ffplay播放器精确跳转seek控制

0   问题-背景

      最近开发的一个项目，业务要求视频跳转非常精确，但是视频的帧率是12帧/s，GOP是60，也就是说两个关键帧之间的距离是5s。目前项目中使用的播放时是基于ffplay源码修改而来，外壳封装了一层Qt通信代码。麻烦的一点是ffmpeg的av_seek_frame方法只能跳转到关键帧,因此这里就会存在误差。

     举个例子：假如 我们的视频 只有在10秒和15秒上才有关键帧，这时候我们希望跳转到14秒，调用av_seek_frame后视频只能跳到10秒或者15秒，因为解码器解码视频必须要有关键帧的信息才能解码，因此av_seek_frame这样设定是合理的，所以我们seek之后还需要执行一些操作来处理这个情况。而目前我们项目中的播放器没有处理这种情况，而是找到需要跳转的时间点的前一个关键帧处开始解码播放。

1  解决方法

    在网上查了一些方法，目前下面这个链接中提供的方式比较合理，目前还没有尝试，如果尝试可以的话，再追加文字描述

   http://blog.yundiantech.com/?log=blog&id=13

2  我的项目上使用的解决方法

    本人的项目是基于ffplay源码改写而来，解决以上问题的时候参考了上面这个链接提供的知识。

     以下是我对ffplay.c文件的修改，一共有5处，修改的地方用/****accurate_seek ******/包围起来方便查找，效果是平均误差在0.5s以下。

•     VideoState结构体，添加几个字段：

    /****accurate_seek ******/
    int64_t seek_time;        // 精确的跳转点时间
    int seek_flag_audio;     // 音频seek标志位
    int seek_flag_video;     //  视频seek标志位
    int seek_flag_subtitle;  //  字幕seek标志位
    /****accurate_seek******/

• read_thread 数据读线程，记录具体的跳转时间点以及标志位置位

        if (is->seek_req) {
            int64_t seek_target = is->seek_pos;
            int64_t seek_min    = is->seek_rel > 0 ? seek_target - is->seek_rel + 2: INT64_MIN;
            int64_t seek_max    = is->seek_rel < 0 ? seek_target - is->seek_rel - 2: INT64_MAX;
// FIXME the +-2 is due to rounding being not done in the correct direction in generation
//      of the seek_pos/seek_rel variables

            ret = avformat_seek_file(is->ic, -1, seek_min, seek_target, seek_max, is->seek_flags);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR,
                       "%s: error while seeking\n", is->ic->filename);
            } else {
                if (is->audio_stream >= 0) {
                    packet_queue_flush(&is->audioq);
                    packet_queue_put(&is->audioq, &flush_pkt);
                }
                if (is->subtitle_stream >= 0) {
                    packet_queue_flush(&is->subtitleq);
                    packet_queue_put(&is->subtitleq, &flush_pkt);
                }
                if (is->video_stream >= 0) {
                    packet_queue_flush(&is->videoq);
                    packet_queue_put(&is->videoq, &flush_pkt);
                }
                if (is->seek_flags & AVSEEK_FLAG_BYTE) {
                   set_clock(&is->extclk, NAN, 0);
                } else {
                   set_clock(&is->extclk, seek_target / (double)AV_TIME_BASE, 0);
                }
            }
			
			/* accurate_seek add by liyi6*/
			is->seek_time =  is->seek_pos / 1000000.0;
			is->seek_flag_audio = 1;
			is->seek_flag_video = 1;
			is->seek_flag_subtitle = 1;
			/* accurate_seek*/
			
            is->seek_req = 0;
            is->queue_attachments_req = 1;
            is->eof = 0;
            if (is->paused)
                step_to_next_frame(is);
			private_data.received_pack_size = 0;
        }

• video_thread 视频解码线程

static int video_thread(void *arg)
{
    VideoState *is = arg;
    AVFrame *frame = av_frame_alloc();
    double pts;
    double duration;
    int ret;
    AVRational tb = is->video_st->time_base;
    AVRational frame_rate = av_guess_frame_rate(is->ic, is->video_st, NULL);

#if CONFIG_AVFILTER
    AVFilterGraph *graph = avfilter_graph_alloc();
    AVFilterContext *filt_out = NULL, *filt_in = NULL;
    int last_w = 0;
    int last_h = 0;
    enum AVPixelFormat last_format = -2;
    int last_serial = -1;
    int last_vfilter_idx = 0;
    if (!graph) {
        av_frame_free(&frame);
        return AVERROR(ENOMEM);
    }

#endif

    if (!frame) {
#if CONFIG_AVFILTER
        avfilter_graph_free(&graph);
#endif
        return AVERROR(ENOMEM);
    }

    for (;;) {
        ret = get_video_frame(is, frame);
        if (ret < 0)
            goto the_end;
        if (!ret)
            continue;

#if CONFIG_AVFILTER
        if (   last_w != frame->width
            || last_h != frame->height
            || last_format != frame->format
            || last_serial != is->viddec.pkt_serial
            || last_vfilter_idx != is->vfilter_idx) {
            av_log(NULL, AV_LOG_DEBUG,
                   "Video frame changed from size:%dx%d format:%s serial:%d to size:%dx%d format:%s serial:%d\n",
                   last_w, last_h,
                   (const char *)av_x_if_null(av_get_pix_fmt_name(last_format), "none"), last_serial,
                   frame->width, frame->height,
                   (const char *)av_x_if_null(av_get_pix_fmt_name(frame->format), "none"), is->viddec.pkt_serial);
            avfilter_graph_free(&graph);
            graph = avfilter_graph_alloc();
            if ((ret = configure_video_filters(graph, is, vfilters_list ? vfilters_list[is->vfilter_idx] : NULL, frame)) < 0) {
                SDL_Event event;
                event.type = FF_QUIT_EVENT;
                event.user.data1 = is;
                SDL_PushEvent(&event);
                goto the_end;
            }
            filt_in  = is->in_video_filter;
            filt_out = is->out_video_filter;
            last_w = frame->width;
            last_h = frame->height;
            last_format = frame->format;
            last_serial = is->viddec.pkt_serial;
            last_vfilter_idx = is->vfilter_idx;
            frame_rate = filt_out->inputs[0]->frame_rate;
        }

        ret = av_buffersrc_add_frame(filt_in, frame);
        if (ret < 0)
            goto the_end;

        while (ret >= 0) {
            is->frame_last_returned_time = av_gettime_relative() / 1000000.0;

            ret = av_buffersink_get_frame_flags(filt_out, frame, 0);
            if (ret < 0) {
                if (ret == AVERROR_EOF)
                    is->viddec.finished = is->viddec.pkt_serial;
                ret = 0;
                break;
            }

            is->frame_last_filter_delay = av_gettime_relative() / 1000000.0 - is->frame_last_returned_time;
            if (fabs(is->frame_last_filter_delay) > AV_NOSYNC_THRESHOLD / 10.0)
                is->frame_last_filter_delay = 0;
            tb = filt_out->inputs[0]->time_base;
#endif
            duration = (frame_rate.num && frame_rate.den ? av_q2d((AVRational){frame_rate.den, frame_rate.num}) : 0);
            pts = (frame->pts == AV_NOPTS_VALUE) ? NAN : frame->pts * av_q2d(tb);
            
    			/*accurate_seek*/
			if (is->seek_flag_video) {
				if (pts < is->seek_time) {
					continue;
				} else {
					is->seek_flag_video = 0;
				}	
			}
			/*accurate_seek*/
			
			ret = queue_picture(is, frame, pts, duration, av_frame_get_pkt_pos(frame), is->viddec.pkt_serial);
            av_frame_unref(frame);
#if CONFIG_AVFILTER
        }
#endif

        if (ret < 0)
            goto the_end;
    }
 the_end:
#if CONFIG_AVFILTER
    avfilter_graph_free(&graph);
#endif
    av_frame_free(&frame);
    return 0;
}

• audio_thread 音频解码线程

static int audio_thread(void *arg)
{
    VideoState *is = arg;
    AVFrame *frame = av_frame_alloc();
    Frame *af;
#if CONFIG_AVFILTER
    int last_serial = -1;
    int64_t dec_channel_layout;
    int reconfigure;
#endif
    int got_frame = 0;
    AVRational tb;
    int ret = 0;

    if (!frame)
        return AVERROR(ENOMEM);

    do {
        if ((got_frame = decoder_decode_frame(&is->auddec, frame, NULL)) < 0)
            goto the_end;

        if (got_frame) {
                tb = (AVRational){1, frame->sample_rate};

#if CONFIG_AVFILTER
                dec_channel_layout = get_valid_channel_layout(frame->channel_layout, av_frame_get_channels(frame));

                reconfigure =
                    cmp_audio_fmts(is->audio_filter_src.fmt, is->audio_filter_src.channels,
                                   frame->format, av_frame_get_channels(frame))    ||
                    is->audio_filter_src.channel_layout != dec_channel_layout ||
                    is->audio_filter_src.freq           != frame->sample_rate ||
                    is->auddec.pkt_serial               != last_serial;

                if (reconfigure) {
                    char buf1[1024], buf2[1024];
                    av_get_channel_layout_string(buf1, sizeof(buf1), -1, is->audio_filter_src.channel_layout);
                    av_get_channel_layout_string(buf2, sizeof(buf2), -1, dec_channel_layout);
                    av_log(NULL, AV_LOG_DEBUG,
                           "Audio frame changed from rate:%d ch:%d fmt:%s layout:%s serial:%d to rate:%d ch:%d fmt:%s layout:%s serial:%d\n",
                           is->audio_filter_src.freq, is->audio_filter_src.channels, av_get_sample_fmt_name(is->audio_filter_src.fmt), buf1, last_serial,
                           frame->sample_rate, av_frame_get_channels(frame), av_get_sample_fmt_name(frame->format), buf2, is->auddec.pkt_serial);

                    is->audio_filter_src.fmt            = frame->format;
                    is->audio_filter_src.channels       = av_frame_get_channels(frame);
                    is->audio_filter_src.channel_layout = dec_channel_layout;
                    is->audio_filter_src.freq           = frame->sample_rate;
                    last_serial                         = is->auddec.pkt_serial;

                    if ((ret = configure_audio_filters(is, afilters, 1)) < 0)
                        goto the_end;
                }

            if ((ret = av_buffersrc_add_frame(is->in_audio_filter, frame)) < 0)
                goto the_end;

            while ((ret = av_buffersink_get_frame_flags(is->out_audio_filter, frame, 0)) >= 0) {
                tb = is->out_audio_filter->inputs[0]->time_base;
#endif
                if (!(af = frame_queue_peek_writable(&is->sampq)))
                    goto the_end;

                af->pts = (frame->pts == AV_NOPTS_VALUE) ? NAN : frame->pts * av_q2d(tb);
                af->pos = av_frame_get_pkt_pos(frame);
                af->serial = is->auddec.pkt_serial;
                af->duration = av_q2d((AVRational){frame->nb_samples, frame->sample_rate});

				/*accurate_seek add by liyi6*/
				if (is->seek_flag_audio) {
					if (af->pts < is->seek_time) {
						continue;
					} else {
						is->seek_flag_audio = 0;
					}	
				}
				/*accurate_seek*/
				
                av_frame_move_ref(af->frame, frame);
                frame_queue_push(&is->sampq);

#if CONFIG_AVFILTER
                if (is->audioq.serial != is->auddec.pkt_serial)
                    break;
            }
            if (ret == AVERROR_EOF)
                is->auddec.finished = is->auddec.pkt_serial;
#endif
        }
    } while (ret >= 0 || ret == AVERROR(EAGAIN) || ret == AVERROR_EOF);
 the_end:
#if CONFIG_AVFILTER
    avfilter_graph_free(&is->agraph);
#endif
    av_frame_free(&frame);
    return ret;
}

• subtitle_thread 字幕解码线程

static int subtitle_thread(void *arg)
{
    VideoState *is = arg;
    Frame *sp;
    int got_subtitle;
    double pts;

    for (;;) {
        if (!(sp = frame_queue_peek_writable(&is->subpq)))
            return 0;

        if ((got_subtitle = decoder_decode_frame(&is->subdec, NULL, &sp->sub)) < 0)
            break;

        pts = 0;

        if (got_subtitle && sp->sub.format == 0) {
            if (sp->sub.pts != AV_NOPTS_VALUE)
                pts = sp->sub.pts / (double)AV_TIME_BASE;
            sp->pts = pts;
            sp->serial = is->subdec.pkt_serial;
            sp->width = is->subdec.avctx->width;
            sp->height = is->subdec.avctx->height;
            sp->uploaded = 0;
			
			/* accurate_seek add by liyi6*/
			if (is->seek_flag_subtitle) {
				if (sp->pts < is->seek_time) {
					continue;
				} else {
					is->seek_flag_subtitle = 0;
				}	
			}
			/* accurate_seek */

            /* now we can update the picture count */
            frame_queue_push(&is->subpq);
        } else if (got_subtitle) {
            avsubtitle_free(&sp->sub);
        }
    }
    return 0;
}