FFmpeg開發實戰（六）：使用 FFmpeg 將YUV數據編碼為視頻文件

本文中實現的一個小功能是把一個YUV原始視頻數據(時間序列圖像)經過h264編碼為視頻碼流，然后在使用mp4封裝格式封裝。

編碼&封裝的流程圖如下：

 

使用ffmpeg編碼流程：

1、首先使用av_register_all()函數注冊所有的編碼器和復用器(理解為格式封裝器)。該步驟必須放在所有ffmpeg代碼前第一個執行

2、avformat_alloc_output_context2()：初始化包含有輸出碼流(AVStream)和解復用器(AVInputFormat)的AVFormatContext

3、avio_open( )打開輸出文件

4、av_new_stream() 創建視頻碼流 該函數生成一個空AVstream 該結構存放編碼后的視頻碼流 。視頻碼流被拆分為AVPacket新式保存在AVStream中。

5、設置編碼器信息，該步驟主要是為AVCodecContext(從AVStream->codec 獲取指針)結構體設置一些參數，包括codec_id、codec_type、width、height、pix_fmt .....  根據編碼器的不同，還要額外設置一些參數(如 h264 要設置qmax、qmin、qcompress參數才能正常使用h264編碼)

6、查找並打開編碼器，根據前一步設置的編碼器參數信息，來查找初始化一個編碼其，並將其打開。用到函數為av_fine_encoder()和av_open2()。

7、寫頭文件  avformat_write_header()。這一步主要是將封裝格式的信息寫入文件頭部位置。

8、編碼幀。用到的函數 avcodec_encode_video2() 將AVFrame編碼為AVPacket

9、在寫入文件之前 還需要做一件事情就是設置AVPacket一些信息。這些信息關乎最后封裝格式能否被正確讀取。后面回詳細講述該部分內容

10、編碼幀寫入文件 av_write_frame()

11、flush_encoder()：輸入的像素數據讀取完成后調用此函數。用於輸出編碼器中剩余的AVPacket。

12、av_write_trailer()：寫文件尾（對於某些沒有文件頭的封裝格式，不需要此函數。比如說MPEG2TS）。

源碼：

#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;

    //打開視頻文件
    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] --注冊所有ffmpeg組件
    avcodec_register_all();
    av_register_all();

    //[2] --初始化AVFormatContext結構體,根據文件名獲取到合適的封裝格式
    avformat_alloc_output_context2(&pFormatCtx, NULL, NULL, out_file);
    fmt = pFormatCtx->oformat;

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

    //[4] --初始化視頻碼流
    video_st = avformat_new_stream(pFormatCtx, 0);
    if (video_st == NULL)
    {
        printf("failed allocating output stram\n");
        return -1;
    }
    video_st->time_base.num = 1;
    video_st->time_base.den = 25;
    //[4]

    //[5] --編碼器Context設置參數
    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] --尋找編碼器並打開編碼器
    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]

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

    //初始化幀
    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] --寫頭文件
    avformat_write_header(pFormatCtx, NULL);
    //[7]

    AVPacket pkt; //創建已編碼幀
    int y_size = pCodecCtx->width*pCodecCtx->height;
    av_new_packet(&pkt, size * 3);

    //[8] --循環編碼每一幀
    for (int i = 0; i < framenum; i++)
    {
        //讀入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;

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

end:
    //釋放內存
    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\n", 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==========\n");
    av_dump_format(ifmt_ctx_v, 0, in_filename_v, 0);
    //av_dump_format(ifmt_ctx_a, 0, in_filename_a, 0);
    printf("======================================\n");
    //Output
    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
    if (!ofmt_ctx) {
        printf("Could not create output context\n");
        ret = AVERROR_UNKNOWN;
        goto end;
    }
    ofmt = ofmt_ctx->oformat;
    printf("ifmt_ctx_v->nb_streams=%d\n", 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\n");
                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\n");
                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==========\n");
    av_dump_format(ofmt_ctx, 0, out_filename, 1);
    printf("======================================\n");
    //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\n");
        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\n", 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\n", 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\tpts:%lld\n", pkt.size, pkt.pts);
        //Write
        if (av_interleaved_write_frame(ofmt_ctx, &pkt) < 0) {
            printf("Error muxing packet\n");
            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.\n");
        return -1;
    }
    return 0;
}

int main(int argc, char *argv[]) {
    // 先將YUV文件轉換為H264文件
    YUV2H264();
    // 在將H264轉封裝為MP4
    H2642MP4();
}

 

總結其流程，其實就是一個編碼+轉封裝的流程。

 

補充

音視頻轉碼與轉封裝的區別：

音視頻轉碼和轉封裝的不同之處在於音視頻轉碼會占用大量的計算資源，而轉封裝主要是將音頻數據或者視頻數據取出，然后封裝成另外一種封裝格式。

轉封裝主要占用的IO資源，而轉碼主要是占用CPU資源，同時轉碼也會使用更多的內存資源。