Recherche avancée

Sur d’autres sites (5509)

• ffmpeg : Trying to access Ebur128Context->integrated_loudness but unsuccessful

  12 avril 2019, par Sourabh Jain

  [FFMPEG] Trying to access Ebur128Context->integrated_loudness but unsuccessful

  I am trying to run ebur128Filter on audio file . similar to be doing
  [http://ffmpeg.org/doxygen/2.6/f__ebur128_8c_source.html#l00135]

  ffmpeg -i sample.wav -filter_complex ebur128=peak=true -f null -

  result of which is :

  [Parsed_ebur128_0 @ 0x7f9d38403ec0] Summary:
  
  
  
  Integrated loudness:
  
  I: -15.5 LUFS
  
  Threshold: -25.6 LUFS
  
  
  
  Loudness range:
  
  LRA: 1.5 LU
  
  Threshold: -35.5 LUFS
  
  LRA low: -16.3 LUFS
  
  LRA high: -14.8 LUFS
  
  
  
  True peak:
  
  Peak: -0.4 dBFS 

  /*
  
   * Copyright (c) 2010 Nicolas George
  
   * Copyright (c) 2011 Stefano Sabatini
  
   * Copyright (c) 2012 Clément Bœsch
  
   *
  
   * Permission is hereby granted, free of charge, to any person obtaining a copy
  
   * of this software and associated documentation files (the "Software"), to deal
  
   * in the Software without restriction, including without limitation the rights
  
   * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  
   * copies of the Software, and to permit persons to whom the Software is
  
   * furnished to do so, subject to the following conditions:
  
   *
  
   * The above copyright notice and this permission notice shall be included in
  
   * all copies or substantial portions of the Software.
  
   *
  
   * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  
   * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  
   * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
  
   * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  
   * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  
   * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  
   * THE SOFTWARE.
  
   */
  
  
  
  /**
  
   * @file
  
   * API example for audio decoding and filtering
  
   * @example filtering_audio.c
  
   */
  
  
  
  #include 
  
  
  
  #include <libavcodec></libavcodec>avcodec.h>
  
  #include <libavformat></libavformat>avformat.h>
  
  #include <libavfilter></libavfilter>buffersink.h>
  
  #include <libavfilter></libavfilter>buffersrc.h>
  
  #include <libavutil></libavutil>opt.h>
  
  
  
  #define MAX_CHANNELS 63
  
  
  
  
  
  
  
  static const char *filter_descr = "ebur128=peak=true";
  
  
  
  static AVFormatContext *fmt_ctx;
  
  static AVCodecContext *dec_ctx;
  
  AVFilterContext *buffersink_ctx;
  
  AVFilterContext *buffersrc_ctx;
  
  AVFilterGraph *filter_graph;
  
  static int audio_stream_index = -1;
  
  
  
  struct rect { int x, y, w, h; };
  
  
  
  
  
  struct hist_entry {
  
      int count;                      ///&lt; how many times the corresponding value occurred
  
      double energy;                  ///&lt; E = 10^((L + 0.691) / 10)
  
      double loudness;                ///&lt; L = -0.691 + 10 * log10(E)
  
  };
  
  
  
  
  
  struct integrator {
  
      double *cache[MAX_CHANNELS];    ///&lt; window of filtered samples (N ms)
  
      int cache_pos;                  ///&lt; focus on the last added bin in the cache array
  
      double sum[MAX_CHANNELS];       ///&lt; sum of the last N ms filtered samples (cache content)
  
      int filled;                     ///&lt; 1 if the cache is completely filled, 0 otherwise
  
      double rel_threshold;           ///&lt; relative threshold
  
      double sum_kept_powers;         ///&lt; sum of the powers (weighted sums) above absolute threshold
  
      int nb_kept_powers;             ///&lt; number of sum above absolute threshold
  
      struct hist_entry *histogram;   ///&lt; histogram of the powers, used to compute LRA and I
  
  };
  
  
  
  typedef struct EBUR128Context {
  
      const AVClass *class;           ///&lt; AVClass context for log and options purpose
  
  
  
      /* peak metering */
  
      int peak_mode;                  ///&lt; enabled peak modes
  
      double *true_peaks;             ///&lt; true peaks per channel
  
      double *sample_peaks;           ///&lt; sample peaks per channel
  
      double *true_peaks_per_frame;   ///&lt; true peaks in a frame per channel
  
  #if CONFIG_SWRESAMPLE
  
      SwrContext *swr_ctx;            ///&lt; over-sampling context for true peak metering
  
      double *swr_buf;                ///&lt; resampled audio data for true peak metering
  
      int swr_linesize;
  
  #endif
  
  
  
      /* video  */
  
      int do_video;                   ///&lt; 1 if video output enabled, 0 otherwise
  
      int w, h;                       ///&lt; size of the video output
  
      struct rect text;               ///&lt; rectangle for the LU legend on the left
  
      struct rect graph;              ///&lt; rectangle for the main graph in the center
  
      struct rect gauge;              ///&lt; rectangle for the gauge on the right
  
      AVFrame *outpicref;             ///&lt; output picture reference, updated regularly
  
      int meter;                      ///&lt; select a EBU mode between +9 and +18
  
      int scale_range;                ///&lt; the range of LU values according to the meter
  
      int y_zero_lu;                  ///&lt; the y value (pixel position) for 0 LU
  
      int y_opt_max;                  ///&lt; the y value (pixel position) for 1 LU
  
      int y_opt_min;                  ///&lt; the y value (pixel position) for -1 LU
  
      int *y_line_ref;                ///&lt; y reference values for drawing the LU lines in the graph and the gauge
  
  
  
      /* audio */
  
      int nb_channels;                ///&lt; number of channels in the input
  
      double *ch_weighting;           ///&lt; channel weighting mapping
  
      int sample_count;               ///&lt; sample count used for refresh frequency, reset at refresh
  
  
  
      /* Filter caches.
  
       * The mult by 3 in the following is for X[i], X[i-1] and X[i-2] */
  
      double x[MAX_CHANNELS * 3];     ///&lt; 3 input samples cache for each channel
  
      double y[MAX_CHANNELS * 3];     ///&lt; 3 pre-filter samples cache for each channel
  
      double z[MAX_CHANNELS * 3];     ///&lt; 3 RLB-filter samples cache for each channel
  
  
  
  #define I400_BINS  (48000 * 4 / 10)
  
  #define I3000_BINS (48000 * 3)
  
      struct integrator i400;         ///&lt; 400ms integrator, used for Momentary loudness  (M), and Integrated loudness (I)
  
      struct integrator i3000;        ///&lt;    3s integrator, used for Short term loudness (S), and Loudness Range      (LRA)
  
  
  
      /* I and LRA specific */
  
      double integrated_loudness;     ///&lt; integrated loudness in LUFS (I)
  
      double loudness_range;          ///&lt; loudness range in LU (LRA)
  
      double lra_low, lra_high;       ///&lt; low and high LRA values
  
  
  
      /* misc */
  
      int loglevel;                   ///&lt; log level for frame logging
  
      int metadata;                   ///&lt; whether or not to inject loudness results in frames
  
      int dual_mono;                  ///&lt; whether or not to treat single channel input files as dual-mono
  
      double pan_law;                 ///&lt; pan law value used to calculate dual-mono measurements
  
      int target;                     ///&lt; target level in LUFS used to set relative zero LU in visualization
  
      int gauge_type;                 ///&lt; whether gauge shows momentary or short
  
      int scale;                      ///&lt; display scale type of statistics
  
  } EBUR128Context;
  
  
  
  void dump_ebur128_context(void *priv);
  
  
  
  static int open_input_file(const char *filename)
  
  {
  
      int ret;
  
      AVCodec *dec;
  
  
  
      if ((ret = avformat_open_input(&amp;fmt_ctx, filename, NULL, NULL)) &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
  
          return ret;
  
      }
  
  
  
      if ((ret = avformat_find_stream_info(fmt_ctx, NULL)) &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
  
          return ret;
  
      }
  
  
  
      /* select the audio stream */
  
      ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, &amp;dec, 0);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot find an audio stream in the input file\n");
  
          return ret;
  
      }
  
      audio_stream_index = ret;
  
  
  
      /* create decoding context */
  
      dec_ctx = avcodec_alloc_context3(dec);
  
      if (!dec_ctx)
  
          return AVERROR(ENOMEM);
  
      avcodec_parameters_to_context(dec_ctx, fmt_ctx->streams[audio_stream_index]->codecpar);
  
  
  
      /* init the audio decoder */
  
      if ((ret = avcodec_open2(dec_ctx, dec, NULL)) &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot open audio decoder\n");
  
          return ret;
  
      }
  
  
  
      return 0;
  
  }
  
  
  
  static int init_filters(const char *filters_descr)
  
  {
  
      char args[512];
  
      int ret = 0;
  
      const AVFilter *abuffersrc  = avfilter_get_by_name("abuffer");
  
      const AVFilter *abuffersink = avfilter_get_by_name("abuffersink");
  
      AVFilterInOut *outputs = avfilter_inout_alloc();
  
      AVFilterInOut *inputs  = avfilter_inout_alloc();
  
      static const enum AVSampleFormat out_sample_fmts[] = { AV_SAMPLE_FMT_S16, -1 };
  
      static const int64_t out_channel_layouts[] = { AV_CH_LAYOUT_MONO, -1 };
  
      static const int out_sample_rates[] = { 8000, -1 };
  
      const AVFilterLink *outlink;
  
      AVRational time_base = fmt_ctx->streams[audio_stream_index]->time_base;
  
  
  
      filter_graph = avfilter_graph_alloc();
  
      if (!outputs || !inputs || !filter_graph) {
  
          ret = AVERROR(ENOMEM);
  
          goto end;
  
      }
  
  
  
      /* buffer audio source: the decoded frames from the decoder will be inserted here. */
  
      if (!dec_ctx->channel_layout)
  
          dec_ctx->channel_layout = av_get_default_channel_layout(dec_ctx->channels);
  
      snprintf(args, sizeof(args),
  
              "time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
  
               time_base.num, time_base.den, dec_ctx->sample_rate,
  
               av_get_sample_fmt_name(dec_ctx->sample_fmt), dec_ctx->channel_layout);
  
      ret = avfilter_graph_create_filter(&amp;buffersrc_ctx, abuffersrc, "in",
  
                                         args, NULL, filter_graph);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
  
          goto end;
  
      }
  
  
  
      /* buffer audio sink: to terminate the filter chain. */
  
      ret = avfilter_graph_create_filter(&amp;buffersink_ctx, abuffersink, "out",
  
                                         NULL, NULL, filter_graph);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
  
          goto end;
  
      }
  
  
  
      ret = av_opt_set_int_list(buffersink_ctx, "sample_fmts", out_sample_fmts, -1,
  
                                AV_OPT_SEARCH_CHILDREN);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
  
          goto end;
  
      }
  
  
  
      ret = av_opt_set_int_list(buffersink_ctx, "channel_layouts", out_channel_layouts, -1,
  
                                AV_OPT_SEARCH_CHILDREN);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
  
          goto end;
  
      }
  
  
  
      ret = av_opt_set_int_list(buffersink_ctx, "sample_rates", out_sample_rates, -1,
  
                                AV_OPT_SEARCH_CHILDREN);
  
      if (ret &lt; 0) {
  
          av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
  
          goto end;
  
      }
  
  
  
      /*
  
       * Set the endpoints for the filter graph. The filter_graph will
  
       * be linked to the graph described by filters_descr.
  
       */
  
  
  
      /*
  
       * The buffer source output must be connected to the input pad of
  
       * the first filter described by filters_descr; since the first
  
       * filter input label is not specified, it is set to "in" by
  
       * default.
  
       */
  
      outputs->name       = av_strdup("in");
  
      outputs->filter_ctx = buffersrc_ctx;
  
      outputs->pad_idx    = 0;
  
      outputs->next       = NULL;
  
  
  
      /*
  
       * The buffer sink input must be connected to the output pad of
  
       * the last filter described by filters_descr; since the last
  
       * filter output label is not specified, it is set to "out" by
  
       * default.
  
       */
  
      inputs->name       = av_strdup("out");
  
      inputs->filter_ctx = buffersink_ctx;
  
      inputs->pad_idx    = 0;
  
      inputs->next       = NULL;
  
  
  
      if ((ret = avfilter_graph_parse_ptr(filter_graph, filters_descr,
  
                                          &amp;inputs, &amp;outputs, NULL)) &lt; 0)
  
          goto end;
  
  
  
      if ((ret = avfilter_graph_config(filter_graph, NULL)) &lt; 0)
  
          goto end;
  
  
  
      /* Print summary of the sink buffer
  
       * Note: args buffer is reused to store channel layout string */
  
      outlink = buffersink_ctx->inputs[0];
  
      av_get_channel_layout_string(args, sizeof(args), -1, outlink->channel_layout);
  
      av_log(NULL, AV_LOG_INFO, "Output: srate:%dHz fmt:%s chlayout:%s\n",
  
             (int)outlink->sample_rate,
  
             (char *)av_x_if_null(av_get_sample_fmt_name(outlink->format), "?"),
  
             args);
  
  
  
  end:
  
      avfilter_inout_free(&amp;inputs);
  
      avfilter_inout_free(&amp;outputs);
  
  
  
      return ret;
  
  }
  
  
  
  static void print_frame(const AVFrame *frame)
  
  {
  
  //    const int n = frame->nb_samples * av_get_channel_layout_nb_channels(frame->channel_layout);
  
  //    const uint16_t *p     = (uint16_t*)frame->data[0];
  
  //    const uint16_t *p_end = p + n;
  
  //
  
  //    while (p &lt; p_end) {
  
  //        fputc(*p    &amp; 0xff, stdout);
  
  //        fputc(*p>>8 &amp; 0xff, stdout);
  
  //        p++;
  
  //    }
  
  //    fflush(stdout);
  
  }
  
  
  
  int main(int argc, char **argv)
  
  {
  
      av_log_set_level(AV_LOG_DEBUG);
  
      int ret;
  
      AVPacket packet;
  
      AVFrame *frame = av_frame_alloc();
  
      AVFrame *filt_frame = av_frame_alloc();
  
  
  
      if (!frame || !filt_frame) {
  
          perror("Could not allocate frame");
  
          exit(1);
  
      }
  
  
  
  
  
      if ((ret = open_input_file(argv[1])) &lt; 0)
  
          goto end;
  
      if ((ret = init_filters(filter_descr)) &lt; 0)
  
          goto end;
  
  
  
      /* read all packets */
  
      while (1) {
  
          if ((ret = av_read_frame(fmt_ctx, &amp;packet)) &lt; 0)
  
              break;
  
  
  
          if (packet.stream_index == audio_stream_index) {
  
              ret = avcodec_send_packet(dec_ctx, &amp;packet);
  
              if (ret &lt; 0) {
  
                  av_log(NULL, AV_LOG_ERROR, "Error while sending a packet to the decoder\n");
  
                  break;
  
              }
  
  
  
              while (ret >= 0) {
  
                  ret = avcodec_receive_frame(dec_ctx, frame);
  
                  if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
  
                      break;
  
                  } else if (ret &lt; 0) {
  
                      av_log(NULL, AV_LOG_ERROR, "Error while receiving a frame from the decoder\n");
  
                      goto end;
  
                  }
  
  
  
                  if (ret >= 0) {
  
                      /* push the audio data from decoded frame into the filtergraph */
  
                      if (av_buffersrc_add_frame_flags(buffersrc_ctx, frame, AV_BUFFERSRC_FLAG_KEEP_REF) &lt; 0) {
  
                          av_log(NULL, AV_LOG_ERROR, "Error while feeding the audio filtergraph\n");
  
                          break;
  
                      }
  
  
  
                      /* pull filtered audio from the filtergraph */
  
                      while (1) {
  
                          ret = av_buffersink_get_frame(buffersink_ctx, filt_frame);
  
                          if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
  
                              break;
  
                          if (ret &lt; 0)
  
                              goto end;
  
                          print_frame(filt_frame);
  
                          av_frame_unref(filt_frame);
  
                      }
  
                      av_frame_unref(frame);
  
                  }
  
              }
  
          }
  
          av_packet_unref(&amp;packet);
  
      }
  
      if(filter_graph->nb_filters){
  
      av_log(filter_graph, AV_LOG_INFO, "hello : %d \n",
  
                  filter_graph->nb_filters);
  
      int i;
  
      for (int i = 0; i &lt; filter_graph->nb_filters; i++){
  
          av_log(filter_graph, AV_LOG_INFO, "name : %s \n",
  
                          filter_graph->filters[i]->name);
  
      }
  
      }
  
  
  
      av_log(filter_graph, AV_LOG_INFO, "name : %s \n",
  
                              filter_graph->filters[2]->name);
  
      void* priv = filter_graph->filters[2]->priv;
  
  
  
      dump_ebur128_context(&amp;priv);
  
  
  
  end:
  
  
  
  
  
      avfilter_graph_free(&amp;filter_graph);
  
      avcodec_free_context(&amp;dec_ctx);
  
      avformat_close_input(&amp;fmt_ctx);
  
      av_frame_free(&amp;frame);
  
      av_frame_free(&amp;filt_frame);
  
  
  
      if (ret &lt; 0 &amp;&amp; ret != AVERROR_EOF) {
  
          fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
  
          exit(1);
  
      }
  
  
  
      exit(0);
  
  }
  
  
  
  void dump_ebur128_context(void *priv){
  
      EBUR128Context *ebur128 = priv;
  
  
  
      av_log(ebur128, AV_LOG_INFO, "integrated_loudness : %5.1f \n",
  
                              ebur128->integrated_loudness);
  
      av_log(ebur128, AV_LOG_INFO, "lra_low : %5.1f \n",
  
                                  ebur128->lra_low);
  
      av_log(ebur128, AV_LOG_INFO, "lra_high : %5.1f \n",
  
                                  ebur128->lra_high);
  
  
  
  
  
  }

  program fails while accessing integrated loudness in dump_ebur128_context.

  can someone guide me about , how I should proceed in here.

• Extracting each individual frame from an H264 stream for real-time analysis with OpenCV

  5 mai 2017, par exclmtnpt

  Problem Outline

  I have an h264 real-time video stream (I’ll call this "the stream") being captured in Process1. My goal is to extract each frame from the stream as it comes through and use Process2 to analyze it with OpenCV. (Process1 is nodejs, Process2 is Python)

  Things I’ve tried, and their failure modes :

  • Send the stream directly from one Process1 to Process2 over a named fifo pipe :

  I succeeded in directing the stream from Process1 into the pipe. However, in Process2 (which is Python) I could not (a) extract individual frames from the stream, and (b) convert any extracted data from h264 into an OpenCV format (e.g. JPEG, numpy array).

  I had hoped to use OpenCV’s VideoCapture() method, but it does not allow you to pass a FIFO pipe as an input. I was able to use VideoCapture by saving the h264 stream to a .h264 file, and then passing that as the file path. This doesn’t help me, because I need to do my analysis in real time (i.e. I can’t save the stream to a file before reading it in to OpenCV).

  • Pipe the stream from Process1 to FFMPEG, use FFMPEG to change the stream format from h264 to MJPEG, then pipe the output to Process2 :

  I attempted this using the command :

  cat pipeFromProcess1.fifo | ffmpeg -i pipe:0 -f h264 -f mjpeg pipe:1 | cat > pipeToProcess2.fifo

  The biggest issue with this approach is that FFMPEG takes inputs from Process1 until Process1 is killed, and only then does Process2 begin to receive the data.

  Additionally, on the Process2 side, I still don’t understand how to extract individual frames from the data coming over the pipe. I open the pipe for reading (as "f") and then execute data = f.readline(). The size of data varies drastically (some reads have length on the order of 100, others length on the order of 1,000). When I use f.read() instead of f.readline(), the length is much larger, on the order of 100,000.

  If I were to know that I was getting the correct size chunk of data, I would still not know how to transform it into an OpenCV-compatible array because I don’t understand the format it’s coming over in. It’s a string, but when I print it out it looks like this :

  ��_M 0A0����tQ,\%��e���f/�H�#Y�p�f#�Kus�} F����ʳa�G������+$x�%V�� }[����Wo �1’̶A���c����*�&=Z^�o’��Ͽ� SX-ԁ涶V&H|��$
   ��<�E�� ��>�����u���7�����cR� �f�=�9 ��fs�q�ڄߧ�9v�]�Ӷ���& gr]�n�IRܜ�檯����
  � ����+ �I��w�}� ��9�o��� �w��M�m���IJ ��� �m�=�Soՙ}S �>j �,�ƙ�’���tad =i ��WY�FeC֓z �2�g� ;EXX��S��Ҁ*, ���w� _|�&�y��H��=��)� ���Ɗ3@ �h���Ѻ�Ɋ��ZzR`��)�y�� c�ڋ.��v� !u���� �S�I#�$9R�Ԯ0py z ��8 #��A�q�� �͕� ijc �bp=��۹ c SqH

  Converting from base64 doesn’t seem to help. I also tried :

  array = np.fromstring(data, dtype=np.uint8)

  which does convert to an array, but not one of a size that makes sense based on the 640x368x3 dimensions of the frames I’m trying to decode.

  • Using decoders such as Broadway.js to convert the h264 stream :

  These seem to be focused on streaming to a website, and I did not have success trying to re-purpose them for my goal.

  Clarification about what I’m NOT trying to do :

  I’ve found many related questions about streaming h264 video to a website. This is a solved problem, but none of the solutions help me extract individual frames and put them in an OpenCV-compatible format.

  Also, I need to use the extracted frames in real time on a continual basis. So saving each frame as a .jpg is not helpful.

  System Specs

  Raspberry Pi 3 running Raspian Jessie

  Additional Detail

  I’ve tried to generalize the problem I’m having in my question. If it’s useful to know, Process1 is using the node-bebop package to pull down the h264 stream (using drone.getVideoStream()) from a Parrot Bebop 2.0. I tried using the other video stream available through node-bebop (getMjpegStream()). This worked, but was not nearly real-time ; I was getting very intermittent data streams. I’ve entered that specific problem as an Issue in the node-bebop repository.

  Thanks for reading ; I really appreciate any help anyone can give !

• Transcoding HEVC 4K HDR using ffmpeg and vaapi

  13 mai 2021, par P. Brand

  I am trying to transcode a 4K HEVC HDR video to a lower bitrate using ffmpeg and VAAPI hardware acceleration for my LG OLED television.

  &#xA;&#xA;

  I use the following file :&#xA;Video

  &#xA;&#xA;

  Using the following command :

  &#xA;&#xA;

  ffmpeg -init_hw_device vaapi=va:/dev/dri/renderD128 -hwaccel vaapi -hwaccel_output_format vaapi -hwaccel_device va -filter_hw_device va -i LG\ 4K\ HDR\ Demo\ -\ Daylight.mkv -map 0:0 -t 00:00:20 -c:v hevc_vaapi -sei hdr -qp:v 21 lg_vaapi.mkv


  &#xA;&#xA;

  But this file is not recognized as HDR on my TV.

  &#xA;&#xA;

  When using the libx265 encoder (which is off course much slower) it works fine :

  &#xA;&#xA;

  ffmpeg -i LG\ 4K\ HDR\ Demo\ -\ Daylight.mkv -t 00:00:20 -map 0:0 -c:v libx265 -preset medium -crf 18 -x265-params "colorprim=bt2020:colormatrix=bt2020nc:transfer=smpte2084:colormatrix=bt2020nc:hdr=1:info=1:repeat-headers=1:master-display=G(13250,34500)B(7500,3000)R(34000,16000)WP(15635,16450)L(11000000,40)" lg_libx265.mkv


  &#xA;&#xA;

  When comparing the output of mediainfo on both files I can see the following properties are not set for the video track :

  &#xA;&#xA;

  &#xA;
  • Color range

  &#xA;

  • Color primaries

  &#xA;

  • Transfer characteristics

  &#xA;

  &#xA;&#xA;

  mediainfo for vaapi encode :

  &#xA;&#xA;

  General
Unique ID                                : 168011494166392912924249315217763643529 
(0x7E65D636029A5354FE73998A5ED6B089)
Complete name                            : lg_vaapi.mkv
Format                                   : Matroska
Format version                           : Version 4
File size                                : 118 MiB
Duration                                 : 20 s 4 ms
Overall bit rate                         : 49.6 Mb/s
Writing application                      : Lavf58.20.100
Writing library                          : Lavf58.20.100
ErrorDetectionType                       : Per level 1

Video
ID                                       : 1
Format                                   : HEVC
Format/Info                              : High Efficiency Video Coding
Format profile                           : Main 10@L5@Main
HDR format                               : SMPTE ST 2086, HDR10 compatible
Codec ID                                 : V_MPEGH/ISO/HEVC
Duration                                 : 20 s 4 ms
Bit rate                                 : 48.6 Mb/s
Width                                    : 3 840 pixels
Height                                   : 2 160 pixels
Display aspect ratio                     : 16:9
Frame rate mode                          : Constant
Frame rate                               : 59.940 (60000/1001) FPS
Color space                              : YUV
Chroma subsampling                       : 4:2:0
Bit depth                                : 10 bits
Bits/(Pixel*Frame)                       : 0.098
Stream size                              : 116 MiB (98%)
Writing library                          : Lavc58.35.100 hevc_vaapi
Default                                  : Yes
Forced                                   : No
Mastering display color primaries        : Display P3
Mastering display luminance              : min: 0.0040 cd/m2, max: 1100 cd/m2


  &#xA;&#xA;

  mediainfo for the libx265 encode :

  &#xA;&#xA;

  General
Unique ID                                : 261605749278874425324960669956061374077 (0xC4CF6F42FE952004772A02D5819DA67D)
Complete name                            : lg_libx265.mkv
Format                                   : Matroska
Format version                           : Version 4
File size                                : 155 MiB
Duration                                 : 47 s 715 ms
Overall bit rate                         : 27.3 Mb/s
Writing application                      : Lavf58.20.100
Writing library                          : Lavf58.20.100
ErrorDetectionType                       : Per level 1

Video
ID                                       : 1
Format                                   : HEVC
Format/Info                              : High Efficiency Video Coding
Format profile                           : Main 10@L5.1@Main
HDR format                               : SMPTE ST 2086, HDR10 compatible
Codec ID                                 : V_MPEGH/ISO/HEVC
Duration                                 : 47 s 715 ms
Bit rate                                 : 26.8 Mb/s
Width                                    : 3 840 pixels
Height                                   : 2 160 pixels
Display aspect ratio                     : 16:9
Frame rate mode                          : Constant
Frame rate                               : 59.940 (60000/1001) FPS
Color space                              : YUV
Chroma subsampling                       : 4:2:0
Bit depth                                : 10 bits
Bits/(Pixel*Frame)                       : 0.054
Stream size                              : 152 MiB (98%)
Writing library                          : x265 2.8:[Linux][GCC 9.1.0][64 bit] 10bit
Encoding settings                        : cpuid=1111039 / frame-threads=3 / wpp / no-pmode / no-pme / no-psnr / no-ssim / log-level=2 / input-csp=1 / input-res=3840x2160 / interlace=0 / total-frames=0 / level-idc=0 / high-tier=1 / uhd-bd=0 / ref=3 / no-allow-non-conformance / repeat-headers / annexb / no-aud / no-hrd / info / hash=0 / no-temporal-layers / open-gop / min-keyint=25 / keyint=250 / gop-lookahead=0 / bframes=4 / b-adapt=2 / b-pyramid / bframe-bias=0 / rc-lookahead=20 / lookahead-slices=8 / scenecut=40 / radl=0 / no-intra-refresh / ctu=64 / min-cu-size=8 / no-rect / no-amp / max-tu-size=32 / tu-inter-depth=1 / tu-intra-depth=1 / limit-tu=0 / rdoq-level=0 / dynamic-rd=0.00 / no-ssim-rd / signhide / no-tskip / nr-intra=0 / nr-inter=0 / no-constrained-intra / strong-intra-smoothing / max-merge=2 / limit-refs=3 / no-limit-modes / me=1 / subme=2 / merange=57 / temporal-mvp / weightp / no-weightb / no-analyze-src-pics / deblock=0:0 / sao / no-sao-non-deblock / rd=3 / no-early-skip / rskip / no-fast-intra / no-tskip-fast / no-cu-lossless / no-b-intra / no-splitrd-skip / rdpenalty=0 / psy-rd=2.00 / psy-rdoq=0.00 / no-rd-refine / no-lossless / cbqpoffs=0 / crqpoffs=0 / rc=crf / crf=18.0 / qcomp=0.60 / qpstep=4 / stats-write=0 / stats-read=0 / ipratio=1.40 / pbratio=1.30 / aq-mode=1 / aq-strength=1.00 / cutree / zone-count=0 / no-strict-cbr / qg-size=32 / no-rc-grain / qpmax=69 / qpmin=0 / no-const-vbv / sar=1 / overscan=0 / videoformat=5 / range=0 / colorprim=9 / transfer=16 / colormatrix=9 / chromaloc=0 / display-window=0 / master-display=G(13250,34500)B(7500,3000)R(34000,16000)WP(15635,16450)L(10000000,50) / max-cll=0,0 / min-luma=0 / max-luma=1023 / log2-max-poc-lsb=8 / vui-timing-info / vui-hrd-info / slices=1 / no-opt-qp-pps / no-opt-ref-list-length-pps / no-multi-pass-opt-rps / scenecut-bias=0.05 / no-opt-cu-delta-qp / no-aq-motion / hdr / no-hdr-opt / no-dhdr10-opt / no-idr-recovery-sei / analysis-reuse-level=5 / scale-factor=0 / refine-intra=0 / refine-inter=0 / refine-mv=0 / no-limit-sao / ctu-info=0 / no-lowpass-dct / refine-mv-type=0 / copy-pic=1 / max-ausize-factor=1.0 / no-dynamic-refine / no-single-sei
Default                                  : Yes
Forced                                   : No
Color range                              : Limited
Color primaries                          : BT.2020
Transfer characteristics                 : PQ
Matrix coefficients                      : BT.2020 non-constant
Mastering display color primaries        : Display P3
Mastering display luminance              : min: 0.0040 cd/m2, max: 1100 cd/m2


  &#xA;&#xA;

  I suspect Color range, Color primaries and Transfer characteristics are necessary to make the file recognized as HDR by my TV. &#xA;How can I add these properties to the VAAPI encoded file ?

  &#xA;&#xA;

  Edit :&#xA;This patch fixes the problem :&#xA;Patch

  &#xA;