Recherche avancée

Sur d’autres sites (4643)

• Unity : Converting Texture2D to YUV420P and sending with UDP using FFmpeg

  22 juin 2018, par potu1304

  In my Unity game each frame is rendered into a texture and then put together into a video using FFmpeg. Now my questions is if I am doing this right because avcodec_send_frame throws every time an exception.
  I am pretty sure that I am doing something wrong or in the wrong order or simply missing something.

  Here is the code for capturing the texture :

  void Update() {
  
          //StartCoroutine(CaptureFrame());
  
  
  
          if (rt == null)
  
          {
  
              rect = new Rect(0, 0, captureWidth, captureHeight);
  
              rt = new RenderTexture(captureWidth, captureHeight, 24);
  
              frame = new Texture2D(captureWidth, captureHeight, TextureFormat.RGB24, false);
  
          }
  
  
  
          Camera camera = this.GetComponent<camera>(); // NOTE: added because there was no reference to camera in original script; must add this script to Camera
  
          camera.targetTexture = rt;
  
          camera.Render();
  
  
  
          RenderTexture.active = rt;
  
          frame.ReadPixels(rect, 0, 0);
  
          frame.Apply();
  
  
  
          camera.targetTexture = null;
  
          RenderTexture.active = null;
  
  
  
          byte[] fileData = null;
  
          fileData = frame.GetRawTextureData();
  
          encoding(fileData, fileData.Length);
  
  
  
      }
  
  </camera>

  And here is the code for encoding and sending the byte data :

  private unsafe void encoding(byte[] bytes, int size)
  
      {
  
          Debug.Log("Encoding...");
  
          AVCodec* codec;
  
          codec = ffmpeg.avcodec_find_encoder(AVCodecID.AV_CODEC_ID_H264);
  
          int ret, got_output = 0;
  
  
  
          AVCodecContext* codecContext = null;
  
          codecContext = ffmpeg.avcodec_alloc_context3(codec);
  
          codecContext->bit_rate = 400000;
  
          codecContext->width = captureWidth;
  
          codecContext->height = captureHeight;
  
          //codecContext->time_base.den = 25;
  
          //codecContext->time_base.num = 1;
  
  
  
          AVRational timeBase = new AVRational();
  
          timeBase.num = 1;
  
          timeBase.den = 25;
  
          codecContext->time_base = timeBase;
  
          //AVStream* videoAVStream = null;
  
          //videoAVStream->time_base = timeBase;
  
  
  
  
  
  
  
          AVRational frameRate = new AVRational();
  
          frameRate.num = 25;
  
          frameRate.den = 1;
  
          codecContext->framerate = frameRate;
  
  
  
          codecContext->gop_size = 10;
  
          codecContext->max_b_frames = 1;
  
          codecContext->pix_fmt = AVPixelFormat.AV_PIX_FMT_YUV420P;
  
  
  
          AVFrame* inputFrame;
  
          inputFrame = ffmpeg.av_frame_alloc();
  
          inputFrame->format = (int)codecContext->pix_fmt;
  
          inputFrame->width = captureWidth;
  
          inputFrame->height = captureHeight;
  
          inputFrame->linesize[0] = inputFrame->width;
  
  
  
          AVPixelFormat dst_pix_fmt = AVPixelFormat.AV_PIX_FMT_YUV420P, src_pix_fmt = AVPixelFormat.AV_PIX_FMT_RGBA;
  
          int src_w = 1920, src_h = 1080, dst_w = 1920, dst_h = 1080;
  
          SwsContext* sws_ctx;
  
  
  
          GCHandle pinned = GCHandle.Alloc(bytes, GCHandleType.Pinned);
  
          IntPtr address = pinned.AddrOfPinnedObject();
  
  
  
          sbyte** inputData = (sbyte**)address;
  
          sws_ctx = ffmpeg.sws_getContext(src_w, src_h, src_pix_fmt,
  
                               dst_w, dst_h, dst_pix_fmt,
  
                               0, null, null, null);
  
  
  
          fixed (int* lineSize = new int[1])
  
          {
  
              lineSize[0] = 4 * captureHeight;
  
              // Convert RGBA to YUV420P
  
              ffmpeg.sws_scale(sws_ctx, inputData, lineSize, 0, codecContext->width, inputFrame->extended_data, inputFrame->linesize);
  
          }
  
  
  
          inputFrame->pts = counter++;
  
  
  
          if (ffmpeg.avcodec_send_frame(codecContext, inputFrame) < 0)
  
              throw new ApplicationException("Error sending a frame for encoding!");
  
  
  
          AVPacket pkt;
  
          pkt = new AVPacket();
  
          //pkt.data = inData;
  
          AVPacket* packet = &pkt;
  
          ffmpeg.av_init_packet(packet);
  
  
  
          Debug.Log("pkt.size " + pkt.size);
  
          pinned.Free();
  
          AVDictionary* options = null;
  
          ffmpeg.av_dict_set(&options, "pkt_size", "1300", 0);
  
          ffmpeg.av_dict_set(&options, "buffer_size", "65535", 0);
  
          AVIOContext* server = null;
  
          ffmpeg.avio_open2(&server, "udp://192.168.0.1:1111", ffmpeg.AVIO_FLAG_WRITE, null, &options);
  
          Debug.Log("encoded");
  
          ret = ffmpeg.avcodec_encode_video2(codecContext, &pkt, inputFrame, &got_output);
  
          ffmpeg.avio_write(server, pkt.data, pkt.size);
  
          ffmpeg.av_free_packet(&pkt);
  
          pkt.data = null;
  
          pkt.size = 0;
  
      }

  And every time I start the game

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

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

• ffmpeg demux into audio and video resets PTS

  30 juillet 2018, par Mukund Manikarnike

  Demuxing

  I am demuxing TS segments into audio and video as follows.

  ffmpeg -y -i input.ts -vcodec copy -an output_video.ts
  
  ffmpeg -y -i input.ts -acodec copy -vn output_audio.aac

  Inspecting Input

  The start_pts and start_time on input.ts are as shown below. I was able to inspect these values using ffprobe -show_streams -print_format json input.ts

  "start_pts": 8306558438,
  
  "start_time": "92295.093756",

  Inspecting output video

  The output .ts has some default start_pts and start_time values as shown below. These were also obtained using the same ffprobe command as indicated above.

  "start_pts": 126000,
  
  "start_time": "1.400000",

  Inspecting output audio

  The same ffprobe command on output_audio.aac shows that the output aac has invalid codec_tag and codec_tag_string as shown below. The start_pts and start_time are not present in the output_audio.aac.

  "codec_tag_string": "[0][0][0][0]", (should have been [15][0][0][0])
  
  "codec_tag": "0x0000", (should have been 0xf000)

  Questions

  1. Wondering if this difference in the start_pts, start_time, codec_tag is expected ?
  2. If it is expected, what can I do to ensure that the all of these parameters get retained on the output ?
  3. If it is not expected, is there some more information I can share to track this down ?

  Note

  There were other outputs that I found inconsistent in the ffprobe command for the output_audio.aac like duration etc.. I shared what I thought are most valuable at this point. If required I can share complete outputs from all of the above executions.

  [EDIT 07/30/2018 - 08:00 MST]
  logs for ffmpeg -y -i input.ts -vcodec copy -an output_video.ts -acodec copy -vn output_audio.aacare as shown below.

  ffmpeg version 4.0.2 Copyright (c) 2000-2018 the FFmpeg developers
  
    built with Apple LLVM version 9.0.0 (clang-900.0.39.2)
  
    configuration: --prefix=/usr/local/Cellar/ffmpeg/4.0.2 --enable-shared --enable-pthreads --enable-version3 --enable-hardcoded-tables --enable-avresample --cc=clang --host-cflags= --host-ldflags= --enable-gpl --enable-ffplay --enable-frei0r --enable-libass --enable-libfdk-aac --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopus --enable-librtmp --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libx264 --enable-libxvid --enable-opencl --enable-videotoolbox --disable-lzma --enable-libopenjpeg --disable-decoder=jpeg2000 --extra-cflags=-I/usr/local/Cellar/openjpeg/2.3.0/include/openjpeg-2.3 --enable-nonfree
  
    libavutil      56. 14.100 / 56. 14.100
  
    libavcodec     58. 18.100 / 58. 18.100
  
    libavformat    58. 12.100 / 58. 12.100
  
    libavdevice    58.  3.100 / 58.  3.100
  
    libavfilter     7. 16.100 /  7. 16.100
  
    libavresample   4.  0.  0 /  4.  0.  0
  
    libswscale      5.  1.100 /  5.  1.100
  
    libswresample   3.  1.100 /  3.  1.100
  
    libpostproc    55.  1.100 / 55.  1.100
  
  [mpegts @ 0x7f88ed803000] start time for stream 0 is not set in estimate_timings_from_pts
  
  Input #0, mpegts, from 'i7h9456s_media_46185.ts':
  
    Duration: 00:00:06.05, start: 86216.852667, bitrate: 2898 kb/s
  
    Program 1 
  
      Stream #0:0[0x102]: Data: timed_id3 (ID3  / 0x20334449)
  
      Stream #0:1[0x100]: Video: h264 (Constrained Baseline) ([27][0][0][0] / 0x001B), yuv420p(tv, smpte170m, progressive), 640x360 [SAR 1:1 DAR 16:9], 29.97 fps, 29.97 tbr, 90k tbn, 59.94 tbc
  
      Stream #0:2[0x101]: Audio: aac (LC) ([15][0][0][0] / 0x000F), 44100 Hz, stereo, fltp, 190 kb/s
  
  Output #0, mpegts, to '../output_video.ts':
  
    Metadata:
  
      encoder         : Lavf58.12.100
  
      Stream #0:0: Video: h264 (Constrained Baseline) ([27][0][0][0] / 0x001B), yuv420p(tv, smpte170m, progressive), 640x360 [SAR 1:1 DAR 16:9], q=2-31, 29.97 fps, 29.97 tbr, 90k tbn, 90k tbc
  
  Output #1, adts, to '../output_audio.aac':
  
    Metadata:
  
      encoder         : Lavf58.12.100
  
      Stream #1:0: Audio: aac (LC) ([15][0][0][0] / 0x000F), 44100 Hz, stereo, fltp, 190 kb/s
  
  Stream mapping:
  
    Stream #0:1 -> #0:0 (copy)
  
    Stream #0:2 -> #1:0 (copy)
  
  Press [q] to stop, [?] for help
  
  frame=  180 fps=0.0 q=-1.0 Lsize=    2088kB time=00:00:06.03 bitrate=2833.8kbits/s speed= 904x    
  
  video:1918kB audio:142kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.349750%

• Modify video frames but keep their timestamp in python (maybe with ffmpeg ?)

  3 août 2018, par bendaf

  I have .ts videos with variable frame rate and I would like to modify the frames of the videos and keep the timestamps belonging to the frames. I am using python and experiencing with ffmpeg, but I am open to any solution.

  The output of

  $ffmpeg -i myvideo.ts -hide_banner

  Input #0, mpegts, from 'myvideo.ts':
  
    Duration: 00:02:37.84, start: 1.400000, bitrate: 13799 kb/s
  
    Program 1 
  
      Metadata:
  
        service_name    : Service01
  
        service_provider: FFmpeg
  
      Stream #0:0[0x100]: Video: h264 (High) ([27][0][0][0] / 0x001B), yuv420p, 3840x1080, 25 fps, 25 tbr, 90k tbn, 50 tbc

  What I have tried so far is :

  import skvideo.io
  
  
  
  outpudict = {"-map": "0",
  
               "-vcodec": "libx264",
  
               "-pix_fmt": "yuv420p",
  
               "-f": "mpegts"
  
               }
  
  
  
  videogen = skvideo.io.vreader(args.input_video)
  
  writer = skvideo.io.FFmpegWriter(filename + file_extension, outputdict=outpudict)
  
  for i, frame in enumerate(videogen):
  
      # modify the frame
  
      writer.writeFrame(frame)
  
  
  
  writer.close()

  But so far I am not able to keep the pts and dts parameters of the frames only the format and encoding.

  Note : I have tried to use skvideo.io.FFmpegReader or pass the outputdict parameter also to vreader but the script crashed because of this bug.

  Note2 : I am checking the pts of the frames with

  $ffprobe -hide_banner -show_entries packet=pts,dts myvideo.ts

  Thank you for reading through my question, any idea would be appreciated !