Jestem nowy w libav i piszę oprogramowanie do manipulacji wideo, które wykorzystuje opencv jako serce. Co zrobiłem to krótko, jak poniżej:Libav AVFrame do OpenCv Mat do konwersji AVPacket
1- czytać pakiet wideo
2- dekodowania pakietu do AVFrame
3- nawróconego AVFrame do CV Mat
4- manipulować maty
5- przekonwertować CV Mat do AVFrame
6- kodują AVFrame do AVPacket
7- zapisu pakietu
8- goto 1
I odczytu poradnik Dranger w http://dranger.com/ffmpeg/tutorial01.html i również przykład decoding_encoding. Mogę odczytać wideo, wyodrębnić klatki wideo i przekonwertować je na matę CV. Mój problem zaczyna się od konwersji z cv Mat na AVFrame i zakodowania go do AVPacket.
Czy możesz mi w tym pomóc?
Oto mój kod:
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;
}
Kiedy uruchomić ten kod, pojawia się nieznany błąd krytyczny w tej części:
/* 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 ---------- */
Oto gdzie chcę przekonwertować z powrotem cv matę AVFrame i zakodować go do AVPacket. Doceniam twoją pomoc.
Dlaczego robisz to ręcznie, gdy OpenCV obsługuje libav jako backend do dekodowania/kodowania? – Aram
@Aram opencv VideoWriter nie uwzględnia strumienia audio w zakodowanym wideo. Nie chcę dodawać dodatkowego etapu do mojego przetwarzania wideo. –
Którą wersję ffmpeg/libav używasz? I wersja opencv? Czym jest struktura "FrameManipulation"? Musisz dać nam sprawdzalny przykład do uruchomienia. I zauważam, że używasz przykładu 'remuxing', a nie' dekodowania_wyrażeń', także bardzo starego, dużo przestarzałego API. – halfelf