c - ffmpeg错误 "Could not allocate picture: Invalid argument Found Video Stream Found Audio Stream"

Question

我正在尝试编写一个 C 程序来通过网络上的 RTP 复制带有 rtp_mpegts 的 AV 编解码器来传输 AV

ffmpeg -re -i Sample_AV_15min.ts -acodec copy -vcodec copy -f rtp_mpegts rtp://192.168.1.1:5004

以 muxing.c 为例，其中使用了 ffmpeg 库。ffmpeg 应用程序运行良好。

直播详情

Input #0, mpegts, from 'Weather_Nation_10min.ts':
  Duration: 00:10:00.38, start: 41313.400811, bitrate: 2840 kb/s
  Program 1
    Stream #0:0[0x11]: Video: h264 (High) ([27][0][0][0] / 0x001B), yuv420p, 1440x1080 [SAR 4:3 DAR 16:9], 29.97 fps, 59.94 tbr, 90k tbn, 59.94 tbc
    Stream #0:1[0x14]: Audio: ac3 (AC-3 / 0x332D4341), 48000 Hz, stereo, fltp, 448 kb/s
Output #0, rtp_mpegts, to 'rtp://192.168.1.1:5004':
  Metadata:
    encoder         : Lavf54.63.104
    Stream #0:0: Video: h264 ([27][0][0][0] / 0x001B), yuv420p, 1440x1080 [SAR 4:3 DAR 16:9], q=2-31, 29.97 fps, 90k tbn, 29.97 tbc
    Stream #0:1: Audio: ac3 (AC-3 / 0x332D4341), 48000 Hz, stereo, 448 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (copy)
  Stream #0:1 -> #0:1 (copy)

但是，我的应用程序失败了

./my_test_app Sample_AV_15min.ts rtp://192.168.1.1:5004  
[h264 @ 0x800b30] non-existing PPS referenced                                  
[h264 @ 0x800b30] non-existing PPS 0 referenced                        
[h264 @ 0x800b30] decode_slice_header error                            
[h264 @ 0x800b30] no frame! 

[....snipped...]
[h264 @ 0x800b30] non-existing PPS 0 referenced        
[h264 @ 0x800b30] non-existing PPS referenced  
[h264 @ 0x800b30] non-existing PPS 0 referenced  
[h264 @ 0x800b30] decode_slice_header error  
[h264 @ 0x800b30] no frame!  
[h264 @ 0x800b30] mmco: unref short failure  
[h264 @ 0x800b30] mmco: unref short failure

[mpegts @ 0x800020] max_analyze_duration 5000000 reached at 5024000 microseconds  
[mpegts @ 0x800020] PES packet size mismatch could not find codec tag for codec id 
17075200, default to 0.  could not find codec tag for codec id 86019, default to 0.  
Could not allocate picture: Invalid argument  
Found Video Stream Found Audio Stream

我该如何解决这个问题？我基于muxing.c的完整源码

/**
 * @file
 * libavformat API example.
 *
 * Output a media file in any supported libavformat format.
 * The default codecs are used.
 * @example doc/examples/muxing.c
 */

#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 */

static int sws_flags = SWS_BICUBIC;

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

static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;
#if 0
/* 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;
}
#endif 
/**************************************************************/
/* 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 {
        /* encode the image */
        AVPacket pkt;
        int got_output;

        av_init_packet(&pkt);
        pkt.data = NULL;    // packet data will be allocated by the encoder
        pkt.size = 0;

        ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
        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 (got_output) {
            if (c->coded_frame->key_frame)
                pkt.flags |= AV_PKT_FLAG_KEY;

            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);
}

/**************************************************************/
/* 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;
    char errbuf[50];
    int i = 0;
    /* Initialize libavcodec, and register all codecs and formats. */
    av_register_all();

    if (argc != 3) {
        printf("usage: %s input_file out_file|stream\n"
               "API example program to output a media file with libavformat.\n"
               "This program generates a synthetic audio and video stream, encodes and\n"
               "muxes them into a file named output_file.\n"
               "The output format is automatically guessed according to the file extension.\n"
               "Raw images can also be output by using '%%d' in the filename.\n"
               "\n", argv[0]);
        return 1;
    }

    filename = argv[2];

    /* allocate the output media context */
    avformat_alloc_output_context2(&oc, NULL, "rtp_mpegts", 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;
    //Find input stream info.

   video_st = NULL;
   audio_st = NULL;

   avformat_open_input( &oc, argv[1], 0, 0);

   if ((ret = avformat_find_stream_info(oc, 0))< 0)
   {
       av_strerror(ret, errbuf,sizeof(errbuf));
       printf("Not Able to find stream info::%s ", errbuf);
       ret = -1;
       return ret;
   }
   for (i = 0; i < oc->nb_streams; i++)
   {
       if(oc->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
       {
           AVCodecContext *codec_ctx;
           unsigned int tag = 0;

           printf("Found Video Stream ");
           video_st = oc->streams[i];
           codec_ctx = video_st->codec;
           // m_num_frames = oc->streams[i]->nb_frames;
           video_codec = avcodec_find_decoder(codec_ctx->codec_id);
           ret = avcodec_open2(codec_ctx, video_codec, NULL);
            if (ret < 0) 
            {
                av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
                return ret;
            }
            if (av_codec_get_tag2(oc->oformat->codec_tag, video_codec->id, &tag) == 0) 
            {
                av_log(NULL, AV_LOG_ERROR, "could not find codec tag for codec id %d, default to 0.\n", audio_codec->id);
            }
            video_st->codec = avcodec_alloc_context3(video_codec);
            video_st->codec->codec_tag = tag;
       }

       if(oc->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
       {
           AVCodecContext *codec_ctx;
           unsigned int tag = 0;

           printf("Found Audio Stream ");
           audio_st = oc->streams[i];
          // aud_dts = audio_st->cur_dts;
          // aud_pts = audio_st->last_IP_pts;           
          codec_ctx = audio_st->codec;
          audio_codec = avcodec_find_decoder(codec_ctx->codec_id);
          ret = avcodec_open2(codec_ctx, audio_codec, NULL);
          if (ret < 0) 
          {
             av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
             return ret;
          }
          if (av_codec_get_tag2(oc->oformat->codec_tag, audio_codec->id, &tag) == 0) 
          {
              av_log(NULL, AV_LOG_ERROR, "could not find codec tag for codec id %d, default to 0.\n", audio_codec->id);
          }
          audio_st->codec = avcodec_alloc_context3(audio_codec);
          audio_st->codec->codec_tag = tag;
       }
   }
    /* Add the audio and video streams using the default format codecs
     * and initialize the codecs. */
    /*
    if (fmt->video_codec != AV_CODEC_ID_NONE) {
        video_st = add_stream(oc, &video_codec, fmt->video_codec);
    }
    if (fmt->audio_codec != AV_CODEC_ID_NONE) {
        audio_st = add_stream(oc, &audio_codec, fmt->audio_codec);
    }
    */

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

    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_st)
            audio_pts = (double)audio_st->pts.val * audio_st->time_base.num / audio_st->time_base.den;
        else
            audio_pts = 0.0;

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

        if ((!audio_st || audio_pts >= STREAM_DURATION) &&
            (!video_st || video_pts >= STREAM_DURATION))
            break;

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

    return 0;
}

Answer 1

我发现您已经硬编码了很多编解码器参数。您是否已验证编解码器支持它们？例如(借用ffmpeg):

static bool check_sample_fmt(AVCodec *codec, enum AVSampleFormat sample_fmt)
{
    const enum AVSampleFormat *p = codec->sample_fmts;
    while (*p != AV_SAMPLE_FMT_NONE) {
        if (*p == sample_fmt) {
            return true;
        }
        p++;
    }
    return false;
}

/* just pick the highest supported samplerate */
static int select_sample_rate(AVCodec *codec)
{
    if (!codec->supported_samplerates) {
        return 44100;
    }
    int best_samplerate = 0;
    const int *p = codec->supported_samplerates;
    while (*p) {
        best_samplerate = FFMAX(*p, best_samplerate);
        p++;
    }
    return best_samplerate;
}