  
      result = libffmpeg::avcodec_open2(recordingContext->audioStream->codec, audioCodec, NULL);
  
      if (result &lt; 0)
  
      {
  
          LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the audio codec");
  
          return false;
  
      }
  
  
  
      // create a new frame to store the audio samples
  
      recordingContext->audioFrame = libffmpeg::av_frame_alloc();
  
      if (!recordingContext->audioFrame)
  
      {
  
          LOG(ERROR) &lt;&lt; "Couldn't alloce the output audio frame";
  
          return false;
  
      }
  
  
  
      recordingContext->audioFrame->nb_samples = recordingContext->audioStream->codec->frame_size;
  
      recordingContext->audioFrame->channel_layout = recordingContext->audioStream->codec->channel_layout;
  
      recordingContext->audioFrame->channels = recordingContext->audioStream->codec->channels;
  
      recordingContext->audioFrame->format = recordingContext->audioStream->codec->sample_fmt;
  
      recordingContext->audioFrame->sample_rate = recordingContext->audioStream->codec->sample_rate;
  
  
  
      result = libffmpeg::av_frame_get_buffer(recordingContext->audioFrame, 0);
  
      if (result &lt; 0)
  
      {
  
          LOG(ERROR) &lt;&lt; "Coudln't initialize the output audio frame buffer";
  
          return false;
  
      }
  
  
  
      // some formats want video_stream headers to be separate  
  
      if (!strcmp(recordingContext->formatContext->oformat->name, "mp4") || !strcmp(recordingContext->formatContext->oformat->name, "mov") || !strcmp(recordingContext->formatContext->oformat->name, "3gp"))
  
      {
  
          recordingContext->audioStream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
  
      }
  
  
  
      // open the ouput file
  
      if (!(recordingContext->formatContext->oformat->flags &amp; AVFMT_NOFILE))
  
      {
  
          result = libffmpeg::avio_open(&amp;recordingContext->formatContext->pb, recordingContext->formatContext->filename, AVIO_FLAG_WRITE);
  
          if (result &lt; 0)
  
          {
  
              LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the output file");
  
              return false;
  
          }
  
      }
  
  
  
      // write the stream headers
  
      result = libffmpeg::avformat_write_header(recordingContext->formatContext, NULL);
  
      if (result &lt; 0)
  
      {
  
          LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't write the headers to the file");
  
          return false;
  
      }
  
  
  
      return true;
  
  }
  
  
  
  static bool FinalizeRecordingContext(RecordingContext* recordingContext)
  
  {
  
      int result = 0;
  
  
  
      // write the trailing information
  
      if (recordingContext->formatContext->pb)
  
      {
  
          result = libffmpeg::av_write_trailer(recordingContext->formatContext);
  
          if (result &lt; 0)
  
          {
  
              LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't write the trailer information");
  
              return false;
  
          }
  
      }
  
  
  
      // close all the codes
  
      for (int i = 0; i &lt; (int)recordingContext->formatContext->nb_streams; i++)
  
      {
  
          result = libffmpeg::avcodec_close(recordingContext->formatContext->streams[i]->codec);
  
          if (result &lt; 0)
  
          {
  
              LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't close the codec");
  
              return false;
  
          }
  
      }
  
  
  
      // close the output file
  
      if (recordingContext->formatContext->pb)
  
      {
  
          if (!(recordingContext->formatContext->oformat->flags &amp; AVFMT_NOFILE))
  
          {
  
              result = libffmpeg::avio_close(recordingContext->formatContext->pb);
  
              if (result &lt; 0)
  
              {
  
                  LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't close the output file");
  
                  return false;
  
              }
  
          }
  
      }
  
  
  
      // free the format context and all of its data
  
      libffmpeg::avformat_free_context(recordingContext->formatContext);
  
  
  
      recordingContext->formatContext = NULL;
  
      recordingContext->audioStream = NULL;
  
  
  
      if (recordingContext->audioFrame)
  
      {
  
          libffmpeg::av_frame_free(&amp;recordingContext->audioFrame);
  
          recordingContext->audioFrame = NULL;
  
      }
  
  
  
      return true;
  
  }
  
  
  
  int TestRecording::Test()
  
  {
  
      PaError result = paNoError;
  
  
  
      result = Pa_Initialize();
  
      if (result != paNoError) LOGINT_WITH_MESSAGE(ERROR, result, "Error initializing audio device framework");
  
  
  
      RecordingContext recordingContext;
  
      if (!InitializeRecordingContext(&amp;recordingContext))
  
      {
  
          LOG(ERROR) &lt;&lt; "Couldn't start recording file";
  
          return 0;
  
      }
  
  
  
      auto defaultDevice = Pa_GetDefaultInputDevice();
  
      auto deviceInfo = Pa_GetDeviceInfo(defaultDevice);
  
  
  
      PaStreamParameters  inputParameters;
  
      inputParameters.device = defaultDevice;
  
      inputParameters.channelCount = 2;
  
      inputParameters.sampleFormat = paFloat32;
  
      inputParameters.suggestedLatency = deviceInfo->defaultLowInputLatency;
  
      inputParameters.hostApiSpecificStreamInfo = NULL;
  
  
  
      PaStream* stream = NULL;
  
      result = Pa_OpenStream(
  
          &amp;stream,
  
          &amp;inputParameters,
  
          NULL,
  
          48000,
  
          1024,
  
          paClipOff,
  
          AudioRecordCallback,
  
          &amp;recordingContext);
  
      if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the audio stream");
  
  
  
      result = Pa_StartStream(stream);
  
      if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't start the audio stream");
  
  
  
      Sleep(1000 * 5);
  
  
  
      result = Pa_StopStream(stream);
  
      if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't stop the audio stream");
  
  
  
      if (!FinalizeRecordingContext(&amp;recordingContext)) LOG(ERROR) &lt;&lt; "Couldn't stop recording file";
  
  
  
      result = Pa_CloseStream(stream);
  
      if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't stop the audio stream");
  
  
  
      return 0;
  
  }
  
  </const>

  Here is the stdout, in case it helps.

  https://gist.github.com/pauldotknopf/9f24a604ce1f8a081aa68da1bf169e98

  Why is the audio lower in pitch ? I assume I am overlooking a parameter that needs to be configured between PortAudio and FFMPEG. Is there something super obvious that I am missing ?