【FFmpeg】音视频编解码

于 2021-02-28 20:09:44 发布
阅读量205 收藏
点赞数
分类专栏： 音视频 文章标签： ffmpeg 音视频 编解码
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_30885821/article/details/114224375
版权

FFmpeg 常识

常用数据结构：

  • AVCodex 编码器结构体
  • AVCodexContext编码器上下文
  • AVFrame解码后的帧

结构体的分配与释放：

av_frame_alloc()  /  av_frame_free()
avcodex_alloc_context3() / avcodec_free_context()

FFmpeg H264解码

解码步骤：
查找解码器：avcodec_find_decoder（通过ID找到解码器）
打开解码器：avcodec_open2
解码：avcodec_decode_video2

将视频解析成图片：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <libavformat/avformat.h>
#include <libavcodec/avcodec.h>
#include <libswscale/swscale.h>

#define INBUF_SIZE 4096

#define WORD uint16_t
#define DWORD uint32_t
#define LONG int32_t

#pragma pack(2)
typedef struct tagBITMAPFILEHEADER {
  WORD  bfType;
  DWORD bfSize;
  WORD  bfReserved1;
  WORD  bfReserved2;
  DWORD bfOffBits;
} BITMAPFILEHEADER, *PBITMAPFILEHEADER;


typedef struct tagBITMAPINFOHEADER {
  DWORD biSize;
  LONG  biWidth;
  LONG  biHeight;
  WORD  biPlanes;
  WORD  biBitCount;
  DWORD biCompression;
  DWORD biSizeImage;
  LONG  biXPelsPerMeter;
  LONG  biYPelsPerMeter;
  DWORD biClrUsed;
  DWORD biClrImportant;
} BITMAPINFOHEADER, *PBITMAPINFOHEADER;

void saveBMP(struct SwsContext *img_convert_ctx, AVFrame *frame, char *filename)
{
    //1 先进行转换,  YUV420=>RGB24:
    int w = frame->width;
    int h = frame->height;


    int numBytes=avpicture_get_size(AV_PIX_FMT_BGR24, w, h);
    uint8_t *buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));


    AVFrame *pFrameRGB = av_frame_alloc();
     /* buffer is going to be written to rawvideo file, no alignment */
    /*
    if (av_image_alloc(pFrameRGB->data, pFrameRGB->linesize,
                              w, h, AV_PIX_FMT_BGR24, pix_fmt, 1) < 0) {
        fprintf(stderr, "Could not allocate destination image\n");
        exit(1);
    }
    */
    avpicture_fill((AVPicture *)pFrameRGB, buffer, AV_PIX_FMT_BGR24, w, h);

    sws_scale(img_convert_ctx, frame->data, frame->linesize,
              0, h, pFrameRGB->data, pFrameRGB->linesize);

    //2 构造 BITMAPINFOHEADER
    BITMAPINFOHEADER header;
    header.biSize = sizeof(BITMAPINFOHEADER);


    header.biWidth = w;
    header.biHeight = h*(-1);
    header.biBitCount = 24;
    header.biCompression = 0;
    header.biSizeImage = 0;
    header.biClrImportant = 0;
    header.biClrUsed = 0;
    header.biXPelsPerMeter = 0;
    header.biYPelsPerMeter = 0;
    header.biPlanes = 1;

    //3 构造文件头
    BITMAPFILEHEADER bmpFileHeader = {0,};
    //HANDLE hFile = NULL;
    DWORD dwTotalWriten = 0;
    DWORD dwWriten;

    bmpFileHeader.bfType = 0x4d42; //'BM';
    bmpFileHeader.bfSize = sizeof(BITMAPFILEHEADER) + sizeof(BITMAPINFOHEADER)+ numBytes;
    bmpFileHeader.bfOffBits=sizeof(BITMAPFILEHEADER)+sizeof(BITMAPINFOHEADER);

    FILE* pf = fopen(filename, "wb");
    fwrite(&bmpFileHeader, sizeof(BITMAPFILEHEADER), 1, pf);
    fwrite(&header, sizeof(BITMAPINFOHEADER), 1, pf);
    fwrite(pFrameRGB->data[0], 1, numBytes, pf);
    fclose(pf);


    //释放资源
    //av_free(buffer);
    av_freep(&pFrameRGB[0]);
    av_free(pFrameRGB);
}

static void pgm_save(unsigned char *buf, int wrap, int xsize, int ysize,
                     char *filename)
{
    FILE *f;
    int i;

    f = fopen(filename,"w");
    fprintf(f, "P5\n%d %d\n%d\n", xsize, ysize, 255);
    for (i = 0; i < ysize; i++)
        fwrite(buf + i * wrap, 1, xsize, f);
    fclose(f);
}

static int decode_write_frame(const char *outfilename, AVCodecContext *avctx,
                              struct SwsContext *img_convert_ctx, AVFrame *frame, int *frame_count, AVPacket *pkt, int last)
{
    int len, got_frame;
    char buf[1024];

    len = avcodec_decode_video2(avctx, frame, &got_frame, pkt);
    if (len < 0) {
        fprintf(stderr, "Error while decoding frame %d\n", *frame_count);
        return len;
    }
    if (got_frame) {
        printf("Saving %sframe %3d\n", last ? "last " : "", *frame_count);
        fflush(stdout);

        /* the picture is allocated by the decoder, no need to free it */
        snprintf(buf, sizeof(buf), "%s-%d.bmp", outfilename, *frame_count);
        
        /*
        pgm_save(frame->data[0], frame->linesize[0],
                 frame->width, frame->height, buf);
        */
        
        saveBMP(img_convert_ctx, frame, buf);
        
        (*frame_count)++;
    }
    return 0;
}

int main(int argc, char **argv)
{
    int ret;

    FILE *f;

    const char *filename, *outfilename;

    AVFormatContext *fmt_ctx = NULL;

    const AVCodec *codec;
    AVCodecContext *c= NULL;

    AVStream *st = NULL;
    int stream_index;

    int frame_count;
    AVFrame *frame;

    struct SwsContext *img_convert_ctx;

    //uint8_t inbuf[INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE];
    AVPacket avpkt;

    if (argc <= 2) {
        fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
        exit(0);
    }
    filename    = argv[1];
    outfilename = argv[2];

    /* register all formats and codecs */
    av_register_all();

    /* open input file, and allocate format context */
    if (avformat_open_input(&fmt_ctx, filename, NULL, NULL) < 0) {
        fprintf(stderr, "Could not open source file %s\n", filename);
        exit(1);
    }

    /* retrieve stream information */
    if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
        fprintf(stderr, "Could not find stream information\n");
        exit(1);
    }

    /* dump input information to stderr */
    av_dump_format(fmt_ctx, 0, filename, 0);

    av_init_packet(&avpkt);

    /* set end of buffer to 0 (this ensures that no overreading happens for damaged MPEG streams) */
    //memset(inbuf + INBUF_SIZE, 0, AV_INPUT_BUFFER_PADDING_SIZE);
    //

    ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not find %s stream in input file '%s'\n",
                av_get_media_type_string(AVMEDIA_TYPE_VIDEO), filename);
        return ret;
    }

    stream_index = ret;
    st = fmt_ctx->streams[stream_index];

    /* find decoder for the stream */
    codec = avcodec_find_decoder(st->codecpar->codec_id);
    if (!codec) {
        fprintf(stderr, "Failed to find %s codec\n",
                av_get_media_type_string(AVMEDIA_TYPE_VIDEO));
        return AVERROR(EINVAL);
    }


    /* find the MPEG-1 video decoder */
    /*
    codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO);
    if (!codec) {
        fprintf(stderr, "Codec not found\n");
        exit(1);
    }
    */

    c = avcodec_alloc_context3(NULL);
    if (!c) {
        fprintf(stderr, "Could not allocate video codec context\n");
        exit(1);
    }

    /* Copy codec parameters from input stream to output codec context */
    if ((ret = avcodec_parameters_to_context(c, st->codecpar)) < 0) {
        fprintf(stderr, "Failed to copy %s codec parameters to decoder context\n",
                av_get_media_type_string(AVMEDIA_TYPE_VIDEO));
        return ret;
    }


    /*
    if (codec->capabilities & AV_CODEC_CAP_TRUNCATED)
        c->flags |= AV_CODEC_FLAG_TRUNCATED; // we do not send complete frames
    */

    /* For some codecs, such as msmpeg4 and mpeg4, width and height
       MUST be initialized there because this information is not
       available in the bitstream. */

    /* open it */
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open codec\n");
        exit(1);
    }

    /*
    f = fopen(filename, "rb");
    if (!f) {
        fprintf(stderr, "Could not open %s\n", filename);
        exit(1);
    }
    */

    img_convert_ctx = sws_getContext(c->width, c->height,
                                     c->pix_fmt,
                                     c->width, c->height,
                                     AV_PIX_FMT_BGR24,
                                     SWS_BICUBIC, NULL, NULL, NULL);

    if (img_convert_ctx == NULL)
    {
        fprintf(stderr, "Cannot initialize the conversion context\n");
        exit(1);
    }

    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate video frame\n");
        exit(1);
    }

    frame_count = 0;
    while (av_read_frame(fmt_ctx, &avpkt) >= 0) {
        /*
        avpkt.size = fread(inbuf, 1, INBUF_SIZE, f);
        if (avpkt.size == 0)
            break;
        */

        /* NOTE1: some codecs are stream based (mpegvideo, mpegaudio)
           and this is the only method to use them because you cannot
           know the compressed data size before analysing it.

           BUT some other codecs (msmpeg4, mpeg4) are inherently frame
           based, so you must call them with all the data for one
           frame exactly. You must also initialize 'width' and
           'height' before initializing them. */

        /* NOTE2: some codecs allow the raw parameters (frame size,
           sample rate) to be changed at any frame. We handle this, so
           you should also take care of it */

        /* here, we use a stream based decoder (mpeg1video), so we
           feed decoder and see if it could decode a frame */
        //avpkt.data = inbuf;
        //while (avpkt.size > 0)
        if(avpkt.stream_index == stream_index){
            if (decode_write_frame(outfilename, c, img_convert_ctx, frame, &frame_count, &avpkt, 0) < 0)
                exit(1);
        }

        av_packet_unref(&avpkt);
    }

    /* Some codecs, such as MPEG, transmit the I- and P-frame with a
       latency of one frame. You must do the following to have a
       chance to get the last frame of the video. */
    avpkt.data = NULL;
    avpkt.size = 0;
    decode_write_frame(outfilename, c, img_convert_ctx, frame, &frame_count, &avpkt, 1);

    fclose(f);

    avformat_close_input(&fmt_ctx);

    sws_freeContext(img_convert_ctx);
    avcodec_free_context(&c);
    av_frame_free(&frame);

    return 0;
}

编译运行：

clang -g -o decode_video decode_video.c `pkg-config --cflags --libs libavformat libavcodec libavutil libswscale`

./decode_video test.mp4 ./video_2_picture

FFmpeg H264编码

编码步骤：
查找解码器：avcodec_find_encoder_by_name（通过名称找到编码器）
设置编码参数，打开编码器：avcodec_open2
编码：avcodec_encode_video2

下面利用编码器生成1秒的一个视频：

#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<libavcodec/avcodec.h>
#include<libavutil/opt.h>
#include<libavutil/imgutils.h>

int main(int argc, char **argv){
	const char *filename, *codec_name;
	const AVCodec *codec;
	AVCodecContext *c = NULL;
	int i, ret, x, y, got_output;
	FILE *f;
	AVFrame *frame;
	AVPacket pkt;
	uint8_t endcode[] = {0, 0, 1, 0xb7};
	
	if(argc <= 2){
		fprintf(stderr, "Usage:%s <output file> <codec name>\n", argv[0]);
		exit(0);
	}
	
	filename = argv[1];
	codec_name = argv[2];
	avcodec_register_all();
	
	/*find the mpeg1video encoder*/
	codec = avcodec_find_encoder_by_name(codec_name);
	if(!codec){
		fprintf(stderr, "Codec not found\n");
		exit(1);
	}
	
	c = avcodec_alloc_context3(codec);
	if(!c){
		fprintf(stderr, "Could not allocate video codec context\n");
		exit(1);
	}

	/*put sample parameters*/
	c->bit_rate = 400000;
	/*resolution must be a multiple of two*/
	c->width = 352;
	c->height = 288;
	/*frames per second*/
	c->time_base = (AVRational){1, 25};
	c->framerate = (AVRational){25, 1};

	/*	一组帧的数量，多少帧产生一个关键帧
		gop_size越大，压缩率高，便于传输；越小，丢失关键帧后恢复越快
		
		使用b帧，前后参考
	*/
	c->gop_size = 10;
	c->max_b_frames = 1;
	c->pix_fmt = AV_PIX_FMT_YUV420P;
	
	if(codec->id == AV_CODEC_ID_H264){
		av_opt_set(c->priv_data, "preset", "slow", 0);// 提前设置好的参数集，压缩速度慢，能保证视频质量
	}

	/*open it*/
	if(avcodec_open2(c, codec, NULL) < 0){
		fprintf(stderr, "Could not open codec\n");
		exit(1);
	}
	
	f = fopen(filename, "wb");
	if(!f){
		fprintf(stderr, "Could not open %s\n", filename);
		exit(1);
	}
	
	frame = av_frame_alloc();
	if(!frame){
		fprintf(stderr, "Could not allocate video frame\n");
		exit(1);
	}
	
	frame->format = c->pix_fmt;
    frame->width  = c->width;
    frame->height = c->height;

    ret = av_frame_get_buffer(frame, 32);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate the video frame data\n");
        exit(1);
    }

    /* encode 1 second of video */
    for (i = 0; i < 25; i++) {
        av_init_packet(&pkt);
        pkt.data = NULL;    // packet data will be allocated by the encoder
        pkt.size = 0;

        fflush(stdout);

        /* make sure the frame data is writable */
        ret = av_frame_make_writable(frame);
        if (ret < 0)
            exit(1);

        /* prepare a dummy image */
        /* Y */
        for (y = 0; y < c->height; y++) {
            for (x = 0; x < c->width; x++) {
                frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3;
            }
        }

        /* Cb and Cr */
        for (y = 0; y < c->height/2; y++) {
            for (x = 0; x < c->width/2; x++) {
                frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2;
                frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5;
            }
        }

        frame->pts = i;

        /* encode the image */
        ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
        if (ret < 0) {
            fprintf(stderr, "Error encoding frame\n");
            exit(1);
        }

        if (got_output) {
            printf("Write frame %3d (size=%5d)\n", i, pkt.size);
            fwrite(pkt.data, 1, pkt.size, f);
            av_packet_unref(&pkt);
        }
    }

    /* get the delayed frames */
    for (got_output = 1; got_output; i++) {
        fflush(stdout);

        ret = avcodec_encode_video2(c, &pkt, NULL, &got_output);
        if (ret < 0) {
            fprintf(stderr, "Error encoding frame\n");
            exit(1);
        }

        if (got_output) {
            printf("Write frame %3d (size=%5d)\n", i, pkt.size);
            fwrite(pkt.data, 1, pkt.size, f);
            av_packet_unref(&pkt);
        }
    }

    /* add sequence end code to have a real MPEG file */
    fwrite(endcode, 1, sizeof(endcode), f);
    fclose(f);

    avcodec_free_context(&c);
    av_frame_free(&frame);

    return 0;
}

编译运行：

clang -g -o encode_video encode_video.c `pkg-config --cflags --libs libavcodec`
./encode_video 1.h264 libx264
ffplay 1.h264

FFmpeg AAC编码

编码流程与视频相同

编码函数 avcodec_encodec_audio2

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>

#include <libavcodec/avcodec.h>

#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/frame.h>
#include <libavutil/samplefmt.h>

/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec, enum AVSampleFormat sample_fmt)
{
    const enum AVSampleFormat *p = codec->sample_fmts;

    while (*p != AV_SAMPLE_FMT_NONE) {
        if (*p == sample_fmt)
            return 1;
        p++;
    }
    return 0;
}

/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec)
{
    const int *p;
    int best_samplerate = 0;

    if (!codec->supported_samplerates)
        return 44100;

    p = codec->supported_samplerates;
    while (*p) {
        if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
            best_samplerate = *p;
        p++;
    }
    return best_samplerate;
}

/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec)
{
    const uint64_t *p;
    uint64_t best_ch_layout = 0;
    int best_nb_channels   = 0;

    if (!codec->channel_layouts)
        return AV_CH_LAYOUT_STEREO;

    p = codec->channel_layouts;
    while (*p) {
        int nb_channels = av_get_channel_layout_nb_channels(*p);

        if (nb_channels > best_nb_channels) {
            best_ch_layout    = *p;
            best_nb_channels = nb_channels;
        }
        p++;
    }
    return best_ch_layout;
}

int main(int argc, char **argv)
{
    const char *filename;
    const AVCodec *codec;
    AVCodecContext *c= NULL;
    AVFrame *frame;
    AVPacket pkt;
    int i, j, k, ret, got_output;
    FILE *f;
    uint16_t *samples;
    float t, tincr;

    if (argc <= 1) {
        fprintf(stderr, "Usage: %s <output file>\n", argv[0]);
        return 0;
    }
    filename = argv[1];

    /* register all the codecs */
    avcodec_register_all();

    /* find the MP2 encoder */
    codec = avcodec_find_encoder(AV_CODEC_ID_MP2);
    if (!codec) {
        fprintf(stderr, "Codec not found\n");
        exit(1);
    }

    c = avcodec_alloc_context3(codec);
    if (!c) {
        fprintf(stderr, "Could not allocate audio codec context\n");
        exit(1);
    }

    /* put sample parameters */
    c->bit_rate = 64000;

    /* check that the encoder supports s16 pcm input */
    c->sample_fmt = AV_SAMPLE_FMT_S16;
    if (!check_sample_fmt(codec, c->sample_fmt)) {
        fprintf(stderr, "Encoder does not support sample format %s",
                av_get_sample_fmt_name(c->sample_fmt));
        exit(1);
    }

    /* select other audio parameters supported by the encoder */
    c->sample_rate    = select_sample_rate(codec);
    c->channel_layout = select_channel_layout(codec);
    c->channels       = av_get_channel_layout_nb_channels(c->channel_layout);

    /* open it */
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open codec\n");
        exit(1);
    }

    f = fopen(filename, "wb");
    if (!f) {
        fprintf(stderr, "Could not open %s\n", filename);
        exit(1);
    }

    /* frame containing input raw audio */
    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate audio frame\n");
        exit(1);
    }

    frame->nb_samples     = c->frame_size;
    frame->format         = c->sample_fmt;
    frame->channel_layout = c->channel_layout;

    /* allocate the data buffers */
    ret = av_frame_get_buffer(frame, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate audio data buffers\n");
        exit(1);
    }

    /* encode a single tone sound */
    t = 0;
    tincr = 2 * M_PI * 440.0 / c->sample_rate;
    for (i = 0; i < 200; i++) {
        av_init_packet(&pkt);
        pkt.data = NULL; // packet data will be allocated by the encoder
        pkt.size = 0;

        /* make sure the frame is writable -- makes a copy if the encoder
         * kept a reference internally */
        ret = av_frame_make_writable(frame);
        if (ret < 0)
            exit(1);
        samples = (uint16_t*)frame->data[0];

        for (j = 0; j < c->frame_size; j++) {
            samples[2*j] = (int)(sin(t) * 10000);

            for (k = 1; k < c->channels; k++)
                samples[2*j + k] = samples[2*j];
            t += tincr;
        }
        /* encode the samples */
        ret = avcodec_encode_audio2(c, &pkt, frame, &got_output);
        if (ret < 0) {
            fprintf(stderr, "Error encoding audio frame\n");
            exit(1);
        }
        if (got_output) {
            fwrite(pkt.data, 1, pkt.size, f);
            av_packet_unref(&pkt);
        }
    }

    /* get the delayed frames */
    for (got_output = 1; got_output; i++) {
        ret = avcodec_encode_audio2(c, &pkt, NULL, &got_output);
        if (ret < 0) {
            fprintf(stderr, "Error encoding frame\n");
            exit(1);
        }

        if (got_output) {
            fwrite(pkt.data, 1, pkt.size, f);
            av_packet_unref(&pkt);
        }
    }
    fclose(f);

    av_frame_free(&frame);
    avcodec_free_context(&c);

    return 0;
}

编译运行：

clang -g -o encode_audio encode_audio.c `pkg-config --cflags --libs libavcodec`
./encode_audio 1.aac
ffplay 1.aac
ScriptGirl
关注
专栏目录
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值