ffmpeg: time_base分析

最新推荐文章于 2024-08-21 16:32:41 发布

cfqcfqcfqcfqcfq

最新推荐文章于 2024-08-21 16:32:41 发布

阅读量2.2k

点赞数 1

分类专栏： ffmpeg

ffmpeg 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

ffmpeg存在多个时间基准(time_base)，对应不同的阶段(结构体)，每个time_base具体的值不一样，ffmpeg提供函数在各个time_base中进行切换。搞清楚各个time_base的来源，对于阅读ffmpeg的代码很重要。

1、AVStream(libavformat/avformat.h)

typedef struct AVStream {
    int index;    /**< stream index in AVFormatContext */
    /**
     * Format-specific stream ID.
     * decoding: set by libavformat
     * encoding: set by the user, replaced by libavformat if left unset
     */
    int id;
#if FF_API_LAVF_AVCTX
    /**
     * @deprecated use the codecpar struct instead
     */
    attribute_deprecated
    AVCodecContext *codec;
#endif
    void *priv_data;

#if FF_API_LAVF_FRAC
    /**
     * @deprecated this field is unused
     */
    attribute_deprecated
    struct AVFrac pts;
#endif

    /**
     * This is the fundamental unit of time (in seconds) in terms
     * of which frame timestamps are represented.
     *
     * decoding: set by libavformat
     * encoding: May be set by the caller before avformat_write_header() to
     *           provide a hint to the muxer about the desired timebase. In
     *           avformat_write_header(), the muxer will overwrite this field
     *           with the timebase that will actually be used for the timestamps
     *           written into the file (which may or may not be related to the
     *           user-provided one, depending on the format).
     */
    AVRational time_base;

    /**
     * Decoding: pts of the first frame of the stream in presentation order, in stream time base.
     * Only set this if you are absolutely 100% sure that the value you set
     * it to really is the pts of the first frame.
     * This may be undefined (AV_NOPTS_VALUE).
     * @note The ASF header does NOT contain a correct start_time the ASF
     * demuxer must NOT set this.
     */
    int64_t start_time;

    /**
     * Decoding: duration of the stream, in stream time base.
     * If a source file does not specify a duration, but does specify
     * a bitrate, this value will be estimated from bitrate and file size.
     *
     * Encoding: May be set by the caller before avformat_write_header() to
     * provide a hint to the muxer about the estimated duration.
     */
    int64_t duration; //这个值可以由文件大小和码率来估计

    int64_t nb_frames;                 ///< number of frames in this stream if known or 0

    int disposition; /**< AV_DISPOSITION_* bit field */

    enum AVDiscard discard; ///< Selects which packets can be discarded at will and do not need to be demuxed.

    /**
     * sample aspect ratio (0 if unknown)
     * - encoding: Set by user.
     * - decoding: Set by libavformat.
     */
    AVRational sample_aspect_ratio;

    AVDictionary *metadata;

    /**
     * Average framerate
     *
     * - demuxing: May be set by libavformat when creating the stream or in
     *             avformat_find_stream_info().
     * - muxing: May be set by the caller before avformat_write_header().
     */
    AVRational avg_frame_rate;

从上面的信息可以看到，AVStream->time_base单位为秒。且这个值在编码时候会在 avformat_write_header()函数中由复用器(muxer)重新估计其值。在设置AVStream->time_base为1/90000。为什么是90000？因为mpeg的pts、dts都是以90kHz来采样的，所以采样间隔为1/90000秒

2、AVCodecContext

typedef struct AVCodecContext {
    /**
     * 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
     * identically 1.
     * - encoding: MUST be set by user.
     * - decoding: Set by libavcodec.
     */
    AVRational time_base;

AVCodecContext->time_base单位同样为秒，不过精度没有AVStream->time_base高，大小为1/framerate

总结：
AVStream->time_base比AVCodecContext->time_base精度要高(数值要小)，比如AVStream->time_base为1/90000，而AVCodecContext->time_base为1/30(假设frame_rate为30)；同样的pts和dts，以AVStream->time_base为单位，数值要比以AVCodecContext->time_base为单位要大。

二、pts、dts
那各个结构下，pts和dts使用哪个time_base来表示呢？

1、AVPacket

typedef struct AVPacket {
    /**
     * Presentation timestamp in AVStream->time_base units; the time at which
     * the decompressed packet will be presented to the user.
     * Can be AV_NOPTS_VALUE if it is not stored in the file.
     * pts MUST be larger or equal to dts as presentation cannot happen before
     * decompression, unless one wants to view hex dumps. Some formats misuse
     * the terms dts and pts/cts to mean something different. Such timestamps
     * must be converted to true pts/dts before they are stored in AVPacket.
     */
    int64_t pts;
    /**
     * Decompression timestamp in AVStream->time_base units; the time at which
     * the packet is decompressed.
     * Can be AV_NOPTS_VALUE if it is not stored in the file.
     */
    int64_t dts;

AVPacket下的pts和dts以AVStream->time_base为单位(数值比较大)。这也很容易理解，根据mpeg的协议，压缩后或解压前的数据，pts和dts是90kHz时钟的采样值，时间间隔就是AVStream->time_base。

2、AVFrame

typedef struct AVFrame {
    /**
     * Presentation timestamp in time_base units (time when frame should be shown to user).
     */
    int64_t pts;

    /**
     * PTS copied from the AVPacket that was decoded to produce this frame.
     */
    int64_t pkt_pts;

    /**
     * DTS copied from the AVPacket that triggered returning this frame. (if frame threading isn't used)
     * This is also the Presentation time of this AVFrame calculated from
     * only AVPacket.dts values without pts values.
     */
    int64_t pkt_dts;

注意：
AVFrame里面的pkt_pts和pkt_dts是拷贝自AVPacket，同样以AVStream->time_base为单位；而pts是为输出(显示)准备的，以AVCodecContex->time_base为单位)。

3、InputStream

typedef struct InputStream {
    int file_index;
    AVStream *st;
    AVCodecContext *dec_ctx;
    int64_t       start;     /* time when read started */
    /* predicted dts of the next packet read for this stream or (when there are
     * several frames in a packet) of the next frame in current packet (in AV_TIME_BASE units) */
    int64_t       next_dts;
    int64_t       dts;       ///< dts of the last packet read for this stream (in AV_TIME_BASE units)

    int64_t       next_pts;  ///< synthetic pts for the next decode frame (in AV_TIME_BASE units)
    int64_t       pts;       ///< current pts of the decoded frame  (in AV_TIME_BASE units)

InputStream下的pts和dts以AV_TIME_BASE为单位(微秒)，至于为什么要转化为微妙，可能是为了避免使用浮点数

三、各个time_base之间转换

ffmpeg提供av_rescale_q函数用于time_base之间转换，av_rescale_q(a,b,c)作用相当于执行a*b/c，通过设置b,c的值，可以很方便的实现time_base之间转换。

1、InputStream(AV_TIME_BASE)到AVPacket(AVStream->time_base)

static int decode_video(InputStream *ist, AVPacket *pkt, int *got_output)
{
pkt->dts  = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base);

2、AVPacket(AVStream->time_base)到InputStream(AV_TIME_BASE)

static int process_input_packet(InputStream *ist, const AVPacket *pkt)
{

    if (pkt->dts != AV_NOPTS_VALUE) {
        ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);

四、后记：
AVFrame->pts和AVPacket->pts、AVPacket->dts的值，在解码/编码后，会经历短暂的time_base不匹配的情况：

1、解码后

static int decode_video(InputStream *ist, AVPacket *pkt, int *got_output)
{
    decoded_frame = ist->decoded_frame;
    pkt->dts  = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base); 

    update_benchmark(NULL);
    ret = avcodec_decode_video2(ist->dec_ctx,
                                decoded_frame, got_output, pkt);

    best_effort_timestamp= av_frame_get_best_effort_timestamp(decoded_frame);   
    if(best_effort_timestamp != AV_NOPTS_VALUE)
        ist->next_pts = ist->pts = av_rescale_q(decoded_frame->pts = best_effort_timestamp, ist->st->time_base, AV_TIME_BASE_Q);

解码后，decoded_frame->pts的值使用AVStream->time_base为单位，后在AVFilter里面转换成以AVCodecContext->time_base为单位。 //FIXME

2、编码后

static void do_video_out(AVFormatContext *s,
                         OutputStream *ost,
                         AVFrame *in_picture)
{
        ret = avcodec_encode_video2(enc, &pkt, in_picture, &got_packet);    
        if (got_packet) {
            if (debug_ts) {
                av_log(NULL, AV_LOG_INFO, "encoder -> type:video "
                       "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s\n",
                       av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &enc->time_base),
                       av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &enc->time_base));
            }

            if (pkt.pts == AV_NOPTS_VALUE && !(enc->codec->capabilities & CODEC_CAP_DELAY))
                pkt.pts = ost->sync_opts;

            av_packet_rescale_ts(&pkt, enc->time_base, ost->st->time_base);  

            if (debug_ts) {
                av_log(NULL, AV_LOG_INFO, "encoder -> type:video "
                    "pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s\n",
                    av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ost->st->time_base),
                    av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ost->st->time_base));
            }

            frame_size = pkt.size;
            write_frame(s, &pkt, ost);  
            /* if two pass, output log */
            if (ost->logfile && enc->stats_out) {
                fprintf(ost->logfile, "%s", enc->stats_out);
            }
        }

编码后，pkt.pts、pkt.dts使用AVCodecContext->time_base为单位，后通过调用"av_packet_rescale_ts"转换为AVStream->time_base为单位。

文章转载地址：http://www.cnitblog.com/luofuchong/archive/2014/11/28/89869.html