C - 使用 FFmpeg 转码为 UDP？

Question

我正在尝试使用 FFmpeg 库获取现有视频文件并通过 UDP 连接传输它。具体来说，我一直在查看 FFmpeg 源代码 doc/example 目录中的 muxing.c 和 demuxing.c 示例文件。解复用文件提供允许将输入视频转换为视频和音频流的代码。 muxing 文件提供了创建假数据的代码，并且已经可以按照我的意愿输出到 UDP 连接。我已经开始将两者结合起来。下面可以找到我的代码，它基本上是 muxing 文件的副本，其中一些部分替换/附加了 demuxing 文件的一部分。不幸的是，我在通过这种方法尝试实现我的目标时遇到了很多麻烦。是否有一个现有的源代码示例可以执行我正在寻找的转码？或者至少是一个关于如何创建它的教程？如果没有，至少有一些指示可能有助于指导我的工作，将这两个文件组合起来以实现我的目标。具体来说，我遇到了错误:

[NULL @ 0x23b4040] Unable to find a suitable output format for 'udp://localhost:7777'
Could not deduce output format from file extension: using MPEG.
Output #0, mpeg, to 'udp://localhost:7777':

即使 muxing 文件可以接受 UDP 格式。有什么建议么？非常感谢!

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>

#include <libavutil/mathematics.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>

/* 5 seconds stream duration */
#define STREAM_DURATION   200.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES  ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT    AV_PIX_FMT_YUV420P /* default pix_fmt */

//FROM DE
static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static AVStream *video_stream = NULL, *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *video_dst_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *video_dst_file = NULL;
static FILE *audio_dst_file = NULL;

static uint8_t *video_dst_data[4] = {NULL};
static int      video_dst_linesize[4];
static int video_dst_bufsize;

static uint8_t **audio_dst_data = NULL;
static int       audio_dst_linesize;
static int audio_dst_bufsize;

static int video_stream_idx = -1, audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
//END DE

static int sws_flags = SWS_BICUBIC;

/**************************************************************/
/* audio output */

static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;

/* Add an output stream. */
static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
                            enum AVCodecID codec_id)
{
    AVCodecContext *c;
    AVStream *st;

    /* find the encoder */
    *codec = avcodec_find_encoder(codec_id);
    if (!(*codec)) {
        fprintf(stderr, "Could not find encoder for '%s'\n",
                avcodec_get_name(codec_id));
        exit(1);
    }

    st = avformat_new_stream(oc, *codec);
    if (!st) {
        fprintf(stderr, "Could not allocate stream\n");
        exit(1);
    }
    st->id = oc->nb_streams-1;
    c = st->codec;

    switch ((*codec)->type) {
    case AVMEDIA_TYPE_AUDIO:
        st->id = 1;
        c->sample_fmt  = AV_SAMPLE_FMT_S16;
        c->bit_rate    = 64000;
        c->sample_rate = 44100;
        c->channels    = 2;
        break;

    case AVMEDIA_TYPE_VIDEO:
        c->codec_id = codec_id;

        c->bit_rate = 400000;
        /* Resolution must be a multiple of two. */
        c->width    = 352;
        c->height   = 288;
        /* timebase: 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
         * identical to 1. */
        c->time_base.den = STREAM_FRAME_RATE;
        c->time_base.num = 1;
        c->gop_size      = 12; /* emit one intra frame every twelve frames at most */
        c->pix_fmt       = STREAM_PIX_FMT;
        if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
            /* just for testing, we also add B frames */
            c->max_b_frames = 2;
        }
        if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
            /* Needed to avoid using macroblocks in which some coeffs overflow.
             * This does not happen with normal video, it just happens here as
             * the motion of the chroma plane does not match the luma plane. */
            c->mb_decision = 2;
        }
    break;

    default:
        break;
    }

    /* Some formats want stream headers to be separate. */
    if (oc->oformat->flags & AVFMT_GLOBALHEADER)
        c->flags |= CODEC_FLAG_GLOBAL_HEADER;

    return st;
}

/**************************************************************/
/* audio output */

static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;

static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
    AVCodecContext *c;
    int ret;

    c = st->codec;

    /* open it */
    ret = avcodec_open2(c, codec, NULL);
    if (ret < 0) {
        fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret));
        exit(1);
    }

    /* init signal generator */
    t     = 0;
    tincr = 2 * M_PI * 110.0 / c->sample_rate;
    /* increment frequency by 110 Hz per second */
    tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;

    if (c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)
        audio_input_frame_size = 10000;
    else
        audio_input_frame_size = c->frame_size;
    samples = av_malloc(audio_input_frame_size *
                        av_get_bytes_per_sample(c->sample_fmt) *
                        c->channels);
    if (!samples) {
        fprintf(stderr, "Could not allocate audio samples buffer\n");
        exit(1);
    }
}

/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
 * 'nb_channels' channels. */
static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
{
    int j, i, v;
    int16_t *q;

    q = samples;
    for (j = 0; j < frame_size; j++) {
        v = (int)(sin(t) * 10000);
        for (i = 0; i < nb_channels; i++)
            *q++ = v;
        t     += tincr;
        tincr += tincr2;
    }
}

static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
    AVCodecContext *c;
    AVPacket pkt = { 0 }; // data and size must be 0;
    AVFrame *frame = avcodec_alloc_frame();
    int got_packet, ret;

    av_init_packet(&pkt);
    c = st->codec;

    get_audio_frame(samples, audio_input_frame_size, c->channels);
    frame->nb_samples = audio_input_frame_size;
    avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
                             (uint8_t *)samples,
                             audio_input_frame_size *
                             av_get_bytes_per_sample(c->sample_fmt) *
                             c->channels, 1);

    ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
    if (ret < 0) {
        fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret));
        exit(1);
    }

    if (!got_packet)
        return;

    pkt.stream_index = st->index;

    /* Write the compressed frame to the media file. */
    ret = av_interleaved_write_frame(oc, &pkt);
    if (ret != 0) {
        fprintf(stderr, "Error while writing audio frame: %s\n",
                av_err2str(ret));
        exit(1);
    }
    avcodec_free_frame(&frame);
}

static void close_audio(AVFormatContext *oc, AVStream *st)
{
    avcodec_close(st->codec);

    av_free(samples);
}

/**************************************************************/
/* video output */

static AVFrame *frame;
static AVPicture src_picture, dst_picture;
static int frame_count;

static void open_video(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
    int ret;
    AVCodecContext *c = st->codec;

    /* open the codec */
    ret = avcodec_open2(c, codec, NULL);
    if (ret < 0) {
        fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret));
        exit(1);
    }

    /* allocate and init a re-usable frame */
    frame = avcodec_alloc_frame();
    if (!frame) {
        fprintf(stderr, "Could not allocate video frame\n");
        exit(1);
    }

    /* Allocate the encoded raw picture. */
    ret = avpicture_alloc(&dst_picture, c->pix_fmt, c->width, c->height);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate picture: %s\n", av_err2str(ret));
        exit(1);
    }

    /* If the output format is not YUV420P, then a temporary YUV420P
     * picture is needed too. It is then converted to the required
     * output format. */
    if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
        ret = avpicture_alloc(&src_picture, AV_PIX_FMT_YUV420P, c->width, c->height);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate temporary picture: %s\n",
                    av_err2str(ret));
            exit(1);
        }
    }

    /* copy data and linesize picture pointers to frame */
    *((AVPicture *)frame) = dst_picture;
}

/* Prepare a dummy image. */
static void fill_yuv_image(AVPicture *pict, int frame_index,
                           int width, int height)
{
    int x, y, i;

    i = frame_index;

    /* Y */
    for (y = 0; y < height; y++)
        for (x = 0; x < width; x++)
            pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;

    /* Cb and Cr */
    for (y = 0; y < height / 2; y++) {
        for (x = 0; x < width / 2; x++) {
            pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
            pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
        }
    }
}

static void write_video_frame(AVFormatContext *oc, AVStream *st)
{
    int ret;
    static struct SwsContext *sws_ctx;
    AVCodecContext *c = st->codec;

    if (frame_count >= STREAM_NB_FRAMES) {
        /* No more frames to compress. The codec has a latency of a few
         * frames if using B-frames, so we get the last frames by
         * passing the same picture again. */
    } else {
        if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
            /* as we only generate a YUV420P picture, we must convert it
             * to the codec pixel format if needed */
            if (!sws_ctx) {
                sws_ctx = sws_getContext(c->width, c->height, AV_PIX_FMT_YUV420P,
                                         c->width, c->height, c->pix_fmt,
                                         sws_flags, NULL, NULL, NULL);
                if (!sws_ctx) {
                    fprintf(stderr,
                            "Could not initialize the conversion context\n");
                    exit(1);
                }
            }
            fill_yuv_image(&src_picture, frame_count, c->width, c->height);
            sws_scale(sws_ctx,
                      (const uint8_t * const *)src_picture.data, src_picture.linesize,
                      0, c->height, dst_picture.data, dst_picture.linesize);
        } else {
            fill_yuv_image(&dst_picture, frame_count, c->width, c->height);
        }
    }

    if (oc->oformat->flags & AVFMT_RAWPICTURE) {
        /* Raw video case - directly store the picture in the packet */
        AVPacket pkt;
        av_init_packet(&pkt);

        pkt.flags        |= AV_PKT_FLAG_KEY;
        pkt.stream_index  = st->index;
        pkt.data          = dst_picture.data[0];
        pkt.size          = sizeof(AVPicture);

        ret = av_interleaved_write_frame(oc, &pkt);
    } else {
        AVPacket pkt = { 0 };
        int got_packet;
        av_init_packet(&pkt);

        /* encode the image */
        ret = avcodec_encode_video2(c, &pkt, frame, &got_packet);
        if (ret < 0) {
            fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret));
            exit(1);
        }
        /* If size is zero, it means the image was buffered. */

        if (!ret && got_packet && pkt.size) {
            pkt.stream_index = st->index;

            /* Write the compressed frame to the media file. */
            ret = av_interleaved_write_frame(oc, &pkt);
        } else {
            ret = 0;
        }
    }
    if (ret != 0) {
        fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret));
        exit(1);
    }
    frame_count++;
}

static void close_video(AVFormatContext *oc, AVStream *st)
{
    avcodec_close(st->codec);
    av_free(src_picture.data[0]);
    av_free(dst_picture.data[0]);
    av_free(frame);
}

static int open_codec_context(int *stream_idx,
                              AVFormatContext *fmt_ctx, enum AVMediaType type)
{
    int ret;
    AVStream *st;
    AVCodecContext *dec_ctx = NULL;
    AVCodec *dec = NULL;

    ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not find %s stream in input file '%s'\n",
                av_get_media_type_string(type), src_filename);
        return ret;
    } else {
        *stream_idx = ret;
        st = fmt_ctx->streams[*stream_idx];

        /* find decoder for the stream */
        dec_ctx = st->codec;
        dec = avcodec_find_decoder(dec_ctx->codec_id);
        if (!dec) {
            fprintf(stderr, "Failed to find %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }

        if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) {
            fprintf(stderr, "Failed to open %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }
    }

    return 0;
}

/**************************************************************/
/* media file output */

int main(int argc, char **argv)
{
    const char *filename;
    AVOutputFormat *fmt;
    AVFormatContext *oc;
    AVStream *audio_st, *video_st;
    AVCodec *audio_codec, *video_codec;
    double audio_pts, video_pts;
    int ret = 0, got_frame;;

    /* Initialize libavcodec, and register all codecs and formats. */
    av_register_all();

    if (argc != 3) {
        printf("usage: %s input_file output_file\n"
               "\n", argv[0]);
        return 1;
    }

    src_filename = argv[1];
    filename = argv[2];

    /* allocate the output media context */
    avformat_alloc_output_context2(&oc, NULL, NULL, filename);
    if (!oc) {
        printf("Could not deduce output format from file extension: using MPEG.\n");
        avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);
    }
    if (!oc) {
        return 1;
    }
    fmt = oc->oformat;

    /* Add the audio and video streams using the default format codecs
     * and initialize the codecs. */
    video_stream = NULL;
    audio_stream = NULL;

    //FROM DE
    /* open input file, and allocate format context */
    if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
        fprintf(stderr, "Could not open source file %s\n", src_filename);
        exit(1);
    }

    /* retrieve stream information */
    if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
        fprintf(stderr, "Could not find stream information\n");
        exit(1);
    }
    if (open_codec_context(&video_stream_idx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
        video_stream = fmt_ctx->streams[video_stream_idx];
        video_dec_ctx = video_stream->codec;

        /* allocate image where the decoded image will be put */
        ret = av_image_alloc(video_dst_data, video_dst_linesize,
                             video_dec_ctx->width, video_dec_ctx->height,
                             video_dec_ctx->pix_fmt, 1);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate raw video buffer\n");
            goto end;
        }
        video_dst_bufsize = ret;
    }

    if (open_codec_context(&audio_stream_idx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
        int nb_planes;

        audio_stream = fmt_ctx->streams[audio_stream_idx];
        audio_dec_ctx = audio_stream->codec;

        nb_planes = av_sample_fmt_is_planar(audio_dec_ctx->sample_fmt) ?
            audio_dec_ctx->channels : 1;
        audio_dst_data = av_mallocz(sizeof(uint8_t *) * nb_planes);
        if (!audio_dst_data) {
            fprintf(stderr, "Could not allocate audio data buffers\n");
            ret = AVERROR(ENOMEM);
            goto end;
        }
    }
    //END DE

    /* Now that all the parameters are set, we can open the audio and
     * video codecs and allocate the necessary encode buffers. */
    if (video_stream)
        open_video(oc, video_codec, video_stream);
    if (audio_stream)
        open_audio(oc, audio_codec, audio_stream);

    av_dump_format(oc, 0, filename, 1);

    /* open the output file, if needed */
    if (!(fmt->flags & AVFMT_NOFILE)) {
        ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);
        if (ret < 0) {
            fprintf(stderr, "Could not open '%s': %s\n", filename,
                    av_err2str(ret));
            return 1;
        }
    }

    /* Write the stream header, if any. */
    ret = avformat_write_header(oc, NULL);
    if (ret < 0) {
        fprintf(stderr, "Error occurred when opening output file: %s\n",
                av_err2str(ret));
        return 1;
    }

    if (frame)
        frame->pts = 0;
    for (;;) {
        /* Compute current audio and video time. */
        if (audio_stream)
            audio_pts = (double)audio_stream->pts.val * audio_stream->time_base.num / audio_stream->time_base.den;
        else
            audio_pts = 0.0;

        if (video_stream)
            video_pts = (double)video_stream->pts.val * video_stream->time_base.num /
                        video_stream->time_base.den;
        else
            video_pts = 0.0;

        if ((!audio_stream || audio_pts >= STREAM_DURATION) &&
            (!video_stream || video_pts >= STREAM_DURATION))
            break;

        /* write interleaved audio and video frames */
        if (!video_stream || (video_stream && audio_st && audio_pts < video_pts)) {
            write_audio_frame(oc, audio_stream);
        } else {
            write_video_frame(oc, video_stream);
            frame->pts += av_rescale_q(1, video_stream->codec->time_base, video_stream->time_base);
        }
    }

    /* Write the trailer, if any. The trailer must be written before you
     * close the CodecContexts open when you wrote the header; otherwise
     * av_write_trailer() may try to use memory that was freed on
     * av_codec_close(). */
    av_write_trailer(oc);

    /* Close each codec. */
    if (video_st)
        close_video(oc, video_st);
    if (audio_st)
        close_audio(oc, audio_st);

    if (!(fmt->flags & AVFMT_NOFILE))
        /* Close the output file. */
        avio_close(oc->pb);

    /* free the stream */
    avformat_free_context(oc);

end:
    if (video_dec_ctx)
        avcodec_close(video_dec_ctx);
    if (audio_dec_ctx)
        avcodec_close(audio_dec_ctx);
    avformat_close_input(&fmt_ctx);
    if (video_dst_file)
        fclose(video_dst_file);
    if (audio_dst_file)
        fclose(audio_dst_file);
    av_free(frame);
    av_free(video_dst_data[0]);
    av_free(audio_dst_data);

    return 0;
}

Answer 1

你遇到的麻烦是因为udp不是多媒体格式。它是一种网络协议(protocol)。 Ffmpeg 转换为多媒体格式并可以将输出转储到各种位置，例如磁盘(最常见的情况)或在这种情况下在网络上。因此，在通过 udp 发送内容之前，您必须决定要将内容转换成哪种格式。在命令行中，这将使用 -f 格式标志来完成。可流格式是传输流、容器中的 webm 和基本流。您可能希望使用 rtp 通过 udp 进行流式传输，否则在接收端您将面临丢失数据包和乱序到达的问题。

鉴于您当前的状态，我建议您首先通过命令行本身实现您想要执行的操作。这将使您了解必须做的各种事情。然后你就可以去节目了。