c - 如何使用 ffmpeg API 将带有 h.264 的原始 PCM 复用到 MP4？

Question

我正在使用 FFmpeg API 进行实时多媒体传输。由于需要单独传输音频/视频数据，所以我需要在接收端将它们混合成一个mp4文件。

现在我可以将 PCM 和 H.264 mux 成 mp4 文件，但是播放时，只有图像出来，音频不能。PCM原始数据属性:8000采样率，单声道，16位。

有人可以给我一些建议吗？非常感谢。

我尝试将 WAV header 添加到 in_pcm_file，并确保 pcm 文件可以被 Windows Media Player 播放。但仍然无法处理 MP4 文件。

int muxerData(char *in_h264_file,
              char *in_pcm_file,
              char *out_mp4_file,
              char *angle)
{
    AVFormatContext *ifmt_ctx_v = NULL;
    AVFormatContext *ifmt_ctx_a = NULL;
    AVFormatContext *ofmt_ctx = NULL;
    AVFormatContext *ifmt_ctx = NULL;

    AVOutputFormat *ofmt = NULL;

    AVPacket pkt = {0};
    AVCodec *dec = NULL;

    AVStream *in_stream = NULL;
    AVStream *out_stream = NULL;

    int ret = 0;
    unsigned int i = 0;
    int videoindex_v = -1;
    int videoindex_out = -1;
    int audioindex_a = -1;
    int audioindex_out = -1;
    int frame_index = 0;
    int64_t cur_pts_v = 0;
    int64_t cur_pts_a = 0;

    int stream_index = 0;

    int compare_tag = -1;

    char log_buf[1024] = {0};

    avcodec_register_all();
    av_register_all();

    //Input
    if ((ret = avformat_open_input(&ifmt_ctx_a, in_pcm_file, NULL, NULL)) < 0)
    {
        av_strerror(ret, log_buf, 1024);
        printf("Couldn't open file %s: %d(%s)", in_pcm_file, ret, log_buf);
        goto end;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx_a, 0)) < 0)
    {
        printf("Failed to retrieve input stream information");
        //if (acc_length>0)
        //  goto end;
    }

    if ((ret = avformat_open_input(&ifmt_ctx_v, in_h264_file, NULL, NULL)) < 0)
    {
        printf("Could not open input file:%d\n", ret);
        goto end;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx_v, 0)) < 0)
    {
        printf("Failed to retrieve input stream information");
        goto end;
    }

    av_dump_format(ifmt_ctx_v, 0, in_h264_file, 0);
    av_dump_format(ifmt_ctx_a, 0, in_pcm_file, 0);

    //Output
    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_mp4_file);
    if (!ofmt_ctx)
    {
        printf("Could not create output context\n");
        ret = AVERROR_UNKNOWN;
        goto end;
    }

    ofmt = ofmt_ctx->oformat;

    for (i = 0; i < ifmt_ctx_v->nb_streams; i++)
    {
        //Create output AVStream according to input AVStream
        if (ifmt_ctx_v->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
        {
            in_stream = ifmt_ctx_v->streams[i];
            out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);
            videoindex_v = i;

            if (!out_stream)
            {
                printf("Failed allocating output stream\n");
                ret = AVERROR_UNKNOWN;
                goto end;
            }

            videoindex_out = out_stream->index;

            //Copy the settings of AVCodecContext
            ret = av_dict_set(&out_stream->metadata, "rotate", angle, 0);

            if (avcodec_copy_context(out_stream->codec, in_stream->codec) < 0)
            {
                printf("Failed to copy context from input to output stream codec context\n");
                goto end;
            }

            out_stream->codec->codec_tag = 0;
            if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
            {
                out_stream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
            }

            break;
        }
    }


    for (i = 0; i < ifmt_ctx_a->nb_streams; i++)
    {
        printf("===========acc=====from======:%d\n", ifmt_ctx_a->nb_streams);

        //Create output AVStream according to input AVStream
        if (ifmt_ctx_a->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
        {
            in_stream = ifmt_ctx_a->streams[i];
            out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);
            audioindex_a = i;

            if (!out_stream)
            {
                printf("Failed allocating output stream\n");
                ret = AVERROR_UNKNOWN;
                goto end;
            }

            audioindex_out = out_stream->index;

            //Copy the settings of AVCodecContext
            if (avcodec_copy_context(out_stream->codec, in_stream->codec) < 0)
            {
                printf("Failed to copy context from input to output stream codec context\n");
                goto end;
            }

            if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
            {
                out_stream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
            }

            break;
        }
    }


    printf("==========Output Information==========\n");
    av_dump_format(ofmt_ctx, 0, out_mp4_file, 1);
    printf("======================================\n");

    //Open output file
    if (!(ofmt->flags & AVFMT_NOFILE))
    {
        if (avio_open(&ofmt_ctx->pb, out_mp4_file, AVIO_FLAG_WRITE) < 0)
        {
            printf("Could not open output file '%s'", out_mp4_file);
            goto end;
        }
    }

    //Write file header
    int header_ret = avformat_write_header(ofmt_ctx, NULL);
    if (header_ret < 0)
    {
        av_strerror(header_ret, log_buf, 1024);
        printf("Error occurred when opening output file:%d (%s)\n", header_ret, log_buf);
        goto end;
    }

    //FIX
    //AVBitStreamFilterContext* h264bsfc = av_bitstream_filter_init("h264_mp4toannexb");
    //AVBitStreamFilterContext* aacbsfc = av_bitstream_filter_init("aac_adtstoasc");


    while (1)
    {
        //Get an AVPacket
        //if (acc_length>0)
        //{
        compare_tag = av_compare_ts(cur_pts_v,
                                    ifmt_ctx_v->streams[videoindex_v]->time_base,
                                    cur_pts_a,
                                    ifmt_ctx_a->streams[audioindex_a]->time_base);
        //}

        if (compare_tag <= 0)
        {
            ifmt_ctx = ifmt_ctx_v;
            stream_index = videoindex_out;

            if (av_read_frame(ifmt_ctx, &pkt) >= 0)
            {
                do
                {
                    in_stream = ifmt_ctx->streams[pkt.stream_index];
                    out_stream = ofmt_ctx->streams[stream_index];

                    if (pkt.stream_index == videoindex_v)
                    {
                        //FIX No PTS (Example: Raw H.264)
                        //Simple Write PTS
                        if (pkt.pts == AV_NOPTS_VALUE)
                        {
                            //Write PTS
                            AVRational time_base1 = in_stream->time_base;
                            //Duration between 2 frames (us)
                            int64_t calc_duration = (double)AV_TIME_BASE / av_q2d(in_stream->r_frame_rate);
                            //Parameters
                            pkt.pts = (double)(frame_index*calc_duration) / (double)(av_q2d(time_base1)*AV_TIME_BASE);
                            pkt.dts = pkt.pts;
                            pkt.duration = (double)calc_duration / (double)(av_q2d(time_base1)*AV_TIME_BASE);
                            frame_index++;
                        }

                        cur_pts_v = pkt.pts;
                        break;
                    }
                } while (av_read_frame(ifmt_ctx, &pkt) >= 0);
            }
            else
            {
                break;
            }
        }
        else
        {
            ifmt_ctx = ifmt_ctx_a;
            stream_index = audioindex_out;
            if (av_read_frame(ifmt_ctx, &pkt) >= 0)
            {
                do
                {
                    in_stream = ifmt_ctx->streams[pkt.stream_index];
                    out_stream = ofmt_ctx->streams[stream_index];

                    if (pkt.stream_index == audioindex_a)
                    {
                        //FIX No PTS
                        //Simple Write PTS
                        if (pkt.pts == AV_NOPTS_VALUE)
                        {
                            //Write PTS
                            AVRational time_base1 = in_stream->time_base;
                            //Duration between 2 frames (us)
                            int64_t calc_duration = (double)AV_TIME_BASE / av_q2d(in_stream->r_frame_rate);
                            //Parameters
                            pkt.pts = (double)(frame_index*calc_duration) / (double)(av_q2d(time_base1)*AV_TIME_BASE);
                            pkt.dts = pkt.pts;
                            pkt.duration = (double)calc_duration / (double)(av_q2d(time_base1)*AV_TIME_BASE);
                            frame_index++;
                        }
                        cur_pts_a = pkt.pts;

                        break;
                    }
                } while (av_read_frame(ifmt_ctx, &pkt) >= 0);
            }
            else
            {
                break;
            }
        }

        //FIX:Bitstream Filter
        //av_bitstream_filter_filter(h264bsfc, in_stream->codec, NULL, &pkt.data, &pkt.size, pkt.data, pkt.size, 0);
        //av_bitstream_filter_filter(aacbsfc, out_stream->codec, NULL, &pkt.data, &pkt.size, pkt.data, pkt.size, 0);

        //Convert PTS/DTS
        pkt.pts = av_rescale_q_rnd(pkt.pts,
                                   in_stream->time_base,
                                   out_stream->time_base,
                                   (AVRounding)(AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX));

        pkt.dts = av_rescale_q_rnd(pkt.dts,
                                   in_stream->time_base,
                                   out_stream->time_base,
                                   (AVRounding)(AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX));

        pkt.duration = av_rescale_q(pkt.duration, in_stream->time_base, out_stream->time_base);
        pkt.pos = -1;
        pkt.stream_index = stream_index;

        printf("Write 1 Packet. size:%5d\tpts:%lld\n", pkt.size, pkt.pts);

        if (av_interleaved_write_frame(ofmt_ctx, &pkt) < 0)
        {
            printf("Error muxing packet\n");
            break;
        }

        av_free_packet(&pkt);
    }

    //Write file trailer
    av_write_trailer(ofmt_ctx);

    //av_bitstream_filter_close(h264bsfc);
    //av_bitstream_filter_close(aacbsfc);


end:

    avformat_close_input(&ifmt_ctx_v);
    avformat_close_input(&ifmt_ctx_a);

    /* close output */
    if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
    {
        avio_close(ofmt_ctx->pb);
    }

    avformat_free_context(ofmt_ctx);

    if ((ret < 0) && (ret != AVERROR_EOF))
    {
        printf("Error occurred.\n");
        return -1;
    }

    printf("======muxer mp4 success =====!\n");
    return 0;
}

Answer 1

Mp4 没有对 PCM 的官方支持。即使某些工具可以用 pcm 制作非标准的 mp4，播放器也不知道如何阅读。