本文详细记录了H264视频解码过程中的跟踪分析，重点关注了循环退出条件、时间基处理及像素格式初始化等关键环节。通过实际案例展示了如何深入理解并定位解码过程中的具体问题。
视频解码为H264时的跟踪:
1. for(;;)中count执行了206次才退出
2. 第206次退出的地方:
if (st->time_base.den > 0 && av_rescale_q(codec_info_duration[st->index], st->time_base, AV_TIME_BASE_Q) >= ic->max_analyze_duration)
break;
满足了av_rescale_q(codec_info_duration[st->index], st->time_base, AV_TIME_BASE_Q) >= ic->max_analyze_duration导致退出
av_rescale_q(codec_info_duration[st->index], st->time_base, AV_TIME_BASE_Q) >= ic->max_analyze_duration还得研究?
3. 设置数据断点发现st->codec->pix_fmt设置为PIX_FMT_YUV420P的地方:
函数堆栈try_decode_frame()->avcodec_open()->avctx->codec->init()->H264.c中的decode_init()下的
avctx->pix_fmt= avctx->get_format(avctx, avctx->codec->pix_fmts);
4.当前流退出av_find_stream_info的判断不仅是has_codec_parameters:
if (!has_codec_parameters(st->codec))
break;
if( tb_unreliable(st->codec)
&& duration_count[i]<20 && st->codec->codec_type == CODEC_TYPE_VIDEO)
break;
if(st->parser && st->parser->parser->split && !st->codec->extradata)
break;
if(st->first_dts == AV_NOPTS_VALUE)
break;
int avformat_find_stream_info(AVFormatContext *ic, AVDictionary **options)
{//avformat_find_stream_info int i, count, ret = 0, j;
int64_t read_size;
AVStream *st;
AVPacket pkt1, *pkt;
int64_t old_offset = avio_tell(ic->pb);
// new streams might appear, no options for those
int orig_nb_streams = ic->nb_streams;
int flush_codecs = ic->probesize > 0;
int64_t max_analyze_duration = ic->max_analyze_duration2;
if (!max_analyze_duration)
max_analyze_duration = ic->max_analyze_duration;
av_opt_set(ic, "skip_clear", "1", AV_OPT_SEARCH_CHILDREN);
if (!max_analyze_duration) {
if (!strcmp(ic->iformat->name, "flv") && !(ic->ctx_flags & AVFMTCTX_NOHEADER)) {
max_analyze_duration = 10*AV_TIME_BASE;
} else
max_analyze_duration = 5*AV_TIME_BASE;
}
if (ic->pb)
av_log(ic, AV_LOG_DEBUG, "Before avformat_find_stream_info() pos: %"PRId64" bytes read:%"PRId64" seeks:%d\n",
avio_tell(ic->pb), ic->pb->bytes_read, ic->pb->seek_count);
for (i = 0; i < ic->nb_streams; i++) {
const AVCodec *codec;
AVDictionary *thread_opt = NULL;
st = ic->streams[i];
if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO ||
st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE) {
/* if (!st->time_base.num)
st->time_base = */
if (!st->codec->time_base.num)
st->codec->time_base = st->time_base;
}
// only for the split stuff
if (!st->parser && !(ic->flags & AVFMT_FLAG_NOPARSE)) {
st->parser = av_parser_init(st->codec->codec_id);
if (st->parser) {
if (st->need_parsing == AVSTREAM_PARSE_HEADERS) {
st->parser->flags |= PARSER_FLAG_COMPLETE_FRAMES;
} else if (st->need_parsing == AVSTREAM_PARSE_FULL_RAW) {
st->parser->flags |= PARSER_FLAG_USE_CODEC_TS;
}
} else if (st->need_parsing) {
av_log(ic, AV_LOG_VERBOSE, "parser not found for codec "
"%s, packets or times may be invalid.\n",
avcodec_get_name(st->codec->codec_id));
}
}
codec = find_decoder(ic, st, st->codec->codec_id);
/* Force thread count to 1 since the H.264 decoder will not extract
* SPS and PPS to extradata during multi-threaded decoding. */
av_dict_set(options ? &options[i] : &thread_opt, "threads", "1", 0);
/* Ensure that subtitle_header is properly set. */
if (st->codec->codec_type == AVMEDIA_TYPE_SUBTITLE
&& codec && !st->codec->codec) {
if (avcodec_open2(st->codec, codec, options ? &options[i] : &thread_opt) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in av_find_stream_info\n");
}
// Try to just open decoders, in case this is enough to get parameters.
if (!has_codec_parameters(st, NULL) && st->request_probe <= 0) {
if (codec && !st->codec->codec)
if (avcodec_open2(st->codec, codec, options ? &options[i] : &thread_opt) < 0)
av_log(ic, AV_LOG_WARNING,
"Failed to open codec in av_find_stream_info\n");
}
if (!options)
av_dict_free(&thread_opt);
}
for (i = 0; i < ic->nb_streams; i++) {
#if FF_API_R_FRAME_RATE
ic->streams[i]->info->last_dts = AV_NOPTS_VALUE;
#endif
ic->streams[i]->info->fps_first_dts = AV_NOPTS_VALUE;
ic->streams[i]->info->fps_last_dts = AV_NOPTS_VALUE;
}
count = 0;
read_size = 0;
for (;;) {
if (ff_check_interrupt(&ic->interrupt_callback)) {
ret = AVERROR_EXIT;
av_log(ic, AV_LOG_DEBUG, "interrupted\n");
break;
}
/* check if one codec still needs to be handled */
for (i = 0; i < ic->nb_streams; i++) {
int fps_analyze_framecount = 20;
st = ic->streams[i];
if (!has_codec_parameters(st, NULL))
break;
/* If the timebase is coarse (like the usual millisecond precision
* of mkv), we need to analyze more frames to reliably arrive at
* the correct fps. */
if (av_q2d(st->time_base) > 0.0005)
fps_analyze_framecount *= 2;
if (!tb_unreliable(st->codec))
fps_analyze_framecount = 0;
if (ic->fps_probe_size >= 0)
fps_analyze_framecount = ic->fps_probe_size;
if (st->disposition & AV_DISPOSITION_ATTACHED_PIC)
fps_analyze_framecount = 0;
/* variable fps and no guess at the real fps */
if (!(st->r_frame_rate.num && st->avg_frame_rate.num) &&
st->info->duration_count < fps_analyze_framecount &&
st->codec->codec_type == AVMEDIA_TYPE_VIDEO)
break;
if (st->parser && st->parser->parser->split &&
!st->codec->extradata)
break;
if (st->first_dts == AV_NOPTS_VALUE &&
!(ic->iformat->flags & AVFMT_NOTIMESTAMPS) &&
(st->codec->codec_type == AVMEDIA_TYPE_VIDEO ||
st->codec->codec_type == AVMEDIA_TYPE_AUDIO))
break;
}
if (i == ic->nb_streams) {
/* NOTE: If the format has no header, then we need to read some
* packets to get most of the streams, so we cannot stop here. */
if (!(ic->ctx_flags & AVFMTCTX_NOHEADER)) {
/* If we found the info for all the codecs, we can stop. */
ret = count;
av_log(ic, AV_LOG_DEBUG, "All info found\n");
flush_codecs = 0;
break;
}
}
/* We did not get all the codec info, but we read too much data. */
if (read_size >= ic->probesize) {
ret = count;
av_log(ic, AV_LOG_DEBUG,
"Probe buffer size limit of %d bytes reached\n", ic->probesize);
for (i = 0; i < ic->nb_streams; i++)
if (!ic->streams[i]->r_frame_rate.num &&
ic->streams[i]->info->duration_count <= 1 &&
ic->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO &&
strcmp(ic->iformat->name, "image2"))
av_log(ic, AV_LOG_WARNING,
"Stream #%d: not enough frames to estimate rate; "
"consider increasing probesize\n", i);
break;
}
/* NOTE: A new stream can be added there if no header in file
* (AVFMTCTX_NOHEADER). */
ret = read_frame_internal(ic, &pkt1);
if (ret == AVERROR(EAGAIN))
continue;
if (ret < 0) {
/* EOF or error*/
break;
}
if (ic->flags & AVFMT_FLAG_NOBUFFER)
free_packet_buffer(&ic->packet_buffer, &ic->packet_buffer_end);
{
pkt = add_to_pktbuf(&ic->packet_buffer, &pkt1,
&ic->packet_buffer_end);
if (!pkt) {
ret = AVERROR(ENOMEM);
goto find_stream_info_err;
}
if ((ret = av_dup_packet(pkt)) < 0)
goto find_stream_info_err;
}
st = ic->streams[pkt->stream_index];
if (!(st->disposition & AV_DISPOSITION_ATTACHED_PIC))
read_size += pkt->size;
if (pkt->dts != AV_NOPTS_VALUE && st->codec_info_nb_frames > 1) {
/* check for non-increasing dts */
if (st->info->fps_last_dts != AV_NOPTS_VALUE &&
st->info->fps_last_dts >= pkt->dts) {
av_log(ic, AV_LOG_DEBUG,
"Non-increasing DTS in stream %d: packet %d with DTS "
"%"PRId64", packet %d with DTS %"PRId64"\n",
st->index, st->info->fps_last_dts_idx,
st->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->info->fps_first_dts =
st->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* Check for a discontinuity in dts. If the difference in dts
* is more than 1000 times the average packet duration in the
* sequence, we treat it as a discontinuity. */
if (st->info->fps_last_dts != AV_NOPTS_VALUE &&
st->info->fps_last_dts_idx > st->info->fps_first_dts_idx &&
(pkt->dts - st->info->fps_last_dts) / 1000 >
(st->info->fps_last_dts - st->info->fps_first_dts) /
(st->info->fps_last_dts_idx - st->info->fps_first_dts_idx)) {
av_log(ic, AV_LOG_WARNING,
"DTS discontinuity in stream %d: packet %d with DTS "
"%"PRId64", packet %d with DTS %"PRId64"\n",
st->index, st->info->fps_last_dts_idx,
st->info->fps_last_dts, st->codec_info_nb_frames,
pkt->dts);
st->info->fps_first_dts =
st->info->fps_last_dts = AV_NOPTS_VALUE;
}
/* update stored dts values */
if (st->info->fps_first_dts == AV_NOPTS_VALUE) {
st->info->fps_first_dts = pkt->dts;
st->info->fps_first_dts_idx = st->codec_info_nb_frames;
}
st->info->fps_last_dts = pkt->dts;
st->info->fps_last_dts_idx = st->codec_info_nb_frames;
}
if (st->codec_info_nb_frames>1) {
int64_t t = 0;
if (st->time_base.den > 0)
t = av_rescale_q(st->info->codec_info_duration, st->time_base, AV_TIME_BASE_Q);
if (st->avg_frame_rate.num > 0)
t = FFMAX(t, av_rescale_q(st->codec_info_nb_frames, av_inv_q(st->avg_frame_rate), AV_TIME_BASE_Q));
if ( t == 0
&& st->codec_info_nb_frames>30
&& st->info->fps_first_dts != AV_NOPTS_VALUE
&& st->info->fps_last_dts != AV_NOPTS_VALUE)
t = FFMAX(t, av_rescale_q(st->info->fps_last_dts - st->info->fps_first_dts, st->time_base, AV_TIME_BASE_Q));
if (t >= max_analyze_duration) {
av_log(ic, AV_LOG_VERBOSE, "max_analyze_duration %"PRId64" reached at %"PRId64" microseconds\n",
max_analyze_duration,
t);
break;
}
if (pkt->duration) {
st->info->codec_info_duration += pkt->duration;
st->info->codec_info_duration_fields += st->parser && st->need_parsing && st->codec->ticks_per_frame ==2 ? st->parser->repeat_pict + 1 : 2;
}
}
#if FF_API_R_FRAME_RATE
if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO)
ff_rfps_add_frame(ic, st, pkt->dts);
#endif
if (st->parser && st->parser->parser->split && !st->codec->extradata) {
int i = st->parser->parser->split(st->codec, pkt->data, pkt->size);
if (i > 0 && i < FF_MAX_EXTRADATA_SIZE) {
if (ff_alloc_extradata(st->codec, i))
return AVERROR(ENOMEM);
memcpy(st->codec->extradata, pkt->data,
st->codec->extradata_size);
}
}
/* If still no information, we try to open the codec and to
* decompress the frame. We try to avoid that in most cases as
* it takes longer and uses more memory. For MPEG-4, we need to
* decompress for QuickTime.
*
* If CODEC_CAP_CHANNEL_CONF is set this will force decoding of at
* least one frame of codec data, this makes sure the codec initializes
* the channel configuration and does not only trust the values from
* the container. */
try_decode_frame(ic, st, pkt,
(options && i < orig_nb_streams) ? &options[i] : NULL);
st->codec_info_nb_frames++;
count++;
}
if (flush_codecs) {
AVPacket empty_pkt = { 0 };
int err = 0;
av_init_packet(&empty_pkt);
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
/* flush the decoders */
if (st->info->found_decoder == 1) {
do {
err = try_decode_frame(ic, st, &empty_pkt,
(options && i < orig_nb_streams)
? &options[i] : NULL);
} while (err > 0 && !has_codec_parameters(st, NULL));
if (err < 0) {
av_log(ic, AV_LOG_INFO,
"decoding for stream %d failed\n", st->index);
}
}
}
}
av_opt_set(ic, "skip_clear", "0", AV_OPT_SEARCH_CHILDREN);
// close codecs which were opened in try_decode_frame()
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
avcodec_close(st->codec);
}
ff_rfps_calculate(ic);
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO) {
if (st->codec->codec_id == AV_CODEC_ID_RAWVIDEO && !st->codec->codec_tag && !st->codec->bits_per_coded_sample) {
uint32_t tag= avcodec_pix_fmt_to_codec_tag(st->codec->pix_fmt);
if (avpriv_find_pix_fmt(ff_raw_pix_fmt_tags, tag) == st->codec->pix_fmt)
st->codec->codec_tag= tag;
}
/* estimate average framerate if not set by demuxer */
if (st->info->codec_info_duration_fields &&
!st->avg_frame_rate.num &&
st->info->codec_info_duration) {
int best_fps = 0;
double best_error = 0.01;
if (st->info->codec_info_duration >= INT64_MAX / st->time_base.num / 2||
st->info->codec_info_duration_fields >= INT64_MAX / st->time_base.den ||
st->info->codec_info_duration < 0)
continue;
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
st->info->codec_info_duration_fields * (int64_t) st->time_base.den,
st->info->codec_info_duration * 2 * (int64_t) st->time_base.num, 60000);
/* Round guessed framerate to a "standard" framerate if it's
* within 1% of the original estimate. */
for (j = 0; j < MAX_STD_TIMEBASES; j++) {
AVRational std_fps = { get_std_framerate(j), 12 * 1001 };
double error = fabs(av_q2d(st->avg_frame_rate) /
av_q2d(std_fps) - 1);
if (error < best_error) {
best_error = error;
best_fps = std_fps.num;
}
}
if (best_fps)
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
best_fps, 12 * 1001, INT_MAX);
}
if (!st->r_frame_rate.num) {
if ( st->codec->time_base.den * (int64_t) st->time_base.num
<= st->codec->time_base.num * st->codec->ticks_per_frame * (int64_t) st->time_base.den) {
st->r_frame_rate.num = st->codec->time_base.den;
st->r_frame_rate.den = st->codec->time_base.num * st->codec->ticks_per_frame;
} else {
st->r_frame_rate.num = st->time_base.den;
st->r_frame_rate.den = st->time_base.num;
}
}
} else if (st->codec->codec_type == AVMEDIA_TYPE_AUDIO) {
if (!st->codec->bits_per_coded_sample)
st->codec->bits_per_coded_sample =
av_get_bits_per_sample(st->codec->codec_id);
// set stream disposition based on audio service type
switch (st->codec->audio_service_type) {
case AV_AUDIO_SERVICE_TYPE_EFFECTS:
st->disposition = AV_DISPOSITION_CLEAN_EFFECTS;
break;
case AV_AUDIO_SERVICE_TYPE_VISUALLY_IMPAIRED:
st->disposition = AV_DISPOSITION_VISUAL_IMPAIRED;
break;
case AV_AUDIO_SERVICE_TYPE_HEARING_IMPAIRED:
st->disposition = AV_DISPOSITION_HEARING_IMPAIRED;
break;
case AV_AUDIO_SERVICE_TYPE_COMMENTARY:
st->disposition = AV_DISPOSITION_COMMENT;
break;
case AV_AUDIO_SERVICE_TYPE_KARAOKE:
st->disposition = AV_DISPOSITION_KARAOKE;
break;
}
}
}
if (ic->probesize)
estimate_timings(ic, old_offset);
if (ret >= 0 && ic->nb_streams)
/* We could not have all the codec parameters before EOF. */
ret = -1;
for (i = 0; i < ic->nb_streams; i++) {
const char *errmsg;
st = ic->streams[i];
if (!has_codec_parameters(st, &errmsg)) {
char buf[256];
avcodec_string(buf, sizeof(buf), st->codec, 0);
av_log(ic, AV_LOG_WARNING,
"Could not find codec parameters for stream %d (%s): %s\n"
"Consider increasing the value for the 'analyzeduration' and 'probesize' options\n",
i, buf, errmsg);
} else {
ret = 0;
}
}
compute_chapters_end(ic);
find_stream_info_err:
for (i = 0; i < ic->nb_streams; i++) {
st = ic->streams[i];
if (ic->streams[i]->codec->codec_type != AVMEDIA_TYPE_AUDIO)
ic->streams[i]->codec->thread_count = 0;
if (st->info)
av_freep(&st->info->duration_error);
av_freep(&ic->streams[i]->info);
}
if (ic->pb)
av_log(ic, AV_LOG_DEBUG, "After avformat_find_stream_info() pos: %"PRId64" bytes read:%"PRId64" seeks:%d frames:%d\n",
avio_tell(ic->pb), ic->pb->bytes_read, ic->pb->seek_count, count);
return ret;
}
扫一扫
1802
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
