[FFMPEG开发]FFMPEG中的pts与音视频同步的关系以及编解码过程中的注意事项

最近几个月在win上做音视频开发,基本上都是围绕着ffmpeg库进行的工作。其中一个问题就是音画不同步,由于本人是新手一枚,也不太清楚是什么原因,翻看了雷神的多篇博客也没有详细的解释。看着前辈留下的代码,只好一脸懵逼去看ffmpeg的源码,然后分析bug以及怎么修复。最后看到了一个东西pts,关于pts这篇文章介绍的十分仔细ffmpeg的pts概念。但是对于初学的我来说还是不太清楚怎么去跟开发对应。所以我就整理了下,在做音视频模块中什么地方会比较频繁遇到pts。废话就不说了,直接进入开发者模式假设我们需要对一个视频进行处理,然后产生一个输出。

input_video->decode->encode->output_video。通常都需要进行一次这样的处理。在ffmpeg中这几个过程密切相关的有容器有AVFormatContext、AVStream、AVCodecContext。这是跟音视频同步相关的主角。
另外接触ffmpeg建议从这几个简单的官方demo入手,毕竟简单做起是最好ffmpeg官方的demo这里就通过transcoding.c进行一个介绍吧(代码比较长,如果已经比较有基础,直接跳到图文那部分)

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

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;

typedef struct StreamContext {
    AVCodecContext *dec_ctx;
    AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_ctx;
//输入流打开,给ifmt_ctx赋值,并且打开解码器
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;
    }

    stream_ctx = av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
    if (!stream_ctx)
        return AVERROR(ENOMEM);

    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        AVStream *stream = ifmt_ctx->streams[i];
        AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
        AVCodecContext *codec_ctx;
        if (!dec) {
            av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
            return AVERROR_DECODER_NOT_FOUND;
        }
        codec_ctx = avcodec_alloc_context3(dec);
        if (!codec_ctx) {
            av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
            return AVERROR(ENOMEM);
        }
        ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
        if (ret < 0) {
            av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
                   "for stream #%u\n", i);
            return ret;
        }
        /* Reencode video & audio and remux subtitles etc. */
        if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
                || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
            if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
                codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
            /* Open decoder */
            ret = avcodec_open2(codec_ctx, dec, NULL);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
                return ret;
            }
        }
        stream_ctx[i].dec_ctx = codec_ctx;
    }

    av_dump_format(ifmt_ctx, 0, filename, 0);
    return 0;
}
//打开输出管理器,并通过解码器给编码器进行设置
static int open_output_file(const char *filename)
{
    AVStream *out_stream;
    AVStream *in_stream;
    AVCodecContext *dec_ctx, *enc_ctx;
    AVCodec *encoder;
    int ret;
    unsigned int i;

    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;
    }


    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        out_stream = avformat_new_stream(ofmt_ctx, NULL);
        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 = stream_ctx[i].dec_ctx;

        if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
                || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
            /* in this example, we choose transcoding to same codec */
            encoder = avcodec_find_encoder(dec_ctx->codec_id);
            if (!encoder) {
                av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
                return AVERROR_INVALIDDATA;
            }
            enc_ctx = avcodec_alloc_context3(encoder);
            if (!enc_ctx) {
                av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
                return AVERROR(ENOMEM);
            }

            /* In this example, we transcode to same properties (picture size,
             * sample rate etc.). These properties can be changed for output
             * streams easily using filters */
            if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
                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 */
                if (encoder->pix_fmts)
                    enc_ctx->pix_fmt = encoder->pix_fmts[0];
                else
                    enc_ctx->pix_fmt = dec_ctx->pix_fmt;
                /* video time_base can be set to whatever is handy and supported by encoder */
                enc_ctx->time_base = av_inv_q(dec_ctx->framerate);
            } else {
                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};
            }

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

            /* Third parameter can be used to pass settings to encoder */
            ret = avcodec_open2(enc_ctx, encoder, NULL);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
                return ret;
            }
            ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
                return ret;
            }

            out_stream->time_base = enc_ctx->time_base;
            stream_ctx[i].enc_ctx = enc_ctx;
        } else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
            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_parameters_copy(out_stream->codecpar, in_stream->codecpar);
            if (ret < 0) {
                av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
                return ret;
            }
            out_stream->time_base = in_stream->time_base;
        }

    }
    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;
}
//初始化过滤器,其实不要也行,因为过滤器涉及操作不多
static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
        AVCodecContext *enc_ctx, const char *filter_spec)
{
    char args[512];
    int ret = 0;
    const AVFilter *buffersrc = NULL;
    const 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(void)
{
    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;
        if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
                || ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
            continue;


        if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
            filter_spec = "null"; /* passthrough (dummy) filter for video */
        else
            filter_spec = "anull"; /* passthrough (dummy) filter for audio */
        ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
                stream_ctx[i].enc_ctx, filter_spec);
        if (ret)
            return ret;
    }
    return 0;
}
//编码并输出
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]->codecpar->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(stream_ctx[stream_index].enc_ctx, &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;
    av_packet_rescale_ts(&enc_pkt,
                         stream_ctx[stream_index].enc_ctx->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;
}
//发送到过滤器进行再编码
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;
}
//刷出编码器剩余数据
static int flush_encoder(unsigned int stream_index)
{
    int ret;
    int got_frame;

    if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
                AV_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;
}

int main(int argc, char **argv)
{
    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 *);

    if (argc != 3) {
        av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]);
        return 1;
    }

    if ((ret = open_input_file(argv[1])) < 0)
        goto end;
    if ((ret = open_output_file(argv[2])) < 0)
        goto end;
    if ((ret = init_filters()) < 0)
        goto end;

    /* 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]->codecpar->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;
            }
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 stream_ctx[stream_index].dec_ctx->time_base);
            dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
                avcodec_decode_audio4;
            ret = dec_func(stream_ctx[stream_index].dec_ctx, 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 = frame->best_effort_timestamp;
                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 */
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 ofmt_ctx->streams[stream_index]->time_base);

            ret = av_interleaved_write_frame(ofmt_ctx, &packet);
            if (ret < 0)
                goto end;
        }
        av_packet_unref(&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);
end:
    av_packet_unref(&packet);
    av_frame_free(&frame);
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        avcodec_free_context(&stream_ctx[i].dec_ctx);
        if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
            avcodec_free_context(&stream_ctx[i].enc_ctx);
        if (filter_ctx && filter_ctx[i].filter_graph)
            avfilter_graph_free(&filter_ctx[i].filter_graph);
    }
    av_free(filter_ctx);
    av_free(stream_ctx);
    avformat_close_input(&ifmt_ctx);
    if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
        avio_closep(&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;
}

首先是AVFormatContext这里有两个相关的ifmt_ctx,ofmt_ctx,我们姑且就当作文件组织管理器吧(个人感觉这样比较合适,因为使用到这个内容多数是直接关联文件的)然后是每个fmt_ctx都有一个或者多个AVStream,这个是音频/视频流的管理结构,最后是每个stream里都有一个AVCodecContext这个是编解码器的管理器。通常在ffmpeg中能解码的都能编码。所以这个既可以做为编码器使用,也能做为解码器使用(我指的是这个结构体,千万不要以为都是同格式的编码器就可以直接用编码器解码,说多了都是泪)总体结构如下:音视频文件编解码相关内容关于这些东西的初始化官方例子可以研究下,比较基础就不解说了。
然后就是我们进行编解码,无论是直播流还是文件流。我们都需要一个函数av_read_frame()从这个函数中我们会接触第一个pts在获取的AVPacket的pts会跳来跳去,忽大忽小,这很正常,因为这个文件并不止一个流。 这个packet中有一个stream_index,有了这个流索引,我们可以换算出这个包是在视频中什么位置播放

av_read_frame(ifmt_ctx, &packet)
int virtualpts=packet.pts;
int realpts=av_rescale_q(virtualpts,ifmt_ctx->streams[packet.stream_index]->time_base,{1,AV_TIME_BASE});

通过这样的换算,我们可以获知这个音频/视频包在什么时候进行播放的(该函数换算出来的是微秒)。这是第一个会遇到pts的地方。进行Decode进行音视频解码,我们可以获得第二个ptsAVFrame->pts这个其实是从packet获取的,所以本质还是由packet引导换算的方法也是跟packet的一样。然后我们在Encode的时候会用到第三个pts这个pts其实是跟frame->pts是一致的,也没什么太大问题。如果要做一些控制需要对frame->pts进行设置(转封装),接着就是第四个pts这个pts会在av_write_frame里使用到,用来将封装好的packet写到输出文件中。那么要进行音视频同步,同帧率同格式只需要进行以下操作(音频同理音频转封装需要重采样,视频跨像素格式需要重调整)。简易的封装这样封装出来的视频是音视频同步的,不会出现异常。这也是ffmpeg demo普遍的做法,但是当你想用来转格式的时候(完成重采样跟像素调整了)就会出问题,有时候转出来的视频视频会出现马赛克,音频会偶尔出现杂音(关于杂音去除的算法比较复杂下期再说,不过这也跟pts有关),这很正常。
首先说说马赛克
视频编码中有ibp帧的概念,其中只有i帧是完整数据的,其余都是根据i帧进行解码的,那么假设,在跨格式的时候,AVStream->time_base不一致了会出现什么?比如1:25转1:15,假设pts每次都加1,这时候会有10帧跟其他帧的pts重复,这时候问题就出现了,重复的帧会被做什么?不会做什么,只是你写不进去,因为重复的包肯定是不能写的,恰巧重复的包中有i帧,那完了,后续的帧肯定马赛克了。这种情况应该怎么处理。
预知编码后包所在位置,合理丢帧
有时候转格式了输入流的time_base分母可能比输出流的time_base分母大,这时候可能会出现帧覆盖,解码器解码的帧不发到编码器进行编码就可以解决了,至于预知,就是对当前编码到的pts进行记录,然后解码完成后对pts进行换算,如果重复了就不发送到编码器。如图所示改进的pts换算合理丢弃会编码重复的帧就可以解决马赛克了。然后接下来是第二个问题设置了编码器为15帧,输出的视频还是跟原视频一样是25帧
这个问题是因为stream->time_base跟videoencodectx->time_base不一致的原因,处理方法也是合理丢帧,不过我们刚刚丢帧是为了丢编码后会出问题的帧,现在丢的是不符合帧率的帧
在这里插入图片描述现在会进行合理丢帧,不过动态帧率的视频可能不行,原因比较复杂,不进行解释了。
第三个问题是跟设置的码率严重不一致(部分格式可能真的没办法控制)
这个原因是部分编码器是根据pts来进行码率控制的,而我们换算pts是最后才进行换算的,如果你需要控制码率则最好在发给编码器的时候就改pts,那么流程就变成这样
发送给编码器前先调整这样同步异常基本上就解决了。关于音频出现杂音的问题比较复杂,我下次有空再进行分解。

  • 0
    点赞
  • 14
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值