Recherche avancée

Sur d’autres sites (11891)

• How to write NALs produced by x264_encoder_encode() using ffmpeg av_interleaved_write_frame()

  21 janvier 2013, par Haleeq Usman

  I have been trying to produce a "flv" video file in the following sequence :

  av_register_all();
  
  
  
  // Open video file
  
  if (avformat_open_input(&pFormatCtx, "6.mp4", NULL, NULL) != 0)
  
      return -1; // Couldn't open file
  
  
  
  // Retrieve stream information
  
  if (avformat_find_stream_info(pFormatCtx, NULL) < 0)
  
      return -1; // Couldn't find stream information
  
  
  
  // Dump information about file onto standard error
  
  av_dump_format(pFormatCtx, 0, "input_file.mp4", 0);
  
  
  
  // Find the first video stream
  
  videoStream = -1;
  
  for (i = 0; i < pFormatCtx->nb_streams; i++)
  
      if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO) {
  
          videoStream = i;
  
          break;
  
      }
  
  if (videoStream == -1)
  
      return -1; // Didn't find a video stream
  
  
  
  // Get a pointer to the codec context for the video stream
  
  pCodecCtx = pFormatCtx->streams[videoStream]->codec;
  
  
  
  // Find the decoder for the video stream
  
  pCodec = avcodec_find_decoder(pCodecCtx->codec_id);
  
  if (pCodec == NULL) {
  
      fprintf(stderr, "Unsupported codec!\n");
  
      return -1; // Codec not found
  
  }
  
  // Open codec
  
  if (avcodec_open2(pCodecCtx, pCodec, NULL) < 0)
  
      return -1; // Could not open codec
  
  
  
  // Allocate video frame
  
  pFrame = avcodec_alloc_frame();
  
  
  
  // Allocate video frame
  
  pFrame = avcodec_alloc_frame();
  
  
  
  // Allocate an AVFrame structure
  
  pFrameYUV420 = avcodec_alloc_frame();
  
  if (pFrameYUV420 == NULL)
  
      return -1;
  
  
  
  // Determine required buffer size and allocate buffer
  
  numBytes = avpicture_get_size(pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);
  
  buffer = (uint8_t *) av_malloc(numBytes * sizeof(uint8_t));
  
  
  
  // Assign appropriate parts of buffer to image planes in pFrameYUV420
  
  // Note that pFrameYUV420 is an AVFrame, but AVFrame is a superset of AVPicture
  
  avpicture_fill((AVPicture *) pFrameRGB, buffer, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);
  
  
  
  // Setup scaler
  
  img_convert_ctx = sws_getContext(pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, SWS_BILINEAR, 0, 0, 0);
  
  if (img_convert_ctx == NULL) {
  
      fprintf(stderr, "Cannot initialize the conversion context!\n");
  
      exit(1);
  
  }
  
  
  
  // Setup encoder/muxing now
  
  filename = "output_file.flv";
  
  fmt = av_guess_format("flv", filename, NULL);
  
  if (fmt == NULL) {
  
      printf("Could not guess format.\n");
  
      return -1;
  
  }
  
  /* allocate the output media context */
  
  oc = avformat_alloc_context();
  
  if (oc == NULL) {
  
      printf("could not allocate context.\n");
  
      return -1;
  
  }
  
  oc->oformat = fmt;
  
  snprintf(oc->filename, sizeof(oc->filename), "%s", filename);
  
  
  
  video_st = NULL;
  
  if (fmt->video_codec != AV_CODEC_ID_NONE) {
  
      video_st = add_stream(oc, &video_codec, fmt->video_codec);
  
  }
  
  
  
  // Let's see some information about our format
  
  av_dump_format(oc, 0, filename, 1);
  
  
  
  /* open the output file, if needed */
  
  if (!(fmt->flags & AVFMT_NOFILE)) {
  
      ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);
  
      if (ret < 0) {
  
          fprintf(stderr, "Could not open '%s': %s\n", filename, av_err2str(ret));
  
          return 1;
  
      }
  
      }
  
  /* Write the stream header, if any. */
  
  ret = avformat_write_header(oc, NULL);
  
  if (ret < 0) {
  
      fprintf(stderr, "Error occurred when opening output file: %s\n", av_err2str(ret));
  
      return 1;
  
  }
  
  
  
  // Setup x264 params
  
  x264_param_t param;
  
  x264_param_default_preset(&param, "veryfast", "zerolatency");
  
  param.i_threads = 1;
  
  param.i_width = video_st->codec->width;
  
  param.i_height = video_st->codec->height;
  
  param.i_fps_num = STREAM_FRAME_RATE; // 30 fps, same as video
  
  param.i_fps_den = 1;
  
  // Intra refres:
  
  param.i_keyint_max = STREAM_FRAME_RATE;
  
  param.b_intra_refresh = 1;
  
  // Rate control:
  
  param.rc.i_rc_method = X264_RC_CRF;
  
  param.rc.f_rf_constant = 25;
  
  param.rc.f_rf_constant_max = 35;
  
  // For streaming:
  
  param.b_repeat_headers = 1;
  
  param.b_annexb = 1;
  
  x264_param_apply_profile(&param, "baseline");
  
  
  
  x264_t* encoder = x264_encoder_open(&param);
  
  x264_picture_t pic_in, pic_out;
  
  x264_picture_alloc(&pic_in, X264_CSP_I420, video_st->codec->width, video_st->codec->height);
  
  
  
  x264_nal_t* nals;
  
  int i_nals;
  
  
  
  // The loop:
  
  // 1. Read frames
  
  // 2. Decode the frame
  
  // 3. Attempt to re-encode using x264
  
  // 4. Write the x264 encoded frame using av_interleaved_write_frame
  
  while (av_read_frame(pFormatCtx, &packet) >= 0) {
  
      // Is this a packet from the video stream?
  
      if (packet.stream_index == videoStream) {
  
          // Decode video frame
  
          avcodec_decode_video2(pCodecCtx, pFrame, &frameFinished, &packet);
  
  
  
          // Did we get a video frame?
  
          if (frameFinished) {
  
              sws_scale(img_convert_ctx, pFrame->data, pFrame->linesize, 0, pCodecCtx->height, pic_in.img.plane, pic_in.img.i_stride);
  
              int frame_size = x264_encoder_encode(encoder, &nals, &i_nals, &pic_in, &pic_out);
  
  
  
              if (frame_size >= 0) {
  
                  if (i_nals < 0)
  
                      printf("invalid frame size: %d\n", i_nals);
  
                  // write out NALs
  
                  for (i = 0; i < i_nals; i++) {
  
                      // initalize a packet
  
                      AVPacket p;
  
                      av_init_packet(&p);
  
                      p.data = nals[i].p_payload;
  
                      p.size = nals[i].i_payload;
  
                      p.stream_index = video_st->index;
  
                      p.flags = AV_PKT_FLAG_KEY;
  
                      p.pts = AV_NOPTS_VALUE;
  
                      p.dts = AV_NOPTS_VALUE;
  
                      ret = av_interleaved_write_frame(oc, &p);
  
                  }
  
              }
  
              printf("encoded frame #%d\n", frame_count);
  
              frame_count++;
  
          }
  
      }
  
  
  
      // Free the packet that was allocated by av_read_frame
  
      av_free_packet(&packet);
  
  }
  
  
  
  // Now we free up resources used/close codecs, and finally close our program.

  Here is the implementation for the add_stream() function :

  /* Add an output stream. */
  
  static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec, enum AVCodecID codec_id) {
  
      AVCodecContext *c;
  
      AVStream *st;
  
      int r;
  
      /* find the encoder */
  
      *codec = avcodec_find_encoder(codec_id);
  
      if (!(*codec)) {
  
          fprintf(stderr, "Could not find encoder for '%s'\n",
  
                  avcodec_get_name(codec_id));
  
          exit(1);
  
      }
  
      st = avformat_new_stream(oc, *codec);
  
      if (!st) {
  
          fprintf(stderr, "Could not allocate stream\n");
  
          exit(1);
  
      }
  
      st->id = oc->nb_streams - 1;
  
      c = st->codec;
  
      switch ((*codec)->type) {
  
      case AVMEDIA_TYPE_AUDIO:
  
          st->id = 1;
  
          c->sample_fmt = AV_SAMPLE_FMT_FLTP;
  
          c->bit_rate = 64000;
  
          c->sample_rate = 44100;
  
          c->channels = 2;
  
          break;
  
      case AVMEDIA_TYPE_VIDEO:
  
          avcodec_get_context_defaults3(c, *codec);
  
          c->codec_id = codec_id;
  
          c->bit_rate = 500*1000;
  
          //c->rc_min_rate = 500*1000;
  
          //c->rc_max_rate = 500*1000;
  
          //c->rc_buffer_size = 500*1000;
  
          /* Resolution must be a multiple of two. */
  
          c->width = 1280;
  
          c->height = 720;
  
          /* timebase: This is the fundamental unit of time (in seconds) in terms
  
           * of which frame timestamps are represented. For fixed-fps content,
  
           * timebase should be 1/framerate and timestamp increments should be
  
           * identical to 1. */
  
          c->time_base.den = STREAM_FRAME_RATE;
  
          c->time_base.num = 1;
  
          c->gop_size = 12; /* emit one intra frame every twelve frames at most */
  
          c->pix_fmt = STREAM_PIX_FMT;
  
          if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
  
              /* just for testing, we also add B frames */
  
              c->max_b_frames = 2;
  
          }
  
          if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
  
              /* Needed to avoid using macroblocks in which some coeffs overflow.
  
               * This does not happen with normal video, it just happens here as
  
               * the motion of the chroma plane does not match the luma plane. */
  
              c->mb_decision = 2;
  
          }
  
          break;
  
      default:
  
          break;
  
      }
  
      /* Some formats want stream headers to be separate. */
  
      if (oc->oformat->flags & AVFMT_GLOBALHEADER)
  
          c->flags |= CODEC_FLAG_GLOBAL_HEADER;
  
      return st;
  
  }

  After the encoding is complete, I check the output file output_file.flv. I notice it's size is very large : 101MB and it does not play. If I use ffmpeg to decode/encode the input file, then I get an output file about 83MB in size (which is about the same size as the original .mp4 file used as input). Also, the 83MB output from just using ffmpeg C api, as opposed to using x264 for the encoding step, plays just fine. Does anyone know where I am going wrong ? I have tried researching this for a few days now but with no luck :(. I feel that I am close to making it work, however, I just cannot figure out what I am doing wrong. Thank you !

• How to write NALs produced by x264_encoder_encode() using ffmpeg av_interleaved_write_frame()

  21 janvier 2013, par Haleeq Usman

  I have been trying to produce a "flv" video file in the following sequence :

  av_register_all();
  
  
  
  // Open video file
  
  if (avformat_open_input(&pFormatCtx, "6.mp4", NULL, NULL) != 0)
  
      return -1; // Couldn't open file
  
  
  
  // Retrieve stream information
  
  if (avformat_find_stream_info(pFormatCtx, NULL) < 0)
  
      return -1; // Couldn't find stream information
  
  
  
  // Dump information about file onto standard error
  
  av_dump_format(pFormatCtx, 0, "input_file.mp4", 0);
  
  
  
  // Find the first video stream
  
  videoStream = -1;
  
  for (i = 0; i < pFormatCtx->nb_streams; i++)
  
      if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO) {
  
          videoStream = i;
  
          break;
  
      }
  
  if (videoStream == -1)
  
      return -1; // Didn't find a video stream
  
  
  
  // Get a pointer to the codec context for the video stream
  
  pCodecCtx = pFormatCtx->streams[videoStream]->codec;
  
  
  
  // Find the decoder for the video stream
  
  pCodec = avcodec_find_decoder(pCodecCtx->codec_id);
  
  if (pCodec == NULL) {
  
      fprintf(stderr, "Unsupported codec!\n");
  
      return -1; // Codec not found
  
  }
  
  // Open codec
  
  if (avcodec_open2(pCodecCtx, pCodec, NULL) < 0)
  
      return -1; // Could not open codec
  
  
  
  // Allocate video frame
  
  pFrame = avcodec_alloc_frame();
  
  
  
  // Allocate video frame
  
  pFrame = avcodec_alloc_frame();
  
  
  
  // Allocate an AVFrame structure
  
  pFrameYUV420 = avcodec_alloc_frame();
  
  if (pFrameYUV420 == NULL)
  
      return -1;
  
  
  
  // Determine required buffer size and allocate buffer
  
  numBytes = avpicture_get_size(pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);
  
  buffer = (uint8_t *) av_malloc(numBytes * sizeof(uint8_t));
  
  
  
  // Assign appropriate parts of buffer to image planes in pFrameYUV420
  
  // Note that pFrameYUV420 is an AVFrame, but AVFrame is a superset of AVPicture
  
  avpicture_fill((AVPicture *) pFrameRGB, buffer, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);
  
  
  
  // Setup scaler
  
  img_convert_ctx = sws_getContext(pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, SWS_BILINEAR, 0, 0, 0);
  
  if (img_convert_ctx == NULL) {
  
      fprintf(stderr, "Cannot initialize the conversion context!\n");
  
      exit(1);
  
  }
  
  
  
  // Setup encoder/muxing now
  
  filename = "output_file.flv";
  
  fmt = av_guess_format("flv", filename, NULL);
  
  if (fmt == NULL) {
  
      printf("Could not guess format.\n");
  
      return -1;
  
  }
  
  /* allocate the output media context */
  
  oc = avformat_alloc_context();
  
  if (oc == NULL) {
  
      printf("could not allocate context.\n");
  
      return -1;
  
  }
  
  oc->oformat = fmt;
  
  snprintf(oc->filename, sizeof(oc->filename), "%s", filename);
  
  
  
  video_st = NULL;
  
  if (fmt->video_codec != AV_CODEC_ID_NONE) {
  
      video_st = add_stream(oc, &video_codec, fmt->video_codec);
  
  }
  
  
  
  // Let's see some information about our format
  
  av_dump_format(oc, 0, filename, 1);
  
  
  
  /* open the output file, if needed */
  
  if (!(fmt->flags & AVFMT_NOFILE)) {
  
      ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);
  
      if (ret < 0) {
  
          fprintf(stderr, "Could not open '%s': %s\n", filename, av_err2str(ret));
  
          return 1;
  
      }
  
      }
  
  /* Write the stream header, if any. */
  
  ret = avformat_write_header(oc, NULL);
  
  if (ret < 0) {
  
      fprintf(stderr, "Error occurred when opening output file: %s\n", av_err2str(ret));
  
      return 1;
  
  }
  
  
  
  // Setup x264 params
  
  x264_param_t param;
  
  x264_param_default_preset(&param, "veryfast", "zerolatency");
  
  param.i_threads = 1;
  
  param.i_width = video_st->codec->width;
  
  param.i_height = video_st->codec->height;
  
  param.i_fps_num = STREAM_FRAME_RATE; // 30 fps, same as video
  
  param.i_fps_den = 1;
  
  // Intra refres:
  
  param.i_keyint_max = STREAM_FRAME_RATE;
  
  param.b_intra_refresh = 1;
  
  // Rate control:
  
  param.rc.i_rc_method = X264_RC_CRF;
  
  param.rc.f_rf_constant = 25;
  
  param.rc.f_rf_constant_max = 35;
  
  // For streaming:
  
  param.b_repeat_headers = 1;
  
  param.b_annexb = 1;
  
  x264_param_apply_profile(&param, "baseline");
  
  
  
  x264_t* encoder = x264_encoder_open(&param);
  
  x264_picture_t pic_in, pic_out;
  
  x264_picture_alloc(&pic_in, X264_CSP_I420, video_st->codec->width, video_st->codec->height);
  
  
  
  x264_nal_t* nals;
  
  int i_nals;
  
  
  
  // The loop:
  
  // 1. Read frames
  
  // 2. Decode the frame
  
  // 3. Attempt to re-encode using x264
  
  // 4. Write the x264 encoded frame using av_interleaved_write_frame
  
  while (av_read_frame(pFormatCtx, &packet) >= 0) {
  
      // Is this a packet from the video stream?
  
      if (packet.stream_index == videoStream) {
  
          // Decode video frame
  
          avcodec_decode_video2(pCodecCtx, pFrame, &frameFinished, &packet);
  
  
  
          // Did we get a video frame?
  
          if (frameFinished) {
  
              sws_scale(img_convert_ctx, pFrame->data, pFrame->linesize, 0, pCodecCtx->height, pic_in.img.plane, pic_in.img.i_stride);
  
              int frame_size = x264_encoder_encode(encoder, &nals, &i_nals, &pic_in, &pic_out);
  
  
  
              if (frame_size >= 0) {
  
                  if (i_nals < 0)
  
                      printf("invalid frame size: %d\n", i_nals);
  
                  // write out NALs
  
                  for (i = 0; i < i_nals; i++) {
  
                      // initalize a packet
  
                      AVPacket p;
  
                      av_init_packet(&p);
  
                      p.data = nals[i].p_payload;
  
                      p.size = nals[i].i_payload;
  
                      p.stream_index = video_st->index;
  
                      p.flags = AV_PKT_FLAG_KEY;
  
                      p.pts = AV_NOPTS_VALUE;
  
                      p.dts = AV_NOPTS_VALUE;
  
                      ret = av_interleaved_write_frame(oc, &p);
  
                  }
  
              }
  
              printf("encoded frame #%d\n", frame_count);
  
              frame_count++;
  
          }
  
      }
  
  
  
      // Free the packet that was allocated by av_read_frame
  
      av_free_packet(&packet);
  
  }
  
  
  
  // Now we free up resources used/close codecs, and finally close our program.

  Here is the implementation for the add_stream() function :

  /* Add an output stream. */
  
  static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec, enum AVCodecID codec_id) {
  
      AVCodecContext *c;
  
      AVStream *st;
  
      int r;
  
      /* find the encoder */
  
      *codec = avcodec_find_encoder(codec_id);
  
      if (!(*codec)) {
  
          fprintf(stderr, "Could not find encoder for '%s'\n",
  
                  avcodec_get_name(codec_id));
  
          exit(1);
  
      }
  
      st = avformat_new_stream(oc, *codec);
  
      if (!st) {
  
          fprintf(stderr, "Could not allocate stream\n");
  
          exit(1);
  
      }
  
      st->id = oc->nb_streams - 1;
  
      c = st->codec;
  
      switch ((*codec)->type) {
  
      case AVMEDIA_TYPE_AUDIO:
  
          st->id = 1;
  
          c->sample_fmt = AV_SAMPLE_FMT_FLTP;
  
          c->bit_rate = 64000;
  
          c->sample_rate = 44100;
  
          c->channels = 2;
  
          break;
  
      case AVMEDIA_TYPE_VIDEO:
  
          avcodec_get_context_defaults3(c, *codec);
  
          c->codec_id = codec_id;
  
          c->bit_rate = 500*1000;
  
          //c->rc_min_rate = 500*1000;
  
          //c->rc_max_rate = 500*1000;
  
          //c->rc_buffer_size = 500*1000;
  
          /* Resolution must be a multiple of two. */
  
          c->width = 1280;
  
          c->height = 720;
  
          /* timebase: This is the fundamental unit of time (in seconds) in terms
  
           * of which frame timestamps are represented. For fixed-fps content,
  
           * timebase should be 1/framerate and timestamp increments should be
  
           * identical to 1. */
  
          c->time_base.den = STREAM_FRAME_RATE;
  
          c->time_base.num = 1;
  
          c->gop_size = 12; /* emit one intra frame every twelve frames at most */
  
          c->pix_fmt = STREAM_PIX_FMT;
  
          if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
  
              /* just for testing, we also add B frames */
  
              c->max_b_frames = 2;
  
          }
  
          if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
  
              /* Needed to avoid using macroblocks in which some coeffs overflow.
  
               * This does not happen with normal video, it just happens here as
  
               * the motion of the chroma plane does not match the luma plane. */
  
              c->mb_decision = 2;
  
          }
  
          break;
  
      default:
  
          break;
  
      }
  
      /* Some formats want stream headers to be separate. */
  
      if (oc->oformat->flags & AVFMT_GLOBALHEADER)
  
          c->flags |= CODEC_FLAG_GLOBAL_HEADER;
  
      return st;
  
  }

  After the encoding is complete, I check the output file output_file.flv. I notice it's size is very large : 101MB and it does not play. If I use ffmpeg to decode/encode the input file, then I get an output file about 83MB in size (which is about the same size as the original .mp4 file used as input). Also, the 83MB output from just using ffmpeg C api, as opposed to using x264 for the encoding step, plays just fine. Does anyone know where I am going wrong ? I have tried researching this for a few days now but with no luck :(. I feel that I am close to making it work, however, I just cannot figure out what I am doing wrong. Thank you !

• VP8 Codec SDK "Aylesbury" Release

  28 octobre 2010, par noreply@blogger.com (John Luther)

  Today we’re making available "Aylesbury," our first named release of libvpx, the VP8 codec SDK. VP8 is the video codec used in WebM. Note that the VP8 specification has not changed, only the SDK.

  What’s an Aylesbury ? It’s a breed of duck. We like ducks, so we plan to use duck-related names for each major libvpx release, in alphabetical order. Our goal is to have one named release of libvpx per calendar quarter, each with a theme.

  You can download the Aylesbury libvpx release from our Downloads page or check it out of our Git repository and build it yourself. In the coming days Aylesbury will be integrated into all of the WebM project components (DirectShow filters, QuickTime plugins, etc.). We encourage anyone using our components to upgrade to the Aylesbury releases.

  For Aylesbury the theme was faster decoder, better encoder. We used our May 19, 2010 launch release of libvpx as the benchmark. We’re very happy with the results (see graphs below) :
  

  • 20-40% (average 28%) improvement in libvpx decoder speed
  • Over 7% overall PSNR improvement (6.3% SSIM) in VP8 "best" quality encoding mode, and up to 60% improvement on very noisy, still or slow moving source video.

  

  
  

  

  
  

  

  
  

  The main improvements to the decoder are :
  

  • Single-core assembly "hot spot" optimizations, including improved vp8_sixtap_predict() and SSE2 loopfilter functions
  • Threading improvements for more efficient use of multiple processor cores
  • Improved memory handling and reduced footprint
  • Combining IDCT and reconstruction steps
  • SSSE3 usage in functions where appropriate

  On the encoder front, we concentrated on clips in the 30-45 dB range and saw the biggest gains in higher-quality source clips (greater that 38 dB), low to medium-motion clips, and clips with noisy source material. Many code contributions made this possible, but a few of the highlights were :
  

  • Adaptive width and strength alternate reference frame noise suppression filter with optional motion compensation.
  • Transform improvements (improved accuracy and reduction in round trip error)
  • Trellis-based quantized coefficient optimization
  • Two-pass rate control and quantizer changes
  • Rate distortion changes
  • Zero bin and rounding changes
  • Work on MB-level quality control and bit allocation

  We’re targeting Q1 2011 for the next named libvpx release, which we’re calling Bali. The theme for that release will be faster encoder. We are constantly working on improvements to video quality in the encoder, so after Aylesbury we won’t tie that work to specific named releases.

  WebM at Streaming Media West

  Members of the WebM project will discuss Aylesbury during a session at the Streaming Media West conference on November 3rd (session C203 : WebM Open Video Project Update). For more information, visit www.streamingmedia.com/west.

  John Luther is Product Manager of the WebM Project.