如何使用 ffmpeg 库从视频中提取灰度图像?
How to extract grayscale image from a video with ffmpeg-library?
我编译并测试了这个 tutorial from here which works just fine. After I tried to edit the tutorial to read/convert frames into grayscale。我只是将 pFrameRGB
更改为 pFrameGray
,将 PIX_FMT_RGB24
更改为 PIX_FMT_GRAY16
并仅保存第 200 帧。它编译并 运行 但图像未显示预期。怎么了?
图片:
修改后的代码:
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <stdio.h>
// compatibility with newer API
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#define av_frame_free avcodec_free_frame
#endif
void SaveFrame(AVFrame *pFrame, int width, int height, int iFrame) {
FILE *pFile;
char szFilename[32];
int y;
// Open file
sprintf(szFilename, "frame%d.ppm", iFrame);
pFile=fopen(szFilename, "wb");
if(pFile==NULL)
return;
// Write header
fprintf(pFile, "P6\n%d %d\n255\n", width, height);
// Write pixel data
for(y=0; y<height; y++)
fwrite(pFrame->data[0]+y*pFrame->linesize[0], 1, width*3, pFile);
// Close file
fclose(pFile);
}
int main(int argc, char *argv[]) {
// Initalizing these to NULL prevents segfaults!
AVFormatContext *pFormatCtx = NULL;
int i, videoStream;
AVCodecContext *pCodecCtxOrig = NULL;
AVCodecContext *pCodecCtx = NULL;
AVCodec *pCodec = NULL;
AVFrame *pFrame = NULL;
AVFrame *pFrameGRAY = NULL;
AVPacket packet;
int frameFinished;
int numBytes;
uint8_t *buffer = NULL;
struct SwsContext *sws_ctx = NULL;
if(argc < 2) {
printf("Please provide a movie file\n");
return -1;
}
// Register all formats and codecs
av_register_all();
// Open video file
if(avformat_open_input(&pFormatCtx, argv[1], NULL, NULL)!=0)
return -1; // Couldn't open file
// Retrieve stream information
if(avformat_find_stream_info(pFormatCtx, NULL)<0)
return -1; // Couldn't find stream information
// Dump information about file onto standard error
av_dump_format(pFormatCtx, 0, argv[1], 0);
// Find the first video stream
videoStream=-1;
for(i=0; i<pFormatCtx->nb_streams; i++)
if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_VIDEO) {
videoStream=i;
break;
}
if(videoStream==-1)
return -1; // Didn't find a video stream
// Get a pointer to the codec context for the video stream
pCodecCtxOrig=pFormatCtx->streams[videoStream]->codec;
// Find the decoder for the video stream
pCodec=avcodec_find_decoder(pCodecCtxOrig->codec_id);
if(pCodec==NULL) {
fprintf(stderr, "Unsupported codec!\n");
return -1; // Codec not found
}
// Copy context
pCodecCtx = avcodec_alloc_context3(pCodec);
if(avcodec_copy_context(pCodecCtx, pCodecCtxOrig) != 0) {
fprintf(stderr, "Couldn't copy codec context");
return -1; // Error copying codec context
}
// Open codec
if(avcodec_open2(pCodecCtx, pCodec, NULL)<0)
return -1; // Could not open codec
// Allocate video frame
pFrame=av_frame_alloc();
// Allocate an AVFrame structure
pFrameGRAY=av_frame_alloc();
if(pFrameGRAY==NULL)
return -1;
// Determine required buffer size and allocate buffer
numBytes=avpicture_get_size(PIX_FMT_GRAY16, pCodecCtx->width,
pCodecCtx->height);
buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));
// Assign appropriate parts of buffer to image planes in pFrameGRAY
// Note that pFrameGRAY is an AVFrame, but AVFrame is a superset
// of AVPicture
avpicture_fill((AVPicture *)pFrameGRAY, buffer, PIX_FMT_GRAY16,
pCodecCtx->width, pCodecCtx->height);
// initialize SWS context for software scaling
sws_ctx = sws_getContext(pCodecCtx->width,
pCodecCtx->height,
pCodecCtx->pix_fmt,
pCodecCtx->width,
pCodecCtx->height,
PIX_FMT_GRAY16,
SWS_BILINEAR,
NULL,
NULL,
NULL
);
// Read frames and save first five frames to disk
i=0;
while(av_read_frame(pFormatCtx, &packet)>=0) {
// Is this a packet from the video stream?
if(packet.stream_index==videoStream) {
// Decode video frame
avcodec_decode_video2(pCodecCtx, pFrame, &frameFinished, &packet);
// Did we get a video frame?
if(frameFinished) {
// Convert the image from its native format to GRAY
sws_scale(sws_ctx, (uint8_t const * const *)pFrame->data,
pFrame->linesize, 0, pCodecCtx->height,
pFrameGRAY->data, pFrameGRAY->linesize);
// Save the frame to disk
if(++i==200)
SaveFrame(pFrameGRAY, pCodecCtx->width, pCodecCtx->height,
i);
}
}
// Free the packet that was allocated by av_read_frame
av_free_packet(&packet);
}
// Free the GRAY image
av_free(buffer);
av_frame_free(&pFrameGRAY);
// Free the YUV frame
av_frame_free(&pFrame);
// Close the codecs
avcodec_close(pCodecCtx);
avcodec_close(pCodecCtxOrig);
// Close the video file
avformat_close_input(&pFormatCtx);
return 0;
}
你的主要问题在这里:
fprintf(pFile, "P6\n%d %d\n255\n", width, height);
根据关于 PPM 的一些信息,我发现:http://paulbourke.net/dataformats/ppm/ 您正在使用标识符 P6
编写 PPM header,这意味着 "rgb color"。如果您正在制作灰度图像,则需要使用 P5
。
此外,您使用的是 ffmpeg 的像素格式 PIX_FMT_GRAY16
,但您将其解释为字节。您可能打算改用 PIX_FMT_GRAY8
。如果您确实想要在输出中使用 16 位灰度,则应将 PPM header 中的第三个数字从 255 更改为 65535。
我编译并测试了这个 tutorial from here which works just fine. After I tried to edit the tutorial to read/convert frames into grayscale。我只是将 pFrameRGB
更改为 pFrameGray
,将 PIX_FMT_RGB24
更改为 PIX_FMT_GRAY16
并仅保存第 200 帧。它编译并 运行 但图像未显示预期。怎么了?
图片:
修改后的代码:
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <stdio.h>
// compatibility with newer API
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#define av_frame_free avcodec_free_frame
#endif
void SaveFrame(AVFrame *pFrame, int width, int height, int iFrame) {
FILE *pFile;
char szFilename[32];
int y;
// Open file
sprintf(szFilename, "frame%d.ppm", iFrame);
pFile=fopen(szFilename, "wb");
if(pFile==NULL)
return;
// Write header
fprintf(pFile, "P6\n%d %d\n255\n", width, height);
// Write pixel data
for(y=0; y<height; y++)
fwrite(pFrame->data[0]+y*pFrame->linesize[0], 1, width*3, pFile);
// Close file
fclose(pFile);
}
int main(int argc, char *argv[]) {
// Initalizing these to NULL prevents segfaults!
AVFormatContext *pFormatCtx = NULL;
int i, videoStream;
AVCodecContext *pCodecCtxOrig = NULL;
AVCodecContext *pCodecCtx = NULL;
AVCodec *pCodec = NULL;
AVFrame *pFrame = NULL;
AVFrame *pFrameGRAY = NULL;
AVPacket packet;
int frameFinished;
int numBytes;
uint8_t *buffer = NULL;
struct SwsContext *sws_ctx = NULL;
if(argc < 2) {
printf("Please provide a movie file\n");
return -1;
}
// Register all formats and codecs
av_register_all();
// Open video file
if(avformat_open_input(&pFormatCtx, argv[1], NULL, NULL)!=0)
return -1; // Couldn't open file
// Retrieve stream information
if(avformat_find_stream_info(pFormatCtx, NULL)<0)
return -1; // Couldn't find stream information
// Dump information about file onto standard error
av_dump_format(pFormatCtx, 0, argv[1], 0);
// Find the first video stream
videoStream=-1;
for(i=0; i<pFormatCtx->nb_streams; i++)
if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_VIDEO) {
videoStream=i;
break;
}
if(videoStream==-1)
return -1; // Didn't find a video stream
// Get a pointer to the codec context for the video stream
pCodecCtxOrig=pFormatCtx->streams[videoStream]->codec;
// Find the decoder for the video stream
pCodec=avcodec_find_decoder(pCodecCtxOrig->codec_id);
if(pCodec==NULL) {
fprintf(stderr, "Unsupported codec!\n");
return -1; // Codec not found
}
// Copy context
pCodecCtx = avcodec_alloc_context3(pCodec);
if(avcodec_copy_context(pCodecCtx, pCodecCtxOrig) != 0) {
fprintf(stderr, "Couldn't copy codec context");
return -1; // Error copying codec context
}
// Open codec
if(avcodec_open2(pCodecCtx, pCodec, NULL)<0)
return -1; // Could not open codec
// Allocate video frame
pFrame=av_frame_alloc();
// Allocate an AVFrame structure
pFrameGRAY=av_frame_alloc();
if(pFrameGRAY==NULL)
return -1;
// Determine required buffer size and allocate buffer
numBytes=avpicture_get_size(PIX_FMT_GRAY16, pCodecCtx->width,
pCodecCtx->height);
buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));
// Assign appropriate parts of buffer to image planes in pFrameGRAY
// Note that pFrameGRAY is an AVFrame, but AVFrame is a superset
// of AVPicture
avpicture_fill((AVPicture *)pFrameGRAY, buffer, PIX_FMT_GRAY16,
pCodecCtx->width, pCodecCtx->height);
// initialize SWS context for software scaling
sws_ctx = sws_getContext(pCodecCtx->width,
pCodecCtx->height,
pCodecCtx->pix_fmt,
pCodecCtx->width,
pCodecCtx->height,
PIX_FMT_GRAY16,
SWS_BILINEAR,
NULL,
NULL,
NULL
);
// Read frames and save first five frames to disk
i=0;
while(av_read_frame(pFormatCtx, &packet)>=0) {
// Is this a packet from the video stream?
if(packet.stream_index==videoStream) {
// Decode video frame
avcodec_decode_video2(pCodecCtx, pFrame, &frameFinished, &packet);
// Did we get a video frame?
if(frameFinished) {
// Convert the image from its native format to GRAY
sws_scale(sws_ctx, (uint8_t const * const *)pFrame->data,
pFrame->linesize, 0, pCodecCtx->height,
pFrameGRAY->data, pFrameGRAY->linesize);
// Save the frame to disk
if(++i==200)
SaveFrame(pFrameGRAY, pCodecCtx->width, pCodecCtx->height,
i);
}
}
// Free the packet that was allocated by av_read_frame
av_free_packet(&packet);
}
// Free the GRAY image
av_free(buffer);
av_frame_free(&pFrameGRAY);
// Free the YUV frame
av_frame_free(&pFrame);
// Close the codecs
avcodec_close(pCodecCtx);
avcodec_close(pCodecCtxOrig);
// Close the video file
avformat_close_input(&pFormatCtx);
return 0;
}
你的主要问题在这里:
fprintf(pFile, "P6\n%d %d\n255\n", width, height);
根据关于 PPM 的一些信息,我发现:http://paulbourke.net/dataformats/ppm/ 您正在使用标识符 P6
编写 PPM header,这意味着 "rgb color"。如果您正在制作灰度图像,则需要使用 P5
。
此外,您使用的是 ffmpeg 的像素格式 PIX_FMT_GRAY16
,但您将其解释为字节。您可能打算改用 PIX_FMT_GRAY8
。如果您确实想要在输出中使用 16 位灰度,则应将 PPM header 中的第三个数字从 255 更改为 65535。