ffmpeg实战将视频转换为图片

简介: ffmpeg实战将视频转换为图片

视频可以是文件或者从服务器拉取的流,流程如下:打开封装->解码->yuv->rgb->写入文件

在yuv->rgb时是用的ffmpeg的像素格式转换函数:

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


具体实现如下:

#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)++;
    }
    if (pkt->data) {
        pkt->size -= len;
        pkt->data += len;
    }
    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_RGB24,
                                     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;
}


image.png

相关文章
|
3月前
|
编解码 Linux
CentOS安装ffmpeg并转码视频为mp4
CentOS安装ffmpeg并转码视频为mp4
130 0
|
12天前
|
Java 数据安全/隐私保护
Java ffmpeg 实现视频加文字/图片水印功能
【10月更文挑战第22天】在 Java 中使用 FFmpeg 实现视频加文字或图片水印功能,需先安装 FFmpeg 并添加依赖(如 JavaCV)。通过构建 FFmpeg 命令行参数,使用 `drawtext` 滤镜添加文字水印,或使用 `overlay` 滤镜添加图片水印。示例代码展示了如何使用 JavaCV 实现文字水印。
|
5月前
|
Python
Python使用ffmpeg下载m3u8拼接为视频
Python使用ffmpeg下载m3u8拼接为视频
|
16天前
|
计算机视觉 Python
FFMPEG学习笔记(一): 提取视频的纯音频及无声视频
本文介绍了如何使用FFmpeg工具从视频中提取纯音频和无声视频。提供了具体的命令行操作,例如使用`ffmpeg -i input.mp4 -vn -c:a libmp3lame output.mp3`来提取音频,以及`ffmpeg -i input.mp4 -c:v copy -an output.mp4`来提取无声视频。此外,还包含了一个Python脚本,用于批量处理视频文件,自动提取音频和生成无声视频。
23 1
|
19天前
FFmpeg学习笔记(二):多线程rtsp推流和ffplay拉流操作,并储存为多路avi格式的视频
这篇博客主要介绍了如何使用FFmpeg进行多线程RTSP推流和ffplay拉流操作,以及如何将视频流保存为多路AVI格式的视频文件。
120 0
|
3月前
|
机器学习/深度学习 编解码 API
【机器学习】FFmpeg+Whisper:二阶段法视频理解(video-to-text)大模型实战
【机器学习】FFmpeg+Whisper:二阶段法视频理解(video-to-text)大模型实战
46 0
|
5月前
|
存储 编解码 Linux
rodert教你学FFmpeg实战这一篇就够了 - 音视频处理入门篇
rodert教你学FFmpeg实战这一篇就够了 - 音视频处理入门篇
61 1
|
5月前
|
Linux 开发工具
Linux下视频截取命令 使用【ffmpeg】使用
Linux下视频截取命令 使用【ffmpeg】使用
46 1
|
9天前
|
Linux 开发工具 Android开发
FFmpeg开发笔记(六十)使用国产的ijkplayer播放器观看网络视频
ijkplayer是由Bilibili基于FFmpeg3.4研发并开源的播放器,适用于Android和iOS,支持本地视频及网络流媒体播放。本文详细介绍如何在新版Android Studio中导入并使用ijkplayer库,包括Gradle版本及配置更新、导入编译好的so文件以及添加直播链接播放代码等步骤,帮助开发者顺利进行App调试与开发。更多FFmpeg开发知识可参考《FFmpeg开发实战:从零基础到短视频上线》。
52 2
FFmpeg开发笔记(六十)使用国产的ijkplayer播放器观看网络视频
|
16天前
|
编解码 语音技术 内存技术
FFmpeg开发笔记(五十八)把32位采样的MP3转换为16位的PCM音频
《FFmpeg开发实战:从零基础到短视频上线》一书中的“5.1.2 把音频流保存为PCM文件”章节介绍了将媒体文件中的音频流转换为原始PCM音频的方法。示例代码直接保存解码后的PCM数据,保留了原始音频的采样频率、声道数量和采样位数。但在实际应用中,有时需要特定规格的PCM音频。例如,某些语音识别引擎仅接受16位PCM数据,而标准MP3音频通常采用32位采样,因此需将32位MP3音频转换为16位PCM音频。
36 0
FFmpeg开发笔记(五十八)把32位采样的MP3转换为16位的PCM音频

热门文章

最新文章