FFmpeg开发实战（六）：使用 FFmpeg 将YUV数据编码为视频文件

本文中实现的一个小功能是把一个YUV原始视频数据(时间序列图像)经过h264编码为视频码流，然后在使用mp4封装格式封装。

编码&封装的流程图如下：

使用ffmpeg编码流程：

1、首先使用av_register_all()函数注册所有的编码器和复用器(理解为格式封装器)。该步骤必须放在所有ffmpeg代码前第一个执行

2、avformat_alloc_output_context2()：初始化包含有输出码流(AVStream)和解复用器(AVInputFormat)的AVFormatContext

3、avio_open( )打开输出文件

4、av_new_stream() 创建视频码流 该函数生成一个空AVstream 该结构存放编码后的视频码流 。视频码流被拆分为AVPacket新式保存在AVStream中。

5、设置编码器信息，该步骤主要是为AVCodecContext(从AVStream->codec 获取指针)结构体设置一些参数，包括codec_id、codec_type、width、height、pix_fmt .....  根据编码器的不同，还要额外设置一些参数(如 h264 要设置qmax、qmin、qcompress参数才能正常使用h264编码)

6、查找并打开编码器，根据前一步设置的编码器参数信息，来查找初始化一个编码其，并将其打开。用到函数为av_fine_encoder()和av_open2()。

7、写头文件  avformat_write_header()。这一步主要是将封装格式的信息写入文件头部位置。

8、编码帧。用到的函数 avcodec_encode_video2() 将AVFrame编码为AVPacket

9、在写入文件之前 还需要做一件事情就是设置AVPacket一些信息。这些信息关乎最后封装格式能否被正确读取。后面回详细讲述该部分内容

10、编码帧写入文件 av_write_frame()

11、flush_encoder()：输入的像素数据读取完成后调用此函数。用于输出编码器中剩余的AVPacket。

12、av_write_trailer()：写文件尾（对于某些没有文件头的封装格式，不需要此函数。比如说MPEG2TS）。

源码：

#include <stdio.h>
#include "pch.h"
#include <iostream>


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

using namespace std;

int flush_encoder(AVFormatContext *fmt_ctx, unsigned int stream_index);

int YUV2H264()
{
    AVFormatContext *pFormatCtx = nullptr;
    AVOutputFormat *fmt = nullptr;
    AVStream *video_st = nullptr;
    AVCodecContext *pCodecCtx = nullptr;
    AVCodec *pCodec = nullptr;

    uint8_t *picture_buf = nullptr;
    AVFrame *picture = nullptr;
    int size;

    //打开视频文件
    FILE *in_file = fopen("111.yuv", "rb");
    if (!in_file) {
        cout << "can not open file!" << endl;
        return -1;
    }

    //352x288
    int in_w = 352, in_h = 288;
    int framenum = 50;
    const char* out_file = "111.H264";

    //[1] --注册所有ffmpeg组件
    avcodec_register_all();
    av_register_all();

    //[2] --初始化AVFormatContext结构体,根据文件名获取到合适的封装格式
    avformat_alloc_output_context2(&pFormatCtx, NULL, NULL, out_file);
    fmt = pFormatCtx->oformat;

    //[3] --打开文件
    if (avio_open(&pFormatCtx->pb, out_file, AVIO_FLAG_READ_WRITE)) {
        cout << "output file open fail!";
        return -1;
    }
    //[3]

    //[4] --初始化视频码流
    video_st = avformat_new_stream(pFormatCtx, 0);
    if (video_st == NULL)
    {
        printf("failed allocating output stram
");
        return -1;
    }
    video_st->time_base.num = 1;
    video_st->time_base.den = 25;
    //[4]

    //[5] --编码器Context设置参数
    pCodecCtx = video_st->codec;
    pCodecCtx->codec_id = fmt->video_codec;
    pCodecCtx->codec_type = AVMEDIA_TYPE_VIDEO;
    pCodecCtx->pix_fmt = AV_PIX_FMT_YUV420P;
    pCodecCtx->width = in_w;
    pCodecCtx->height = in_h;
    pCodecCtx->time_base.num = 1;
    pCodecCtx->time_base.den = 25;
    pCodecCtx->bit_rate = 400000;
    pCodecCtx->gop_size = 12;

    if (pCodecCtx->codec_id == AV_CODEC_ID_H264)
    {
        pCodecCtx->qmin = 10;
        pCodecCtx->qmax = 51;
        pCodecCtx->qcompress = 0.6;
    }
    if (pCodecCtx->codec_id == AV_CODEC_ID_MPEG2VIDEO)
        pCodecCtx->max_b_frames = 2;
    if (pCodecCtx->codec_id == AV_CODEC_ID_MPEG1VIDEO)
        pCodecCtx->mb_decision = 2;
    //[5]

    //[6] --寻找编码器并打开编码器
    pCodec = avcodec_find_encoder(pCodecCtx->codec_id);
    if (!pCodec)
    {
        cout << "no right encoder!" << endl;
        return -1;
    }
    if (avcodec_open2(pCodecCtx, pCodec, NULL) < 0)
    {
        cout << "open encoder fail!" << endl;
        return -1;
    }
    //[6]

    //输出格式信息
    av_dump_format(pFormatCtx, 0, out_file, 1);

    //初始化帧
    picture = av_frame_alloc();
    picture->width = pCodecCtx->width;
    picture->height = pCodecCtx->height;
    picture->format = pCodecCtx->pix_fmt;
    size = avpicture_get_size(pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);
    picture_buf = (uint8_t*)av_malloc(size);
    avpicture_fill((AVPicture*)picture, picture_buf, pCodecCtx->pix_fmt, pCodecCtx->width, pCodecCtx->height);

    //[7] --写头文件
    avformat_write_header(pFormatCtx, NULL);
    //[7]

    AVPacket pkt; //创建已编码帧
    int y_size = pCodecCtx->width*pCodecCtx->height;
    av_new_packet(&pkt, size * 3);

    //[8] --循环编码每一帧
    for (int i = 0; i < framenum; i++)
    {
        //读入YUV
        if (fread(picture_buf, 1, y_size * 3 / 2, in_file) < 0)
        {
            cout << "read file fail!" << endl;
            return -1;
        }
        else if (feof(in_file))
            break;

        picture->data[0] = picture_buf; //亮度Y
        picture->data[1] = picture_buf + y_size; //U
        picture->data[2] = picture_buf + y_size * 5 / 4; //V
        //AVFrame PTS
        picture->pts = i;
        int got_picture = 0;

        //编码
        int ret = avcodec_encode_video2(pCodecCtx, &pkt, picture, &got_picture);
        if (ret < 0)
        {
            cout << "encoder fail!" << endl;
            return -1;
        }

        if (got_picture == 1)
        {
            cout << "encoder success!" << endl;

            // parpare packet for muxing
            pkt.stream_index = video_st->index;
            av_packet_rescale_ts(&pkt, pCodecCtx->time_base, video_st->time_base);
            pkt.pos = -1;
            ret = av_interleaved_write_frame(pFormatCtx, &pkt);
            av_free_packet(&pkt);
        }
    }
    //[8]

    //[9] --Flush encoder
    int ret = flush_encoder(pFormatCtx, 0);
    if (ret < 0)
    {
        cout << "flushing encoder failed!" << endl;
        goto end;
    }
    //[9]

    //[10] --写文件尾
    av_write_trailer(pFormatCtx);
    //[10]

end:
    //释放内存
    if (video_st)
    {
        avcodec_close(video_st->codec);
        av_free(picture);
        av_free(picture_buf);
    }
    if (pFormatCtx)
    {
        avio_close(pFormatCtx->pb);
        avformat_free_context(pFormatCtx);
    }

    fclose(in_file);

    return 0;
}

int flush_encoder(AVFormatContext *fmt_ctx, unsigned int stream_index)
{
    int ret;
    int got_frame;
    AVPacket enc_pkt;
    if (!(fmt_ctx->streams[stream_index]->codec->codec->capabilities & AV_CODEC_CAP_DELAY))
        return 0;
    while (1) {
        printf("Flushing stream #%u encoder
", stream_index);
        enc_pkt.data = NULL;
        enc_pkt.size = 0;
        av_init_packet(&enc_pkt);
        ret = avcodec_encode_video2(fmt_ctx->streams[stream_index]->codec, &enc_pkt,
            NULL, &got_frame);
        av_frame_free(NULL);
        if (ret < 0)
            break;
        if (!got_frame)
        {
            ret = 0; break;
        }
        cout << "success encoder 1 frame" << endl;

        // parpare packet for muxing
        enc_pkt.stream_index = stream_index;
        av_packet_rescale_ts(&enc_pkt,
            fmt_ctx->streams[stream_index]->codec->time_base,
            fmt_ctx->streams[stream_index]->time_base);
        ret = av_interleaved_write_frame(fmt_ctx, &enc_pkt);
        if (ret < 0)
            break;
    }
    return ret;
}

int H2642MP4() {

    AVOutputFormat *ofmt = NULL;
    //Input AVFormatContext and Output AVFormatContext
    AVFormatContext *ifmt_ctx_v = NULL, *ifmt_ctx_a = NULL, *ofmt_ctx = NULL;
    AVPacket pkt;
    int ret, i;
    int videoindex_v = 0, videoindex_out = 0;
    int frame_index = 0;
    int64_t cur_pts_v = 0, cur_pts_a = 0;
    const char *in_filename_v = "111.H264";
    const char *out_filename = "222.mp4";//Output file URL
    av_register_all();
    //Input
    if ((ret = avformat_open_input(&ifmt_ctx_v, in_filename_v, 0, 0)) < 0) {
        printf("Could not open input file.");
        goto end;

    }
    if ((ret = avformat_find_stream_info(ifmt_ctx_v, 0)) < 0) {
        printf("Failed to retrieve input stream information");
        goto end;
    }
    
    printf("===========Input Information==========
");
    av_dump_format(ifmt_ctx_v, 0, in_filename_v, 0);
    //av_dump_format(ifmt_ctx_a, 0, in_filename_a, 0);
    printf("======================================
");
    //Output
    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
    if (!ofmt_ctx) {
        printf("Could not create output context
");
        ret = AVERROR_UNKNOWN;
        goto end;
    }
    ofmt = ofmt_ctx->oformat;
    printf("ifmt_ctx_v->nb_streams=%d
", ifmt_ctx_v->nb_streams);
    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)
        {
            AVStream *in_stream = ifmt_ctx_v->streams[i];
            AVStream *out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);
            videoindex_v = i;
            if (!out_stream) {
                printf("Failed allocating output stream
");
                ret = AVERROR_UNKNOWN;
                goto end;
            }
            videoindex_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
");
                goto end;
            }
            out_stream->codec->codec_tag = 0;
            if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
                out_stream->codec->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
            //break;
        }
    }
    
    printf("==========Output Information==========
");
    av_dump_format(ofmt_ctx, 0, out_filename, 1);
    printf("======================================
");
    //Open output file
    if (!(ofmt->flags & AVFMT_NOFILE)) {
        if (avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE) < 0) {
            printf("Could not open output file '%s'", out_filename);
            goto end;
        }
    }
    //Write file header
    if (avformat_write_header(ofmt_ctx, NULL) < 0) {
        printf("Error occurred when opening output file
");
        goto end;
    }

    while (1) {
        AVFormatContext *ifmt_ctx;
        int stream_index = 0;
        AVStream *in_stream, *out_stream;
        //Get an AVPacket
        //if(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) <= 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];
                    printf("stream_index==%d,pkt.stream_index==%d,videoindex_v=%d
", stream_index, pkt.stream_index, videoindex_v);
                    if (pkt.stream_index == videoindex_v) {
                        //FIX：No PTS (Example: Raw H.264)
                        //Simple Write PTS
                        if (pkt.pts == AV_NOPTS_VALUE) {
                            printf("frame_index==%d
", frame_index);
                            //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;
            }
        }
        
        //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	pts:%lld
", pkt.size, pkt.pts);
        //Write
        if (av_interleaved_write_frame(ofmt_ctx, &pkt) < 0) {
            printf("Error muxing packet
");
            break;
        }
        av_free_packet(&pkt);
    }
    //Write file trailer
    av_write_trailer(ofmt_ctx);

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.
");
        return -1;
    }
    return 0;
}

int main(int argc, char *argv[]) {
    // 先将YUV文件转换为H264文件
    YUV2H264();
    // 在将H264转封装为MP4
    H2642MP4();
}

总结其流程，其实就是一个编码+转封装的流程。

补充

音视频转码与转封装的区别：

音视频转码和转封装的不同之处在于音视频转码会占用大量的计算资源，而转封装主要是将音频数据或者视频数据取出，然后封装成另外一种封装格式。

转封装主要占用的IO资源，而转码主要是占用CPU资源，同时转码也会使用更多的内存资源。