c - 使用 libav* 将 H.264 转码为 VP8 的帧速率不正确

Question

到目前为止，在使用 libav* 库将 H.264 转码为 VP8 时，我未能获得正确的输出帧速率。我使用 FFmpeg 源代码中的 transcoding.c 示例的修改创建了 Sintel.2010.720p.mkv 的功能编码作为 WebM (VP8/Vorbis)。不幸的是，生成的文件是 48 fps，与原始文件的 24 fps 和我试图模仿的 ffmpeg 命令的输出不同。

我注意到 ffprobe 为该视频和其他 H.264 视频生成的 tbc 是 fps 的两倍，而 ffmpeg 命令生成的结果 VP8 流的 tbc 是默认值 1000。stock transcoding.c 示例复制时基解码器到编码器 AVCodecContext 的 1/48。通过 gdb 运行 ffmpeg 命令，看起来 AVCodecContext 的时基设置为 1/24，但单独进行更改只会导致生成的视频以 24 fps 的速度减慢到持续时间的两倍。

我可以创建一个可用的视频，但帧速率加倍。当输出帧速率为正确的 24 fps 时，视频很流畅但速度减半。

这是我对示例的修改。

 /*
  * Copyright (c) 2010 Nicolas George
  * Copyright (c) 2011 Stefano Sabatini
  * Copyright (c) 2014 Andrey Utkin
  *
  * 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 demuxing, decoding, filtering, encoding and muxing
  * @example doc/examples/transcoding.c
  */

 #include <libavcodec/avcodec.h>
 #include <libavformat/avformat.h>
 #include <libavfilter/avfiltergraph.h>
 #include <libavfilter/avcodec.h>
 #include <libavfilter/buffersink.h>
 #include <libavfilter/buffersrc.h>
 #include <libavutil/opt.h>
 #include <libavutil/pixdesc.h>

 #define STATS_LOG "stats.log"

 static AVFormatContext *ifmt_ctx;
 static AVFormatContext *ofmt_ctx;
 typedef struct FilteringContext {
   AVFilterContext *buffersink_ctx;
   AVFilterContext *buffersrc_ctx;
   AVFilterGraph *filter_graph;
 } FilteringContext;
 static FilteringContext *filter_ctx;

 static int open_input_file(const char *filename) {
   int ret;
   unsigned int i;

   ifmt_ctx = NULL;
   if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
 av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
 return ret;
   }

   if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
 av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
 return ret;
   }

   for (i = 0; i < ifmt_ctx->nb_streams; i++) {
 AVStream *stream;
 AVCodecContext *codec_ctx;
 stream = ifmt_ctx->streams[i];
 codec_ctx = stream->codec;
 /* Reencode video & audio and remux subtitles etc. */
 if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
     || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
   /* Open decoder */
   ret = avcodec_open2(codec_ctx,
               avcodec_find_decoder(codec_ctx->codec_id), NULL);
   if (ret < 0) {
     av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
     return ret;
   }
 }
   }

   av_dump_format(ifmt_ctx, 0, filename, 0);
   return 0;
 }

 static int init_output_context(char* filename) {
   int ret;
   ofmt_ctx = NULL;

   avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
   if (!ofmt_ctx) {
 av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
 return AVERROR_UNKNOWN;
   }

   return 0;
 }

 static int init_webm_encoders(int audioBitRate, int crf, int videoMaxBitRate, int threads,
               char* quality, int speed, int pass, char* stats) {
   AVStream *out_stream;
   AVStream *in_stream;
   AVCodecContext *dec_ctx, *enc_ctx;
   AVCodec *encoder;
   int ret;
   unsigned int i;

   for (i = 0; i < ifmt_ctx->nb_streams; i++) {
 in_stream = ifmt_ctx->streams[i];
 dec_ctx = in_stream->codec;
 if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {

   AVDictionary *opts = NULL;
   if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
     encoder = avcodec_find_encoder(AV_CODEC_ID_VP8);
     out_stream = avformat_new_stream(ofmt_ctx, encoder);
     if (!out_stream) {
       av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
       return AVERROR_UNKNOWN;
     }

     enc_ctx = out_stream->codec;
     enc_ctx->height = dec_ctx->height;
     enc_ctx->width = dec_ctx->width;
     enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
     /* take first format from list of supported formats */
     enc_ctx->pix_fmt = encoder->pix_fmts[0];
     /* video time_base can be set to whatever is handy and supported by encoder */
     enc_ctx->time_base = dec_ctx->time_base;
     /* enc_ctx->time_base.num = 1; */
     /* enc_ctx->time_base.den = 24; */

     enc_ctx->bit_rate = videoMaxBitRate;
     enc_ctx->thread_count = threads;
     switch (pass) {
     case 1:
       enc_ctx->flags |= CODEC_FLAG_PASS1;
       break;
     case 2:
       enc_ctx->flags |= CODEC_FLAG_PASS2;
       if (stats) {
     enc_ctx->stats_in = stats;
       }
       break;
     }

     char crfString[3];
     snprintf(crfString, 3, "%d", crf);
     av_dict_set(&opts, "crf", crfString, 0);
     av_dict_set(&opts, "quality", quality, 0);
     char speedString[3];
     snprintf(speedString, 3, "%d", speed);
     av_dict_set(&opts, "speed", speedString, 0);
   } else {
     encoder = avcodec_find_encoder(AV_CODEC_ID_VORBIS);
     out_stream = avformat_new_stream(ofmt_ctx, encoder);
     if (!out_stream) {
       av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
       return AVERROR_UNKNOWN;
     }

     /* in_stream = ifmt_ctx->streams[i]; */
     /* dec_ctx = in_stream->codec; */
     enc_ctx = out_stream->codec;
     /* encoder = out_stream->codec->codec; */

     enc_ctx->sample_rate = dec_ctx->sample_rate;
     enc_ctx->channel_layout = dec_ctx->channel_layout;
     enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
     /* take first format from list of supported formats */
     enc_ctx->sample_fmt = encoder->sample_fmts[0];
     enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate};
     enc_ctx->bit_rate = audioBitRate;
   }

   /* Open codec with the set options */
   ret = avcodec_open2(enc_ctx, encoder, &opts);
   if (ret < 0) {
     av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
     return ret;
   }
   int unused = av_dict_count(opts);
   if (unused > 0) {
     av_log(NULL, AV_LOG_WARNING, "%d unused options\n", unused);
   }
   /* } else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) { */
 } else {
   av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
   return AVERROR_INVALIDDATA;
 } /* else { */
   /*   /\* if this stream must be remuxed *\/ */
   /*   ret = avcodec_copy_context(ofmt_ctx->streams[i]->codec, */
   /*                ifmt_ctx->streams[i]->codec); */
   /*   if (ret < 0) { */
   /*   av_log(NULL, AV_LOG_ERROR, "Copying stream context failed\n"); */
   /*   return ret; */
   /*   } */
   /* } */

 if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
   enc_ctx->flags |= CODEC_FLAG_GLOBAL_HEADER;
   }

   return 0;
 }

 static int open_output_file(const char *filename) {
   int ret;

   av_dump_format(ofmt_ctx, 0, filename, 1);

   if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
 ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
   return ret;
 }
   }

   /* init muxer, write output file header */
   ret = avformat_write_header(ofmt_ctx, NULL);
   if (ret < 0) {
 av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
 return ret;
   }

   return 0;
 }

 static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
            AVCodecContext *enc_ctx, const char *filter_spec) {
   char args[512];
   int ret = 0;
   AVFilter *buffersrc = NULL;
   AVFilter *buffersink = NULL;
   AVFilterContext *buffersrc_ctx = NULL;
   AVFilterContext *buffersink_ctx = NULL;
   AVFilterInOut *outputs = avfilter_inout_alloc();
   AVFilterInOut *inputs  = avfilter_inout_alloc();
   AVFilterGraph *filter_graph = avfilter_graph_alloc();

   if (!outputs || !inputs || !filter_graph) {
 ret = AVERROR(ENOMEM);
 goto end;
   }

   if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
 buffersrc = avfilter_get_by_name("buffer");
 buffersink = avfilter_get_by_name("buffersink");
 if (!buffersrc || !buffersink) {
   av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
   ret = AVERROR_UNKNOWN;
   goto end;
 }

 snprintf(args, sizeof(args),
      "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
      dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
      dec_ctx->time_base.num, dec_ctx->time_base.den,
      dec_ctx->sample_aspect_ratio.num,
      dec_ctx->sample_aspect_ratio.den);

 ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
                    args, NULL, filter_graph);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
   goto end;
 }

 ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
                    NULL, NULL, filter_graph);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
   goto end;
 }

 ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
              (uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
              AV_OPT_SEARCH_CHILDREN);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
   goto end;
 }
   } else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
 buffersrc = avfilter_get_by_name("abuffer");
 buffersink = avfilter_get_by_name("abuffersink");
 if (!buffersrc || !buffersink) {
   av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
   ret = AVERROR_UNKNOWN;
   goto end;
 }

 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,
      dec_ctx->time_base.num, dec_ctx->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(&buffersrc_ctx, buffersrc, "in",
                    args, NULL, filter_graph);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
   goto end;
 }

 ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
                    NULL, NULL, filter_graph);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
   goto end;
 }

 ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
              (uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
              AV_OPT_SEARCH_CHILDREN);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
   goto end;
 }

 ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
              (uint8_t*)&enc_ctx->channel_layout,
              sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
   goto end;
 }

 ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
              (uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
              AV_OPT_SEARCH_CHILDREN);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
   goto end;
 }
   } else {
 ret = AVERROR_UNKNOWN;
 goto end;
   }

   /* Endpoints for the filter graph. */
   outputs->name       = av_strdup("in");
   outputs->filter_ctx = buffersrc_ctx;
   outputs->pad_idx    = 0;
   outputs->next       = NULL;

   inputs->name       = av_strdup("out");
   inputs->filter_ctx = buffersink_ctx;
   inputs->pad_idx    = 0;
   inputs->next       = NULL;

   if (!outputs->name || !inputs->name) {
 ret = AVERROR(ENOMEM);
 goto end;
   }

   if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
                   &inputs, &outputs, NULL)) < 0)
 goto end;

   if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
 goto end;

   /* Fill FilteringContext */
   fctx->buffersrc_ctx = buffersrc_ctx;
   fctx->buffersink_ctx = buffersink_ctx;
   fctx->filter_graph = filter_graph;

  end:
   avfilter_inout_free(&inputs);
   avfilter_inout_free(&outputs);

   return ret;
 }

 static int init_filters(enum AVCodecID audioCodec) {
   const char *filter_spec;
   unsigned int i;
   int ret;
   filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
   if (!filter_ctx)
 return AVERROR(ENOMEM);

   for (i = 0; i < ifmt_ctx->nb_streams; i++) {
 filter_ctx[i].buffersrc_ctx  = NULL;
 filter_ctx[i].buffersink_ctx = NULL;
 filter_ctx[i].filter_graph   = NULL;
 /* Skip streams that are neither audio nor video */
 if (!(ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO
       || ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO))
   continue;


 if (ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
   filter_spec = "null"; /* passthrough (dummy) filter for video */
 else
   /* TODO: make this more general */
   if (audioCodec == AV_CODEC_ID_VORBIS) {
     filter_spec = "asetnsamples=n=64";
   } else {
     /* filter_spec = "null"; /\* passthrough (dummy) filter for audio *\/ */
     filter_spec = "fps=24";
     /* filter_spec = "settb=expr=1/24"; */
   }
 ret = init_filter(&filter_ctx[i], ifmt_ctx->streams[i]->codec,
           ofmt_ctx->streams[i]->codec, filter_spec);
 if (ret)
   return ret;
   }
   return 0;
 }

 static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
   int ret;
   int got_frame_local;
   AVPacket enc_pkt;
   int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
 (ifmt_ctx->streams[stream_index]->codec->codec_type ==
  AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;

   if (!got_frame)
 got_frame = &got_frame_local;

   /* av_log(NULL, AV_LOG_INFO, "Encoding frame\n"); */
   /* encode filtered frame */
   enc_pkt.data = NULL;
   enc_pkt.size = 0;
   av_init_packet(&enc_pkt);
   ret = enc_func(ofmt_ctx->streams[stream_index]->codec, &enc_pkt,
          filt_frame, got_frame);
   av_frame_free(&filt_frame);
   if (ret < 0)
 return ret;
   if (!(*got_frame))
 return 0;

   /* prepare packet for muxing */
   enc_pkt.stream_index = stream_index;
   enc_pkt.dts = av_rescale_q_rnd(enc_pkt.dts,
                  ofmt_ctx->streams[stream_index]->codec->time_base,
                  ofmt_ctx->streams[stream_index]->time_base,
                  AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
   enc_pkt.pts = av_rescale_q_rnd(enc_pkt.pts,
                  ofmt_ctx->streams[stream_index]->codec->time_base,
                  ofmt_ctx->streams[stream_index]->time_base,
                  AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
   enc_pkt.duration = av_rescale_q(enc_pkt.duration,
                   ofmt_ctx->streams[stream_index]->codec->time_base,
                   ofmt_ctx->streams[stream_index]->time_base);

   /* av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n"); */
   /* mux encoded frame */
   ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
   return ret;
 }

 static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index) {
   int ret;
   AVFrame *filt_frame;

   /* av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n"); */
   /* push the decoded frame into the filtergraph */
   ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
                  frame, 0);
   if (ret < 0) {
 av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
 return ret;
   }

   /* pull filtered frames from the filtergraph */
   while (1) {
 filt_frame = av_frame_alloc();
 if (!filt_frame) {
   ret = AVERROR(ENOMEM);
   break;
 }
 /* av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n"); */
 ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
                   filt_frame);
 if (ret < 0) {
   /* if no more frames for output - returns AVERROR(EAGAIN)
    * if flushed and no more frames for output - returns AVERROR_EOF
    * rewrite retcode to 0 to show it as normal procedure completion
    */
   if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
     ret = 0;
   av_frame_free(&filt_frame);
   break;
 }

 filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
 ret = encode_write_frame(filt_frame, stream_index, NULL);
 if (ret < 0)
   break;
   }

   return ret;
 }

 static int flush_encoder(unsigned int stream_index) {
   int ret;
   int got_frame;

   if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities &
     CODEC_CAP_DELAY))
 return 0;

   while (1) {
 av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
 ret = encode_write_frame(NULL, stream_index, &got_frame);
 if (ret < 0)
   break;
 if (!got_frame)
   return 0;
   }
   return ret;
 }

 static int transcode() {
   int ret;
   AVPacket packet = { .data = NULL, .size = 0 };
   AVFrame *frame = NULL;
   enum AVMediaType type;
   unsigned int stream_index;
   unsigned int i;
   int got_frame;
   int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);

   /* read all packets */
   while (1) {
 if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
   break;
 stream_index = packet.stream_index;
 type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type;
 av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
    stream_index);

 if (filter_ctx[stream_index].filter_graph) {
   av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
   frame = av_frame_alloc();
   if (!frame) {
     ret = AVERROR(ENOMEM);
     break;
   }
   packet.dts = av_rescale_q_rnd(packet.dts,
                 ifmt_ctx->streams[stream_index]->time_base,
                 ifmt_ctx->streams[stream_index]->codec->time_base,
                 AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
   packet.pts = av_rescale_q_rnd(packet.pts,
                 ifmt_ctx->streams[stream_index]->time_base,
                 ifmt_ctx->streams[stream_index]->codec->time_base,
                 AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
   dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
     avcodec_decode_audio4;
   ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame,
          &got_frame, &packet);
   if (ret < 0) {
     av_frame_free(&frame);
     av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
     break;
   }

   if (got_frame) {
     frame->pts = av_frame_get_best_effort_timestamp(frame);
     ret = filter_encode_write_frame(frame, stream_index);
     av_frame_free(&frame);
     if (ret < 0)
       goto end;
   } else {
     av_frame_free(&frame);
   }
 } else {
   /* remux this frame without reencoding */
   packet.dts = av_rescale_q_rnd(packet.dts,
                 ifmt_ctx->streams[stream_index]->time_base,
                 ofmt_ctx->streams[stream_index]->time_base,
                 AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
   packet.pts = av_rescale_q_rnd(packet.pts,
                 ifmt_ctx->streams[stream_index]->time_base,
                 ofmt_ctx->streams[stream_index]->time_base,
                 AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);

   ret = av_interleaved_write_frame(ofmt_ctx, &packet);
   if (ret < 0)
     goto end;
 }
 av_free_packet(&packet);
   }

   /* flush filters and encoders */
   for (i = 0; i < ifmt_ctx->nb_streams; i++) {
 /* flush filter */
 if (!filter_ctx[i].filter_graph)
   continue;
 ret = filter_encode_write_frame(NULL, i);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
   goto end;
 }

 /* flush encoder */
 ret = flush_encoder(i);
 if (ret < 0) {
   av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
   goto end;
 }
   }

   av_write_trailer(ofmt_ctx);

   // Retrieve and store the first instance of codec statistics
   // TODO: less naive, deal with multiple instances of statistics
   for (i = 0; i < ofmt_ctx->nb_streams; i++) {
 AVCodecContext* codec = ofmt_ctx->streams[i]->codec;
 if ((codec->flags & CODEC_FLAG_PASS1) && (codec->stats_out)){
   FILE* logfile = fopen(STATS_LOG, "wb");
   fprintf(logfile, "%s", codec->stats_out);
   if (fclose(logfile) < 0) {
     av_log(NULL, AV_LOG_ERROR, "Error closing log file.\n");
   }
   break;
 }
   }

   av_log(NULL, AV_LOG_INFO, "output duration = %" PRId64 "\n", ofmt_ctx->duration);

  end:
   av_free_packet(&packet);
   av_frame_free(&frame);
   for (i = 0; i < ifmt_ctx->nb_streams; i++) {
 avcodec_close(ifmt_ctx->streams[i]->codec);
 if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && ofmt_ctx->streams[i]->codec)
   avcodec_close(ofmt_ctx->streams[i]->codec);
 if (filter_ctx && filter_ctx[i].filter_graph)
   avfilter_graph_free(&filter_ctx[i].filter_graph);
   }
   av_free(filter_ctx);
   avformat_close_input(&ifmt_ctx);
   if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
 avio_close(ofmt_ctx->pb);
   avformat_free_context(ofmt_ctx);

   if (ret < 0)
 av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));

   return ret ? 1 : 0;
 }

 int TranscodeToWebM(char* inputPath, char* outputPath, int audioBitRate, int crf, int videoMaxBitRate, int threads,
         char* quality, int speed) {
   int ret;
   unsigned int pass;
   char* stats = NULL;

   av_register_all();
   avfilter_register_all();

   for (pass = 1; pass <= 2; pass++) {
 if ((ret = open_input_file(inputPath)) < 0)
   goto end;

 if ((ret = init_output_context(outputPath)) < 0)
   goto end;

 if (pass == 2) {
   size_t stats_length;
   if (cmdutils_read_file(STATS_LOG, &stats, &stats_length) < 0) {
     av_log(NULL, AV_LOG_ERROR, "Error reading stats file.\n");
     break;
   }
 }

 if ((ret = init_webm_encoders(audioBitRate, crf, videoMaxBitRate, threads, quality, speed, pass, stats)) < 0)
   goto end;

 if ((ret = open_output_file(outputPath)) < 0)
   goto end;

 if ((ret = init_filters(AV_CODEC_ID_VORBIS)) < 0)
   goto end;

 if ((ret = transcode()) < 0)
   goto end;
   }

   if (remove(STATS_LOG) != 0) {
 av_log(NULL, AV_LOG_ERROR, "Failed to remove %s\n", STATS_LOG);
   }

  end:
   if (ret < 0) {
 av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));
 return ret;
   }

   return 0;
 }

这是我试图模仿的 ffmpeg 命令的输出。

ffmpeg version N-62301-g59a5384 Copyright (c) 2000-2014 the FFmpeg developers
  built on Apr  9 2014 09:58:44 with gcc 4.8.2 (GCC) 20140206 (prerelease)
  configuration: --prefix=/opt/ffmpeg --extra-cflags=-I/opt/x264/include --extra-ldflags=-L/opt/x264/lib --extra-libs=-ldl --enable-gpl --enable-nonfree --enable-libfdk-aac --enable-libopus --enable-libvorbis --enable-libvpx --enable-libx264
  libavutil      52. 75.100 / 52. 75.100
  libavcodec     55. 58.103 / 55. 58.103
  libavformat    55. 36.102 / 55. 36.102
  libavdevice    55. 11.100 / 55. 11.100
  libavfilter     4.  3.100 /  4.  3.100
  libswscale      2.  6.100 /  2.  6.100
  libswresample   0. 18.100 /  0. 18.100
  libpostproc    52.  3.100 / 52.  3.100
Input #0, matroska,webm, from '/mnt/scratch/test_source/Sintel.2010.720p.mkv':
  Metadata:
encoder         : libebml v1.0.0 + libmatroska v1.0.0
creation_time   : 2011-04-24 17:20:33
  Duration: 00:14:48.03, start: 0.000000, bitrate: 6071 kb/s
Chapter #0.0: start 0.000000, end 103.125000
Metadata:
  title           : Chapter 01
Chapter #0.1: start 103.125000, end 148.667000
Metadata:
  title           : Chapter 02
Chapter #0.2: start 148.667000, end 349.792000
Metadata:
  title           : Chapter 03
Chapter #0.3: start 349.792000, end 437.208000
Metadata:
  title           : Chapter 04
Chapter #0.4: start 437.208000, end 472.075000
Metadata:
  title           : Chapter 05
Chapter #0.5: start 472.075000, end 678.833000
Metadata:
  title           : Chapter 06
Chapter #0.6: start 678.833000, end 744.083000
Metadata:
  title           : Chapter 07
Chapter #0.7: start 744.083000, end 888.032000
Metadata:
  title           : Chapter 08
Stream #0:0(eng): Video: h264 (High), yuv420p(tv, bt709), 1280x544, SAR 1:1 DAR 40:17, 24 fps, 24 tbr, 1k tbn, 48 tbc
Stream #0:1(eng): Audio: ac3, 48000 Hz, 5.1(side), fltp, 640 kb/s
Metadata:
  title           : AC3 5.1 @ 640 Kbps
Stream #0:2(ger): Subtitle: subrip
Stream #0:3(eng): Subtitle: subrip
Stream #0:4(spa): Subtitle: subrip
Stream #0:5(fre): Subtitle: subrip
Stream #0:6(ita): Subtitle: subrip
Stream #0:7(dut): Subtitle: subrip
Stream #0:8(pol): Subtitle: subrip
Stream #0:9(por): Subtitle: subrip
Stream #0:10(rus): Subtitle: subrip
Stream #0:11(vie): Subtitle: subrip
[libvpx @ 0x24b74c0] v1.3.0
Output #0, webm, to '/mnt/scratch/test_out/Sintel.2010.720p.script.webm':
  Metadata:
encoder         : Lavf55.36.102
Chapter #0.0: start 0.000000, end 103.125000
Metadata:
  title           : Chapter 01
Chapter #0.1: start 103.125000, end 148.667000
Metadata:
  title           : Chapter 02
Chapter #0.2: start 148.667000, end 349.792000
Metadata:
  title           : Chapter 03
Chapter #0.3: start 349.792000, end 437.208000
Metadata:
  title           : Chapter 04
Chapter #0.4: start 437.208000, end 472.075000
Metadata:
  title           : Chapter 05
Chapter #0.5: start 472.075000, end 678.833000
Metadata:
  title           : Chapter 06
Chapter #0.6: start 678.833000, end 744.083000
Metadata:
  title           : Chapter 07
Chapter #0.7: start 744.083000, end 888.032000
Metadata:
  title           : Chapter 08
Stream #0:0(eng): Video: vp8 (libvpx), yuv420p, 1280x544 [SAR 1:1 DAR 40:17], q=-1--1, pass 2, 60000 kb/s, 1k tbn, 24 tbc
Stream #0:1(eng): Audio: vorbis (libvorbis), 48000 Hz, 5.1(side), fltp, 384 kb/s
Metadata:
  title           : AC3 5.1 @ 640 Kbps
Stream mapping:
  Stream #0:0 -> #0:0 (h264 -> libvpx)
  Stream #0:1 -> #0:1 (ac3 -> libvorbis)
Press [q] to stop, [?] for help
frame=21312 fps= 11 q=0.0 Lsize=  567191kB time=00:14:48.01 bitrate=5232.4kbits/s    
video:537377kB audio:29266kB subtitle:0kB other streams:0kB global headers:7kB muxing overhead: 0.096885%

Answer 1

看来您的问题出在您的转码函数中，您需要在输入格式 PTS/DTS 和输出格式 PTS/DTS 之间进行 av_rescale_q。

不要相信将任意数字放入其中，通过从上下文和编解码器中获取它来继续执行您正在做的事情。

我写了一个bit about PTS/DTS here它可能对你有用。在您的情况下，尽管您已经有一个“正确的”PTS/DTS，但您需要将其转换为输出 PTS/DTS。