基于ffmpeg源码实现提取视频时间轴缩略图

以下代码实现了，从1280*544.mp4视频的第十秒开始提取100帧,并将每一帧缩小为源帧的1/4宽高，然后将处理过后的100帧封装到一帧中，并输出为yuv文件。

#include <stdio.h>

#define __STDC_CONSTANT_MACROS
#define FRAMEWITH 320
#define FRAMEHEIGTH 136

extern "C"
{
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libswscale/swscale.h"
};

#define NUM 100

int main(int argc, char* argv[])
{
    AVFormatContext *pFormatCtx;
    int             i, videoindex;
    AVCodecContext  *pCodecCtx;
    AVCodec         *pCodec;
    AVFrame *pFrame, *pFrameYUV[NUM], *pDstFrame;
    uint8_t *out_buffer[NUM];
    AVPacket *packet;
    int y_size;
    int ret, got_picture;
    struct SwsContext *img_convert_ctx;
    //输入文件路径
    char filepath[]="1280*544.mp4";
    int frame_cnt;
    av_register_all();
    avformat_network_init();
    pFormatCtx = avformat_alloc_context();

    if(avformat_open_input(&pFormatCtx,filepath,NULL,NULL)!=0)
    {
        printf("Couldn't open input stream.\n");      
        return -1;
    }
    
    if(avformat_find_stream_info(pFormatCtx,NULL)<0)
    {
        printf("Couldn't find stream information.\n");        
        return -1;
    }
    
    videoindex = -1;
    for(i = 0; i < pFormatCtx->nb_streams; i++)
    {
       if(pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
       {
           videoindex = i;
           break;
       }
    } 
       
    if(videoindex == -1)
    {
        printf("Didn't find a video stream.\n");      
        return -1;
    }

    pCodecCtx = pFormatCtx->streams[videoindex]->codec;
    pCodec = avcodec_find_decoder(pCodecCtx->codec_id);
    if(pCodec==NULL)
    {
        printf("Codec not found.\n");       
        return -1;
    }
    
    if(avcodec_open2(pCodecCtx, pCodec,NULL)<0)
    {
        printf("Could not open codec.\n");        
        return -1;
    }
    /*
     * 在此处添加输出视频信息的代码
     * 取自于pFormatCtx，使用fprintf()
     */
    pFrame = av_frame_alloc();
    for(int i = 0; i < NUM; i++)
    {
        pFrameYUV[i] = av_frame_alloc();        
    }
       
    for(int i = 0; i < NUM; i++)
    {
        out_buffer[i] = (uint8_t *)av_malloc(avpicture_get_size(AV_PIX_FMT_YUV420P, FRAMEWITH, FRAMEHEIGTH));
        avpicture_fill((AVPicture *)pFrameYUV[i], out_buffer[i], AV_PIX_FMT_YUV420P, FRAMEWITH, FRAMEHEIGTH);
    }
    
    pDstFrame = av_frame_alloc();
    int nDstSize = avpicture_get_size(AV_PIX_FMT_YUV420P, FRAMEWITH * NUM, FRAMEHEIGTH);
    uint8_t *dstbuf = new uint8_t[nDstSize];
    avpicture_fill((AVPicture*)pDstFrame, dstbuf, AV_PIX_FMT_YUV420P, FRAMEWITH * NUM, FRAMEHEIGTH);

    pDstFrame->width  = FRAMEWITH * NUM;
    pDstFrame->height = FRAMEHEIGTH;
    pDstFrame->format = AV_PIX_FMT_YUV420P;

    //将预先分配的AVFrame图像背景数据设置为黑色背景  
    memset(pDstFrame->data[0], 0, FRAMEWITH * FRAMEHEIGTH * NUM);
    memset(pDstFrame->data[1], 0x80, FRAMEWITH * FRAMEHEIGTH / 4 * NUM);
    memset(pDstFrame->data[2], 0x80, FRAMEWITH * FRAMEHEIGTH / 4 * NUM);

    packet=(AVPacket *)av_malloc(sizeof(AVPacket));    
    printf("--------------- File Information ----------------\n");
    av_dump_format(pFormatCtx, 0, filepath, 0);
    printf("-------------------------------------------------\n");
    img_convert_ctx = sws_getContext(pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, 
        FRAMEWITH, FRAMEHEIGTH, AV_PIX_FMT_YUV420P, SWS_BICUBIC, NULL, NULL, NULL);

    int count = 0;
    frame_cnt = 0;
    int make  = 0;
        
    FILE *fp_yuv420 = fopen("test.yuv", "wb+");
    if(NULL == fp_yuv420)
    {
        printf("test.yuv open error!\n");
        av_frame_free(&pDstFrame);
        av_free_packet(packet);
        return -1;  
    }
      
    while((av_read_frame(pFormatCtx, packet) >= 0) && (make < (NUM + 10)))
    {
        if(packet->stream_index == videoindex)
        {               
            ret = avcodec_decode_video2(pCodecCtx, pFrame, &got_picture, packet);
            if(ret < 0)
            {
                printf("Decode Error.\n");
                fclose(fp_yuv420);
                av_free_packet(packet);
                return -1;
            }
            if(got_picture && (make > 9))
            {
                sws_scale(img_convert_ctx, (const uint8_t* const*)pFrame->data, pFrame->linesize, 0, pCodecCtx->height, 
                    pFrameYUV[count]->data, pFrameYUV[count]->linesize);
                printf("Decoded frame index: %d\n",frame_cnt);
                count++;  
            }  
            make++;
            av_free_packet(packet);                                       
        }
    }
    
    /* 如果需要直接写为YUV文件  */
    for (int i = 0; i < FRAMEHEIGTH; i++)
    {                   
        //从pFrameYUV[]中提取数据一帧一帧写入到文件中
        for(int j = 0; j < NUM; j++)
        {
          fwrite(pFrameYUV[j]->data[0] + i*FRAMEWITH, 1, FRAMEWITH, fp_yuv420);    //Y      
        }                                     
    }
    
    for (int i = 0; i < FRAMEHEIGTH / 4; i++)
    {
        //从pFrameYUV[]中提取数据一帧一帧写入到文件中
        for(int j =0; j < NUM; j++)
        {
          fwrite(pFrameYUV[j]->data[1] + i * FRAMEWITH, 1, FRAMEWITH, fp_yuv420);  //U    
        }                                   
    }
    
    for (int i = 0; i < FRAMEHEIGTH / 4; i++)
    {
        for(int j =0; j < NUM; j++)
        {
          fwrite(pFrameYUV[j]->data[2] + i * FRAMEWITH, 1, FRAMEWITH, fp_yuv420);  //V  
        }
    }
   
    fclose(fp_yuv420);
    sws_freeContext(img_convert_ctx);

    for(int i =0; i< NUM; i++)
    {
        av_frame_free(&pFrameYUV[i]);
    }
    
    av_frame_free(&pFrame);
    avcodec_close(pCodecCtx);
    avformat_close_input(&pFormatCtx);

    return 0;
}

1280_544.png

下面这张图是将yuv转换为图片后，由于是宽度是100*320，图片太大，这边就截取其中的一段。

100_320_136.png