Recherche avancée

Sur d’autres sites (9401)

• FFmpeg C API - syncing video and audio

  10 novembre 2015, par Justin Bradley

  I am trimming video and having a hard getting the audio to sync correctly. The code below is as close as I’ve gotten it work. I’ve tried both re-encoding and not re-encoding the output streams.

  The video trims correctly and is written to the output container. The audio stream also trims correctly, but is written to the front of the output container. For example if the trim length is 10s - the correct portion of audio plays for 10s and then the correct portion of video plays.

  //////// audio stream ////////
  
  const AVStream *input_stream_audio = input_container->streams[audio_stream_index];
  
  const AVCodec *decoder_audio = avcodec_find_decoder(input_stream_audio->codec->codec_id);
  
  if(!decoder_audio) {
  
      cleanup(decoded_packet, output_container, decoded_frame);
  
      avformat_close_input(&input_container);
  
      LOGE("=> Audio decoder not found");
  
      return -1;
  
  }
  
  if(avcodec_open2(input_stream_audio->codec, decoder_audio, NULL) < 0) {
  
      cleanup(decoded_packet, output_container, decoded_frame);
  
      avformat_close_input(&input_container);
  
      LOGE("=> Error opening audio decoder");
  
      return -1;
  
  }
  
  
  
  AVStream *output_stream_audio = avformat_new_stream(output_container, NULL);
  
  if(avcodec_copy_context(output_stream_audio->codec, input_stream_audio->codec) != 0){
  
      LOGE("=> Failed to Copy audio Context ");
  
      return -1;
  
  }
  
  else {
  
      LOGI("=> Copied audio context ");
  
      output_stream_audio->codec->codec_id = input_stream_audio->codec->codec_id;
  
      output_stream_audio->codec->codec_tag = 0;
  
      output_stream_audio->pts = input_stream_audio->pts;
  
      output_stream_audio->time_base.num = input_stream_audio->time_base.num;
  
      output_stream_audio->time_base.den = input_stream_audio->time_base.den;
  
  
  
  }
  
  
  
  if(avio_open(&output_container->pb, output_file, AVIO_FLAG_WRITE) < 0) {
  
      cleanup(decoded_packet, output_container, decoded_frame);
  
      avformat_close_input(&input_container);
  
      LOGE("=> Error opening output file");
  
      return -1;
  
  }
  
  
  
  // allocate frame for conversion
  
  decoded_frame = avcodec_alloc_frame();
  
  if(!decoded_frame) {
  
      cleanup(decoded_packet, output_container, decoded_frame);
  
      avformat_close_input(&input_container);
  
      LOGE("=> Error allocating frame");
  
      return -1;
  
  }
  
  
  
  av_dump_format(input_container, 0, input_file, 0);
  
  avformat_write_header(output_container, NULL);
  
  av_init_packet(&decoded_packet);
  
  
  
  decoded_packet.data = NULL;
  
  decoded_packet.size = 0;
  
  int current_frame_num = 1;
  
  int current_frame_num_audio = 1;
  
  int got_frame, len;
  
  
  
  AVRational default_timebase;
  
  default_timebase.num = 1;
  
  default_timebase.den = AV_TIME_BASE;
  
  
  
  int64_t starttime_int64 = av_rescale_q((int64_t)( 12.0 * AV_TIME_BASE ), AV_TIME_BASE_Q, input_stream->time_base);
  
  int64_t endtime_int64 = av_rescale_q((int64_t)( 18.0 * AV_TIME_BASE ), AV_TIME_BASE_Q, input_stream->time_base);
  
  LOGI("=> starttime_int64:     %" PRId64, starttime_int64);
  
  LOGI("=> endtime_int64:       %" PRId64, endtime_int64);
  
  
  
  int64_t starttime_int64_audio = av_rescale_q((int64_t)( 12.0 * AV_TIME_BASE ), AV_TIME_BASE_Q, input_stream_audio->time_base);
  
  int64_t endtime_int64_audio = av_rescale_q((int64_t)( 18.0 * AV_TIME_BASE ), AV_TIME_BASE_Q, input_stream_audio->time_base);
  
  LOGI("=> starttime_int64_audio:     %" PRId64, starttime_int64_audio);
  
  LOGI("=> endtime_int64_audio:       %" PRId64, endtime_int64_audio);
  
  
  
  // loop input container and decode frames
  
  while(av_read_frame(input_container, &decoded_packet)>=0) {
  
      // video packets
  
      if (decoded_packet.stream_index == video_stream_index) {
  
          len = avcodec_decode_video2(input_stream->codec, decoded_frame, &got_frame, &decoded_packet);
  
          if(len < 0) {
  
              cleanup(decoded_packet, output_container, decoded_frame);
  
              avformat_close_input(&input_container);
  
              LOGE("=> No frames to decode");
  
              return -1;
  
          }
  
          // this is the trim range we're looking for
  
          if(got_frame && decoded_frame->pkt_pts >= starttime_int64 && decoded_frame->pkt_pts <= endtime_int64) {
  
                  av_init_packet(&encoded_packet);
  
                  encoded_packet.data =  NULL;
  
                  encoded_packet.size =  0;
  
  
  
                  ret = avcodec_encode_video2(output_stream->codec, &encoded_packet, decoded_frame, &got_frame);
  
                  if (ret < 0) {
  
                      cleanup(decoded_packet, output_container, decoded_frame);
  
                      avformat_close_input(&input_container);
  
                      LOGE("=> Error encoding frames");
  
                      return ret;
  
                  }
  
                  if(got_frame) {
  
                      if (output_stream->codec->coded_frame->key_frame) {
  
                          encoded_packet.flags |= AV_PKT_FLAG_KEY;
  
                      }
  
  
  
                      encoded_packet.stream_index = output_stream->index;
  
                      encoded_packet.pts = av_rescale_q(current_frame_num, output_stream->codec->time_base, output_stream->time_base);
  
                      encoded_packet.dts = av_rescale_q(current_frame_num, output_stream->codec->time_base, output_stream->time_base);
  
  
  
                      ret = av_interleaved_write_frame(output_container, &encoded_packet);
  
                      if (ret < 0) {
  
                          cleanup(decoded_packet, output_container, decoded_frame);
  
                          avformat_close_input(&input_container);
  
                          LOGE("=> Error encoding frames");
  
                          return ret;
  
                      }
  
                      else {
  
                          current_frame_num +=1;
  
                      }
  
                  }
  
              av_free_packet(&encoded_packet);
  
          }
  
      }
  
      // audio packets
  
      else if(decoded_packet.stream_index == audio_stream_index) {
  
          // this is the trim range we're looking for
  
          if(decoded_packet.pts >= starttime_int64_audio && decoded_packet.pts <= endtime_int64_audio) {
  
              av_init_packet(&encoded_packet);
  
  
  
              encoded_packet.data =  decoded_packet.data;
  
              encoded_packet.size =  decoded_packet.size;
  
              encoded_packet.stream_index = audio_stream_index;
  
              encoded_packet.pts = av_rescale_q(current_frame_num_audio, output_stream_audio->codec->time_base, output_stream_audio->time_base);
  
              encoded_packet.dts = av_rescale_q(current_frame_num_audio, output_stream_audio->codec->time_base, output_stream_audio->time_base);
  
  
  
              ret = av_interleaved_write_frame(output_container, &encoded_packet);
  
              if (ret < 0) {
  
                  cleanup(decoded_packet, output_container, decoded_frame);
  
                  avformat_close_input(&input_container);
  
                  LOGE("=> Error encoding frames");
  
                  return ret;
  
              }
  
              else {
  
                  current_frame_num_audio +=1;
  
              }
  
             av_free_packet(&encoded_packet);
  
          }
  
      }
  
  }

  Edit

  I have slight improvement on the initial code. The audio and video are still not perfectly synced, but the original problem of the audio playing first followed by the video is resolved.

  I’m now writing the decoded packet to the output container rather than re-encoding it.

  In the end though I have the same problem - the trimmed video’s audio and video streams are not perfectly synced.

  // audio packets
  
      else if(decoded_packet.stream_index == audio_stream_index) {
  
          // this is the trim range we're looking for
  
          if(decoded_packet.pts >= starttime_int64_audio && decoded_packet.pts <= endtime_int64_audio) {
  
              ret = av_interleaved_write_frame(output_container, &decoded_packet);
  
              if (ret < 0) {
  
                  cleanup(decoded_packet, output_container, decoded_frame);
  
                  avformat_close_input(&input_container);
  
                  LOGE("=> Error writing audio frame (%s)", av_err2str(ret));
  
                  return ret;
  
              }
  
              else {
  
                  current_frame_num_audio +=1;
  
              }
  
          }
  
          else if(decoded_frame->pkt_pts > endtime_int64_audio) {
  
              audio_copy_complete = true;
  
          }
  
      }

• How can i create a portrait video using Android's MediaRecorder

  23 mars 2015, par urudroid

  I have an Android application which is able to record and play a videos in portrait mode, those features are working fine on Android phones.

  The issue comes up because this video is needed to be played also on iOS devices (after being shared through a server).

  iOS is not correctly showing the video as it looks "cropped", but videos recorded on iOS are played without issues.

  So, the main difference between videos created on Android and iOS’ is the size and the rotation.

  Im using CWAC-Camera library for preview and recording and ffmpeg to scale the video down to 320x568px (as this is the standard size for both Android and iOS apps).

  Here is the metadata from an video created from Android :

  General
  
  Complete name                            : android_video.mp4
  
  Format                                   : MPEG-4
  
  Format profile                           : Base Media
  
  Codec ID                                 : isom
  
  File size                                : 447 KiB
  
  Duration                                 : 5s 596ms
  
  Overall bit rate                         : 654 Kbps
  
  Encoded date                             : UTC 1904-01-01 00:00:00
  
  Tagged date                              : UTC 1904-01-01 00:00:00
  
  Writing application                      : Lavf56.4.101
  
  
  
  Video
  
  ID                                       : 1
  
  Format                                   : AVC
  
  Format/Info                              : Advanced Video Codec
  
  Format profile                           : High@L2.1
  
  Format settings, CABAC                   : Yes
  
  Format settings, ReFrames                : 4 frames
  
  Codec ID                                 : avc1
  
  Codec ID/Info                            : Advanced Video Coding
  
  Duration                                 : 5s 406ms
  
  Bit rate                                 : 536 Kbps
  
  Width                                    : 568 pixels
  
  Height                                   : 320 pixels
  
  Display aspect ratio                     : 16:9
  
  Original display aspect ratio            : 16:9
  
  Rotation                                 : 270°
  
  Frame rate mode                          : Constant
  
  Frame rate                               : 14.985 fps
  
  Color space                              : YUV
  
  Chroma subsampling                       : 4:2:0
  
  Bit depth                                : 8 bits
  
  Scan type                                : Progressive
  
  Bits/(Pixel*Frame)                       : 0.197
  
  Stream size                              : 354 KiB (79%)
  
  Writing library                          : x264 core 142
  
  Encoding settings                        : cabac=1 / ref=3 / deblock=1:0:0 / analyse=0x3:0x113 / me=hex / subme=7 / psy=1 / psy_rd=1.00:0.00 / mixed_ref=1 / me_range=16 / chroma_me=1 / trellis=1 / 8x8dct=1 / cqm=0 / deadzone=21,11 / fast_pskip=1 / chroma_qp_offset=-2 / threads=6 / lookahead_threads=1 / sliced_threads=0 / nr=0 / decimate=1 / interlaced=0 / bluray_compat=0 / constrained_intra=0 / bframes=3 / b_pyramid=2 / b_adapt=1 / b_bias=0 / direct=1 / weightb=1 / open_gop=0 / weightp=2 / keyint=250 / keyint_min=14 / scenecut=40 / intra_refresh=0 / rc_lookahead=40 / rc=crf / mbtree=1 / crf=23.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / ip_ratio=1.40 / aq=1:1.00
  
  Language                                 : English
  
  Encoded date                             : UTC 1904-01-01 00:00:00
  
  Tagged date                              : UTC 1904-01-01 00:00:00
  
  
  
  Audio
  
  ID                                       : 2
  
  Format                                   : AAC
  
  Format/Info                              : Advanced Audio Codec
  
  Format profile                           : LC
  
  Codec ID                                 : 40
  
  Duration                                 : 5s 596ms
  
  Bit rate mode                            : Constant
  
  Bit rate                                 : 132 Kbps
  
  Channel(s)                               : 2 channels
  
  Channel(s)_Original                      : 1 channel
  
  Channel positions                        : Front: C
  
  Sampling rate                            : 44.1 KHz
  
  Compression mode                         : Lossy
  
  Stream size                              : 89.4 KiB (20%)
  
  Language                                 : English
  
  Encoded date                             : UTC 1904-01-01 00:00:00
  
  Tagged date                              : UTC 1904-01-01 00:00:00

  And here is the metadata from the video created on iOS :

  General
  
  Complete name                            : ios_video.mp4
  
  Format                                   : MPEG-4
  
  Format profile                           : Base Media / Version 2
  
  Codec ID                                 : mp42
  
  File size                                : 673 KiB
  
  Duration                                 : 7s 38ms
  
  Overall bit rate                         : 783 Kbps
  
  Encoded date                             : UTC 2015-03-17 19:16:36
  
  Tagged date                              : UTC 2015-03-17 19:16:37
  
  
  
  Video
  
  ID                                       : 2
  
  Format                                   : AVC
  
  Format/Info                              : Advanced Video Codec
  
  Format profile                           : Main@L3.0
  
  Format settings, CABAC                   : Yes
  
  Format settings, ReFrames                : 2 frames
  
  Codec ID                                 : avc1
  
  Codec ID/Info                            : Advanced Video Coding
  
  Duration                                 : 7s 33ms
  
  Bit rate                                 : 711 Kbps
  
  Width                                    : 320 pixels
  
  Height                                   : 568 pixels
  
  Display aspect ratio                     : 0.563
  
  Frame rate mode                          : Constant
  
  Frame rate                               : 30.000 fps
  
  Color space                              : YUV
  
  Chroma subsampling                       : 4:2:0
  
  Bit depth                                : 8 bits
  
  Scan type                                : Progressive
  
  Bits/(Pixel*Frame)                       : 0.130
  
  Stream size                              : 610 KiB (91%)
  
  Title                                    : Core Media Video
  
  Encoded date                             : UTC 2015-03-17 19:16:36
  
  Tagged date                              : UTC 2015-03-17 19:16:37
  
  Color primaries                          : BT.709
  
  Transfer characteristics                 : BT.709
  
  Matrix coefficients                      : BT.709
  
  Color range                              : Limited
  
  
  
  Audio
  
  ID                                       : 1
  
  Format                                   : AAC
  
  Format/Info                              : Advanced Audio Codec
  
  Format profile                           : LC
  
  Codec ID                                 : 40
  
  Duration                                 : 7s 38ms
  
  Source duration                          : 7s 105ms
  
  Bit rate mode                            : Constant
  
  Bit rate                                 : 64.0 Kbps
  
  Channel(s)                               : 2 channels
  
  Channel(s)_Original                      : 1 channel
  
  Channel positions                        : Front: C
  
  Sampling rate                            : 44.1 KHz
  
  Compression mode                         : Lossy
  
  Stream size                              : 56.8 KiB (8%)
  
  Source stream size                       : 57.2 KiB (9%)
  
  Title                                    : Core Media Audio
  
  Encoded date                             : UTC 2015-03-17 19:16:36
  
  Tagged date                              : UTC 2015-03-17 19:16:37

  The values width and height are inverted on Android, also the Rotation parameter is set to 270º (this is the rotation parameter for portrait videos).

  This is a sketch of how iOS’ videos look on iOS app :

  

  And this is how Android’s videos look on iOS app :

  

  So, in order to get the videos correctly displayed both on iOS and Android i need to be able to set the width to 320 and height to 568 on Android. I tried it from several places (outside and inside CWAC-Camera library) but i always get a Camera.Parameters error.

  It is possible to do this on Android ?

  EDIT :

  This is the result i get when i set the rotation to 0 with ffmpeg :

  

• reading ffmpeg output and sending it to a form

  3 juillet 2013, par Aeon2058

  I can run arguments through ffmpeg just fine, but I need to be able to read its output LIVE as it streams (as you may know, ffmpeg can take a while, and it updates its stderr twice a second with current frame, etc).

  I have a form called prog that was declared globally with ProgressForm prog = new ProgressForm(); The user inputs a folder of video files, some data is gathered, and then a button is pushed to start the encoding process with ffmpeg. The button_click event creates a new thread like so :

   runFFMpeg = new Thread(run_ffmpeg);
  
   runFFMpeg.start();

  runFFMpeg was initialized globally earlier with private Thread runFFMpeg;.

  Now I have the method run_ffmpeg :

  private void run_ffmpeg()
  
  {
  
      string program = "C:\\ffmpeg64.exe";
  
      string args = //some arguments that I know work;
  
  
  
      ProcessStartInfo run = new ProcessStartInfo(program,args);
  
      run.UseShellExecute = false;
  
      run.CreateNoWindow = true;
  
      run.RedirectStandardOutput = true;
  
      run.RedirectStandardError = true;
  
      Process runP = new Process();
  
      runP = Process.Start(run);
  
      runP.WaitForExit();
  
  
  
      //NOW WHAT?
  
  
  
   }

  I'm not sure what to do now to get the data LIVE, but if I can, I would be updating prog, which has a number of controls, including progress bars, etc. Typical output (that I'm interested in) looks like "frame= 240 fps= 12.8 q=0.0 size= 1273802kB time=00:00:08.008 bitrate=4415.2kbits/s dup=46 drop=0". I know how to parse that to get what I need, I just need that line !