gpt4 book ai didi

c++ - Libav AVFrame 到 Opencv Mat 到 AVPacket 转换

转载 作者:塔克拉玛干 更新时间:2023-11-02 23:30:04 29 4
gpt4 key购买 nike

我是 libav 的新手,我正在编写一个以 opencv 为核心的视频处理软件。我所做的简要如下:

1- read the video packet

2- decode the packet into AVFrame

3- convertthe AVFrame to CV Mat

4- manipulate the Mat

5- convert the CV Matinto AVFrame

6- encode the AVFrame into AVPacket

7- write the packet

8- goto 1

我在 http://dranger.com/ffmpeg/tutorial01.html 阅读了 dranger 教程我还使用了 decoding_encoding 示例。我可以阅读视频、提取视频帧并将它们转换为 CV Mat。我的问题从将 cv Mat 转换为 AVFrame 并将其编码为 AVPacket 开始。

你能帮我解决这个问题吗?

这是我的代码:

int main(int argc, char **argv)
{
AVOutputFormat *ofmt = NULL;
AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
AVPacket pkt;
AVCodecContext *pCodecCtx = NULL;
AVCodec *pCodec = NULL;
AVFrame *pFrame = NULL;
AVFrame *pFrameRGB = NULL;
int videoStream=-1;
int audioStream=-1;
int frameFinished;
int numBytes;
uint8_t *buffer = NULL;
struct SwsContext *sws_ctx = NULL;
FrameManipulation *mal_frame;

const char *in_filename, *out_filename;
int ret, i;
if (argc < 3) {

printf("usage: %s input output\n"
"API example program to remux a media file with libavformat and libavcodec.\n"
"The output format is guessed according to the file extension.\n"
"\n", argv[0]);
return 1;
}
in_filename = arg[1];
out_filename = arg[2];
av_register_all();
if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0) {
fprintf(stderr, "Could not open input file '%s'", in_filename);
goto end;
}

if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) {
fprintf(stderr, "Failed to retrieve input stream information");
goto end;
}

av_dump_format(ifmt_ctx, 0, in_filename, 0);
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);

if (!ofmt_ctx) {
fprintf(stderr, "Could not create output context\n");
ret = AVERROR_UNKNOWN;
goto end;
}

ofmt = ofmt_ctx->oformat;

for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *in_stream = ifmt_ctx->streams[i];
AVStream *out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);

if(ifmt_ctx->streams[i]->codec->codec_type==AVMEDIA_TYPE_VIDEO &&
videoStream < 0) {
videoStream=i;
}

if(ifmt_ctx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO &&
audioStream < 0) {
audioStream=i;
}

if (!out_stream) {
fprintf(stderr, "Failed allocating output stream\n");
ret = AVERROR_UNKNOWN;
goto end;
}

ret = avcodec_copy_context(out_stream->codec, in_stream->codec);

if (ret < 0) {
fprintf(stderr, "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;
}

pCodec=avcodec_find_decoder(ifmt_ctx->streams[videoStream]->codec->codec_id);
pCodecCtx = avcodec_alloc_context3(pCodec);

if(avcodec_copy_context(pCodecCtx, ifmt_ctx->streams[videoStream]->codec) != 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
pFrameRGB=av_frame_alloc();

// Determine required buffer size and allocate buffer
numBytes=avpicture_get_size(AV_PIX_FMT_RGB24, ifmt_ctx->streams[videoStream]->codec->width,
ifmt_ctx->streams[videoStream]->codec->height);

buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));

// Assign appropriate parts of buffer to image planes in pFrameRGB
// Note that pFrameRGB is an AVFrame, but AVFrame is a superset
// of AVPicture
avpicture_fill((AVPicture *)pFrameRGB, buffer, AV_PIX_FMT_BGR24,
ifmt_ctx->streams[videoStream]->codec->width, ifmt_ctx->streams[videoStream]->codec->height);

av_dump_format(ofmt_ctx, 0, out_filename, 1);

if (!(ofmt->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
if (ret < 0) {
fprintf(stderr, "Could not open output file '%s'", out_filename);
goto end;
}
}

ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
fprintf(stderr, "Error occurred when opening output file\n");
goto end;
}

// Assign appropriate parts of buffer to image planes in pFrameRGB
// Note that pFrameRGB is an AVFrame, but AVFrame is a superset
// of AVPicture

avpicture_fill((AVPicture *)pFrameRGB, buffer, AV_PIX_FMT_BGR24,
ifmt_ctx->streams[videoStream]->codec->width,
ifmt_ctx->streams[videoStream]->codec->height);

// initialize SWS context for software scaling
sws_ctx = sws_getContext(
ifmt_ctx->streams[videoStream]->codec->width,
ifmt_ctx->streams[videoStream]->codec->height,
ifmt_ctx->streams[videoStream]->codec->pix_fmt,
ifmt_ctx->streams[videoStream]->codec->width,
ifmt_ctx->streams[videoStream]->codec->height,
AV_PIX_FMT_BGR24,
SWS_BICUBIC,
NULL,
NULL,
NULL
);
// Loop through packets
while (1) {

AVStream *in_stream, *out_stream;
ret = av_read_frame(ifmt_ctx, &pkt);
if(pkt.stream_index==videoStream)

// Decode video frame
avcodec_decode_video2(pCodecCtx, pFrame, &frameFinished, &pkt);

if(frameFinished) {
sws_scale(sws_ctx, (uint8_t const * const *)pFrame->data,
pFrame->linesize, 0, pCodecCtx->height,
pFrameRGB->data, pFrameRGB->linesize);
cv::Mat img= mal_frame->process(
pFrameRGB,pFrame->width,pFrame->height);
/* My problem is Here ------------*/


avpicture_fill((AVPicture*)pFrameRGB,
img.data,
PIX_FMT_BGR24,
outStream->codec->width,
outStream->codec->height);

pFrameRGB->width = ifmt_ctx->streams[videoStream]->codec->width;
pFrameRGB->height = ifmt_ctx->streams[videoStream]->codec->height;

avcodec_encode_video2(ifmt_ctx->streams[videoStream]->codec ,
&pkt , pFrameRGB , &gotPacket);
/*
I get this error
[swscaler @ 0x14b58a0] bad src image pointers
[swscaler @ 0x14b58a0] bad src image pointers
*/

/* My Problem Ends here ---------- */

}

if (ret < 0)

break;

in_stream = ifmt_ctx->streams[pkt.stream_index];

out_stream = ofmt_ctx->streams[pkt.stream_index];



//log_packet(ifmt_ctx, &pkt, "in");

/* copy packet */

pkt.pts = av_rescale_q_rnd(pkt.pts, in_stream->time_base, out_stream->time_base,

AV_ROUND_NEAR_INF);



pkt.dts = av_rescale_q_rnd(pkt.dts, in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF);

pkt.duration = av_rescale_q(pkt.duration, in_stream->time_base, out_stream->time_base);

pkt.pos = -1;

log_packet(ofmt_ctx, &pkt, "out");

ret = av_interleaved_write_frame(ofmt_ctx, &pkt);

if (ret < 0) {

fprintf(stderr, "Error muxing packet\n");

break;

}

av_free_packet(&pkt);

}

av_write_trailer(ofmt_ctx);

end:

avformat_close_input(&ifmt_ctx);

/* close output */

if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))

avio_closep(&ofmt_ctx->pb);

avformat_free_context(ofmt_ctx);

if (ret < 0 && ret != AVERROR_EOF) {

return 1;

}

return 0;

}

当我运行这段代码时,我在这部分遇到了未知的 fatal error :

   /* My problem is Here ------------*/


avpicture_fill((AVPicture*)pFrameRGB,
img.data,
PIX_FMT_BGR24,
outStream->codec->width,
outStream->codec->height);

pFrameRGB->width = ifmt_ctx->streams[videoStream]->codec->width;
pFrameRGB->height = ifmt_ctx->streams[videoStream]->codec->height;

avcodec_encode_video2(ifmt_ctx->streams[videoStream]->codec ,
&pkt , pFrameRGB , &gotPacket);
/*
I get this error
[swscaler @ 0x14b58a0] bad src image pointers
[swscaler @ 0x14b58a0] bad src image pointers
*/

/* My Problem Ends here ---------- */

这是我想将 cv Mat 转换回 AVFrame 并将其编码为 AVPacket 的地方。感谢您的帮助。

最佳答案

在阅读了一些示例、阅读源代码和一些帮助人们提供的帮助之后,我设法让代码运行起来。我使用了转码和编码示例并将它们混合在一起。 Here is my code

以下是亮点:1- 应使用 libswscale 将具有所需数据包格式的 AVFrame 转换为 openCV Mat。为此,我们定义

struct SwsContext *sws_ctx = NULL;
sws_ctx = sws_getContext(pCodecCtx->width,
pCodecCtx->height,
pCodecCtx->pix_fmt,
pCodecCtx->width,
pCodecCtx->height,
AV_PIX_FMT_BGR24,
SWS_BICUBIC,
NULL,
NULL,
NULL
);

要将 opencv Mat 转换回 AVFrame,应该再次使用 swscale 并将 opencv BGR 帧格式转换为 YUV。所以,我这样做:

 struct SwsContext *sws_ctx_bgr_yuv = NULL;
sws_ctx_bgr_yuv = sws_getContext(pCodecCtx->width,
pCodecCtx->height,
AV_PIX_FMT_BGR24,
pCodecCtx->width,
pCodecCtx->height,
pCodecCtx->pix_fmt //AV_PIX_FMT_YUV420p
,0,0,NULL,NULL);

并且,这里是帧读取/解码/编码循环:

while (1) {
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;
type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ifmt_ctx->streams[stream_index]->codec->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}
if (got_frame) {
if(stream_index==video_index){

sws_scale(sws_ctx, (uint8_t const * const *)frame->data,
frame->linesize, 0, pCodecCtx->height,
pFrameRGB->data, pFrameRGB->linesize);
/*------------------------------------------------------------------------
/* Frame converts to opencv Mat
/*------------------------------------------------------------------------*/
cv::Mat img(frame->height,frame->width,CV_8UC3,pFrameRGB->data[0]);
img=manipulate_image(img); //this is opencv Mat, do whatever you want, but don't change its dimensions and format
//manipulate_function can be considered as as simple as blurring
const int stride[] = {img.step[0] };
/* opencv Mat converts back to AVFrame */
sws_scale(sws_ctx_bgr_yuv, &img.data, stride, 0, img.rows, frame->data, frame->linesize);

}
frame->pts = av_frame_get_best_effort_timestamp(frame);
/* AVFrame re-encodes to AVPacket and will be sent to encoder */
ret = filter_encode_write_frame(frame, stream_index);
av_frame_free(&frame);

if (ret < 0)
goto end;
} else {
av_frame_free(&frame);
}
} else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);
ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_free_packet(&packet);
}

关于c++ - Libav AVFrame 到 Opencv Mat 到 AVPacket 转换,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/44852117/

29 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com