Update (转)FFMpeg写MP4文件例子分析.c

(转)FFMpeg写MP4文件例子分析.c

@@ -1,151 +1,546 @@
 /**
-使用FFMpeg可以很方便的对音视频进行编码，并且写文件。
+这段时间看了FFMpeg提供的例子muxing.c，我略微修改了下源代码，使其生成一个MP4文件，音频使用AAC编码，视频使用H.264编码。代码很简单，我就不做说明了，代码如下。
 
-下面的代码是将5幅1280*720大小的图片进行编码，并且写到文件中。
+以后我们继续写如何将DirectShow中采集的音视频数据编码并生成MP4文件。
+*/
+
+/* 5 seconds stream duration */
+#define STREAM_DURATION   5.0
+#define STREAM_FRAME_RATE 25 /* 25 images/s */
+#define STREAM_NB_FRAMES  ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
+#define STREAM_PIX_FMT PIX_FMT_YUV420P /* default pix_fmt */
+
+static int sws_flags = SWS_BICUBIC;
+
+/**************************************************************/
+/* audio output */
 
-代码有些乱，但希望能抛砖引玉，对学习这方面的朋友有帮助。
+static float t, tincr, tincr2;
+static int16_t *samples;
+static uint8_t *audio_outbuf;
+static int audio_outbuf_size;
+static int audio_input_frame_size;
+
+/*
+* add an audio output stream
 */
+static AVStream *add_audio_stream(AVFormatContext *oc, enum CodecID codec_id)
+{
+    AVCodecContext *c;
+    AVStream *st;
+
+    st = avformat_new_stream(oc, NULL);
+    if (!st) {
+        fprintf(stderr, "Could not alloc stream\n");
+        exit(1);
+    }
+    st->id = 1;
+
+    c = st->codec;
+    c->codec_id = codec_id;
+    c->codec_type = AVMEDIA_TYPE_AUDIO;
+
+    /* put sample parameters */
+    c->sample_fmt = AV_SAMPLE_FMT_S16;
+    c->bit_rate = 64000;
+    c->sample_rate = 44100;
+    c->channels = 2;
+
+    // some formats want stream headers to be separate
+    if (oc->oformat->flags & AVFMT_GLOBALHEADER)
+        c->flags |= CODEC_FLAG_GLOBAL_HEADER;
+
+    return st;
+}
+
+static void open_audio(AVFormatContext *oc, AVStream *st)
+{
+    AVCodecContext *c;
+    AVCodec *codec;
 
-CFile file[5];
+    c = st->codec;
-BYTE *szTxt[5];
 
-int nWidth = 0;
+    /* find the audio encoder */
-int nHeight= 0;
+    codec = avcodec_find_encoder(c->codec_id);
+    if (!codec) {
+        fprintf(stderr, "codec not found\n");
+        exit(1);
+    }
 
-int nDataLen=0;
+    /* open it */
+    if (avcodec_open(c, codec) < 0) {
+        fprintf(stderr, "could not open codec\n");
+        exit(1);
+    }
 
-int nLen;
+    /* 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;
+
+    audio_outbuf_size = 10000;
+    audio_outbuf = (uint8_t *)av_malloc(audio_outbuf_size);
+
+    /* ugly hack for PCM codecs (will be removed ASAP with new PCM
+    support to compute the input frame size in samples */
+    if (c->frame_size <= 1) {
+        audio_input_frame_size = audio_outbuf_size / c->channels;
+        switch(st->codec->codec_id) {
+        case CODEC_ID_PCM_S16LE:
+        case CODEC_ID_PCM_S16BE:
+        case CODEC_ID_PCM_U16LE:
+        case CODEC_ID_PCM_U16BE:
+            audio_input_frame_size >>= 1;
+            break;
+        default:
+            break;
+        }
+    } else {
+        audio_input_frame_size = c->frame_size;
+    }
+    samples = (int16_t *)av_malloc(audio_input_frame_size * 2 * c->channels);
+}
 
-CString csFileName;
+/* prepare a 16 bit dummy audio frame of 'frame_size' samples and
-for (int fileI = 1; fileI <= 5; fileI ++)
+'nb_channels' channels */
+static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
 {
-  csFileName.Format("e:\\pics\\%d.bmp", fileI);
+    int j, i, v;
-  file[fileI - 1].Open(csFileName,CFile::modeRead | CFile::typeBinary);
+    int16_t *q;
-  nLen = file[fileI - 1].GetLength();
+
+    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;
+    av_init_packet(&pkt);
 
-  szTxt[fileI -1] = new BYTE[nLen];
+    c = st->codec;
-  file[fileI - 1].Read(szTxt[fileI - 1], nLen);
-  file[fileI - 1].Close();
 
-  //BMP bmi;//BITMAPINFO bmi;
+    get_audio_frame(samples, audio_input_frame_size, c->channels);
-  //int nHeadLen = sizeof(BMP);
-  BITMAPFILEHEADER bmpFHeader;
-  BITMAPINFOHEADER bmpIHeader;
-  memcpy(&bmpFHeader,szTxt[fileI -1],sizeof(BITMAPFILEHEADER));
 
-  int nHeadLen = bmpFHeader.bfOffBits - sizeof(BITMAPFILEHEADER);
+    pkt.size = avcodec_encode_audio(c, audio_outbuf, audio_outbuf_size, samples);
-  memcpy(&bmpIHeader,szTxt[fileI - 1]+sizeof(BITMAPFILEHEADER),nHeadLen);
 
-nWidth = bmpIHeader.biWidth;// 464;// bmi.bmpInfo.bmiHeader.biWidth;// ;
+    if (c->coded_frame && c->coded_frame->pts != AV_NOPTS_VALUE)
-  nHeight = bmpIHeader.biHeight;//362;// bmi.bmpInfo.bmiHeader.biHeight;// ;
+        pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
+    pkt.flags |= AV_PKT_FLAG_KEY;
+    pkt.stream_index = st->index;
+    pkt.data = audio_outbuf;
 
-  szTxt[fileI - 1] += bmpFHeader.bfOffBits;
+    /* write the compressed frame in the media file */
-  nDataLen = nLen-bmpFHeader.bfOffBits;
+    if (av_interleaved_write_frame(oc, &pkt) != 0) {
+        fprintf(stderr, "Error while writing audio frame\n");
+        exit(1);
+    }
 }
 
-av_register_all();
+static void close_audio(AVFormatContext *oc, AVStream *st)
-avcodec_register_all();
-AVFrame *m_pRGBFrame =  new AVFrame[1];  //RGB帧数据
-AVFrame *m_pYUVFrame = new AVFrame[1];;  //YUV帧数据
-AVCodecContext *c= NULL;
-AVCodecContext *in_c= NULL;
-AVCodec *pCodecH264; //编码器
-uint8_t * yuv_buff;//
-
-//查找h264编码器
-pCodecH264 = avcodec_find_encoder(CODEC_ID_H264);
-if(!pCodecH264)
 {
-  fprintf(stderr, "h264 codec not found\n");
+    avcodec_close(st->codec);
+
+    av_free(samples);
+    av_free(audio_outbuf);
+}
+
+/**************************************************************/
+/* video output */
+
+static AVFrame *picture, *tmp_picture;
+static uint8_t *video_outbuf;
+static int frame_count, video_outbuf_size;
+
+/* add a video output stream */
+static AVStream *add_video_stream(AVFormatContext *oc, enum CodecID codec_id)
+{
+    AVCodecContext *c;
+    AVStream *st;
+    AVCodec *codec;
+
+    st = avformat_new_stream(oc, NULL);
+    if (!st) {
+        fprintf(stderr, "Could not alloc stream\n");
+        exit(1);
+    }
+
+    c = st->codec;
+
+    /* find the video encoder */
+    codec = avcodec_find_encoder(codec_id);
+    if (!codec) {
+        fprintf(stderr, "codec not found\n");
+        exit(1);
+    }
+    avcodec_get_context_defaults3(c, codec);
+
+    c->codec_id = codec_id;
+
+    /* put sample parameters */
+    c->bit_rate = /*400000*/3000000;
+    /* resolution must be a multiple of two */
+    c->width = /*352*/640;
+    c->height = /*288*/480;
+    /* time base: 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
+    identically 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 == CODEC_ID_MPEG2VIDEO) {
+        /* just for testing, we also add B frames */
+        c->max_b_frames = 2;
+    }
+    if (c->codec_id == 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;
+    }
+    // some formats want stream headers to be separate
+    if (oc->oformat->flags & AVFMT_GLOBALHEADER)
+        c->flags |= CODEC_FLAG_GLOBAL_HEADER;
+
+
+
+    return st;
+}
+
+static AVFrame *alloc_picture(enum PixelFormat pix_fmt, int width, int height)
+{
+    AVFrame *picture;
+    uint8_t *picture_buf;
+    int size;
+
+    picture = avcodec_alloc_frame();
+    if (!picture)
+        return NULL;
+    size = avpicture_get_size(pix_fmt, width, height);
+    picture_buf = (uint8_t *)av_malloc(size);
+    if (!picture_buf) {
+        av_free(picture);
+        return NULL;
+    }
+    avpicture_fill((AVPicture *)picture, picture_buf,
+        pix_fmt, width, height);
+    return picture;
+}
+
+static void open_video(AVFormatContext *oc, AVStream *st)
+{
+    AVCodec *codec;
+    AVCodecContext *c;
+
+    c = st->codec;
+
+    /* find the video encoder */
+    codec = avcodec_find_encoder(c->codec_id);
+    if (!codec) {
+        fprintf(stderr, "codec not found\n");
+        exit(1);
+    }
+
+    /* open the codec */
+    if (avcodec_open(c, codec) < 0) {
+        fprintf(stderr, "could not open codec\n");
         exit(1);
+    }
+
+    video_outbuf = NULL;
+    if (!(oc->oformat->flags & AVFMT_RAWPICTURE)) {
+        /* allocate output buffer */
+        /* XXX: API change will be done */
+        /* buffers passed into lav* can be allocated any way you prefer,
+        as long as they're aligned enough for the architecture, and
+        they're freed appropriately (such as using av_free for buffers
+        allocated with av_malloc) */
+        video_outbuf_size = 200000;
+        video_outbuf = (uint8_t *)av_malloc(video_outbuf_size);
+    }
+
+    /* allocate the encoded raw picture */
+    picture = alloc_picture(c->pix_fmt, c->width, c->height);
+    if (!picture) {
+        fprintf(stderr, "Could not allocate picture\n");
+        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 */
+    tmp_picture = NULL;
+    if (c->pix_fmt != PIX_FMT_YUV420P) {
+        tmp_picture = alloc_picture(PIX_FMT_YUV420P, c->width, c->height);
+        if (!tmp_picture) {
+            fprintf(stderr, "Could not allocate temporary picture\n");
+            exit(1);
+        }
+    }
+}
+
+/* prepare a dummy image */
+static void fill_yuv_image(AVFrame *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;
+        }
+    }
 }
 
-c= avcodec_alloc_context3(pCodecH264);
+static void write_video_frame(AVFormatContext *oc, AVStream *st)
-c->bit_rate = 3000000;// put sample parameters
-c->width =nWidth;//
-c->height = nHeight;//
-
-// frames per second
-AVRational rate;
-rate.num = 1;
-rate.den = 25;
-c->time_base= rate;//(AVRational){1,25};
-c->gop_size = 10; // emit one intra frame every ten frames
-c->max_b_frames=1;
-c->thread_count = 1;
-c->pix_fmt = PIX_FMT_YUV420P;//PIX_FMT_RGB24;
-
-//av_opt_set(c->priv_data, /*"preset"*/"libvpx-1080p.ffpreset", /*"slow"*/NULL, 0);
-//打开编码器
-if(avcodec_open2(c,pCodecH264,NULL)<0)
-  TRACE("不能打开编码库");
-
-int size = c->width * c->height;
-
-yuv_buff = (uint8_t *) malloc((size * 3) / 2); // size for YUV 420
-
-//将rgb图像数据填充rgb帧
-uint8_t * rgb_buff = new uint8_t[nDataLen];
-
-//图象编码
-int outbuf_size=100000;
-uint8_t * outbuf= (uint8_t*)malloc(outbuf_size);
-int u_size = 0;
-FILE *f=NULL;
-char * filename = "e:\\pics\\myData.h264";
-f = fopen(filename, "wb");
-if (!f)
 {
-  TRACE( "could not open %s\n", filename);
+    int out_size, ret;
+    AVCodecContext *c;
+    static struct SwsContext *img_convert_ctx;
+
+    c = st->codec;
+
+    if (frame_count >= STREAM_NB_FRAMES) {
+        /* no more frame 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 != PIX_FMT_YUV420P) {
+            /* as we only generate a YUV420P picture, we must convert it
+            to the codec pixel format if needed */
+            if (img_convert_ctx == NULL) {
+                img_convert_ctx = sws_getContext(c->width, c->height,
+                    PIX_FMT_YUV420P,
+                    c->width, c->height,
+                    c->pix_fmt,
+                    sws_flags, NULL, NULL, NULL);
+                if (img_convert_ctx == NULL) {
+                    fprintf(stderr, "Cannot initialize the conversion context\n");
                     exit(1);
+                }
+            }
+            fill_yuv_image(tmp_picture, frame_count, c->width, c->height);
+            sws_scale(img_convert_ctx, tmp_picture->data, tmp_picture->linesize,
+                0, c->height, picture->data, picture->linesize);
+        } else {
+            fill_yuv_image(picture, frame_count, c->width, c->height);
+        }
+    }
+
+
+    if (oc->oformat->flags & AVFMT_RAWPICTURE) {
+        /* raw video case. The API will change slightly in the near
+        future for that. */
+        AVPacket pkt;
+        av_init_packet(&pkt);
+
+        pkt.flags |= AV_PKT_FLAG_KEY;
+        pkt.stream_index = st->index;
+        pkt.data = (uint8_t *)picture;
+        pkt.size = sizeof(AVPicture);
+
+        ret = av_interleaved_write_frame(oc, &pkt);
+    } else {
+        /* encode the image */
+        out_size = avcodec_encode_video(c, video_outbuf, video_outbuf_size, picture);
+        /* if zero size, it means the image was buffered */
+        if (out_size > 0) {
+            AVPacket pkt;
+            av_init_packet(&pkt);
+
+            if (c->coded_frame->pts != AV_NOPTS_VALUE)
+                pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
+            if(c->coded_frame->key_frame)
+                pkt.flags |= AV_PKT_FLAG_KEY;
+            pkt.stream_index = st->index;
+            pkt.data = video_outbuf;
+            pkt.size = out_size;
+
+//            printf("pts %d \n", c->coded_frame->pts);
+
+            /* write the compressed frame in the media file */
+            ret = av_interleaved_write_frame(oc, &pkt);
+        } else {
+            ret = 0;
+        }
+    }
+    if (ret != 0) {
+        fprintf(stderr, "Error while writing video frame\n");
+        exit(1);
+    }
+    frame_count++;
 }
 
-//初始化SwsContext
+static void close_video(AVFormatContext *oc, AVStream *st)
-SwsContext * scxt = sws_getContext(c->width,c->height,PIX_FMT_BGR24,c->width,c->height,PIX_FMT_YUV420P,SWS_POINT,NULL,NULL,NULL);
+{
+    avcodec_close(st->codec);
+    av_free(picture->data[0]);
+    av_free(picture);
+    if (tmp_picture) {
+        av_free(tmp_picture->data[0]);
+        av_free(tmp_picture);
+    }
+    av_free(video_outbuf);
+}
+
+/**************************************************************/
+/* media file output */
 
-AVPacket avpkt;
 
-//AVFrame *pTFrame=new AVFrame
+int main(int argc, char **argv)
-for (int i=0;i<250;++i)
 {
+    const char *filename;
+    AVOutputFormat *fmt;
+    AVFormatContext *oc;
+    AVStream *audio_st, *video_st;
+    double audio_pts, video_pts;
+    int i;
+
+    /* initialize libavcodec, and register all codecs and formats */
+    av_register_all();
+
+#if 0
+    if (argc != 2) {
+        printf("usage: %s output_file\n"
+            "API example program to output a media file with libavformat.\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;
+    }
 
-  //AVFrame *m_pYUVFrame = new AVFrame[1];
+    filename = argv[1];
+#endif
 
-  int index = (i / 25) % 5;
+//#define RTMP_STREAM
-  memcpy(rgb_buff,szTxt[index],nDataLen);
+#ifdef RTMP_STREAM
+    filename = "rtmp://192.168.0.239/live/livestream";
+#else
+    filename = "1.mp4";
+#endif
 
-  avpicture_fill((AVPicture*)m_pRGBFrame, (uint8_t*)rgb_buff, PIX_FMT_RGB24, nWidth, nHeight);
+    /* 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"*/"flv", filename);
+    }
 
-  //将YUV buffer 填充YUV Frame
+    if (!oc)
-  avpicture_fill((AVPicture*)m_pYUVFrame, (uint8_t*)yuv_buff, PIX_FMT_YUV420P, nWidth, nHeight);
+    {
+        return 1;
+    }
+
+    // 强制指定 264 编码
+    oc->oformat->video_codec = CODEC_ID_H264;
+    oc->oformat->audio_codec = CODEC_ID_AAC;
 
-  // 翻转RGB图像
+    fmt = oc->oformat;
-  m_pRGBFrame->data[0]  += m_pRGBFrame->linesize[0] * (nHeight - 1);
-  m_pRGBFrame->linesize[0] *= -1;
-  m_pRGBFrame->data[1]  += m_pRGBFrame->linesize[1] * (nHeight / 2 - 1);
-  m_pRGBFrame->linesize[1] *= -1;
-  m_pRGBFrame->data[2]  += m_pRGBFrame->linesize[2] * (nHeight / 2 - 1);
-  m_pRGBFrame->linesize[2] *= -1;
 
+    /* add the audio and video streams using the default format codecs
+    and initialize the codecs */
+    video_st = NULL;
+    audio_st = NULL;
+    if (fmt->video_codec != CODEC_ID_NONE) {
+        video_st = add_video_stream(oc, fmt->video_codec);
+    }
+    if (fmt->audio_codec != CODEC_ID_NONE) {
+        audio_st = add_audio_stream(oc, fmt->audio_codec);
+    }
 
-  //将RGB转化为YUV
+    av_dump_format(oc, 0, filename, 1);
-  sws_scale(scxt,m_pRGBFrame->data,m_pRGBFrame->linesize,0,c->height,m_pYUVFrame->data,m_pYUVFrame->linesize);
 
-  int got_packet_ptr = 0;
+    /* now that all the parameters are set, we can open the audio and
-  av_init_packet(&avpkt);
+    video codecs and allocate the necessary encode buffers */
-  avpkt.data = outbuf;
+    if (video_st)
-  avpkt.size = outbuf_size;
+        open_video(oc, video_st);
-  u_size = avcodec_encode_video2(c, &avpkt, m_pYUVFrame, &got_packet_ptr);
+    if (audio_st)
-  if (u_size == 0)
+        open_audio(oc, audio_st);
+
+    /* open the output file, if needed */
+    if (!(fmt->flags & AVFMT_NOFILE)) {
+        if (avio_open(&oc->pb, filename, AVIO_FLAG_WRITE) < 0) {
+            fprintf(stderr, "Could not open '%s'\n", filename);
+            return 1;
+        }
+    }
+
+    /* write the stream header, if any */
+    avformat_write_header(oc, NULL);
+    picture->pts = 0;
+    for(;;)
     {
-   fwrite(avpkt.data, 1, avpkt.size, f);
+        /* 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);
+
+            picture->pts++;
+        }
+    }
+
+    /* write the trailer, if any.  the trailer must be written
+    * before you close the CodecContexts open when you wrote the
+    * header; otherwise 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);
+
+    /* free the streams */
+    for(i = 0; i < oc->nb_streams; i++) {
+        av_freep(&oc->streams[i]->codec);
+        av_freep(&oc->streams[i]);
     }
-}
 
-fclose(f);
+    if (!(fmt->flags & AVFMT_NOFILE)) {
-delete []m_pRGBFrame;
+        /* close the output file */
-delete []m_pYUVFrame;
+        avio_close(oc->pb);
-delete []rgb_buff;
+    }
-free(outbuf);
+
-avcodec_close(c);
+    /* free the stream */
-av_free(c);
+    av_free(oc);
+
+    return 0;
+}