Advanced search
Other articles (96)
-
MediaSPIP 0.1 Beta version
25 April 2011, byMediaSPIP 0.1 beta is the first version of MediaSPIP proclaimed as "usable".
The zip file provided here only contains the sources of MediaSPIP in its standalone version.
To get a working installation, you must manually install all-software dependencies on the server.
If you want to use this archive for an installation in "farm mode", you will also need to proceed to other manual (...) -
Multilang : améliorer l’interface pour les blocs multilingues
18 February 2011, byMultilang est un plugin supplémentaire qui n’est pas activé par défaut lors de l’initialisation de MediaSPIP.
Après son activation, une préconfiguration est mise en place automatiquement par MediaSPIP init permettant à la nouvelle fonctionnalité d’être automatiquement opérationnelle. Il n’est donc pas obligatoire de passer par une étape de configuration pour cela. -
Librairies et binaires spécifiques au traitement vidéo et sonore
31 January 2010, byLes logiciels et librairies suivantes sont utilisées par SPIPmotion d’une manière ou d’une autre.
Binaires obligatoires FFMpeg : encodeur principal, permet de transcoder presque tous les types de fichiers vidéo et sonores dans les formats lisibles sur Internet. CF ce tutoriel pour son installation; Oggz-tools : outils d’inspection de fichiers ogg; Mediainfo : récupération d’informations depuis la plupart des formats vidéos et sonores;
Binaires complémentaires et facultatifs flvtool2 : extraction / (...)
On other websites (7531)
-
Using ffmpeg to overlay dvdsub
27 April 2019, by ib11I am trying to overlay a dvdsub file pair (*.idx + *.sub) to a video file.
This is the batch script with the command line I am trying to use:
@echo off
set srcVidFile1="myvideo.mov"
set srcSubFile=mysub.sub
set srcIdxFile=mysub.idx
set destFile=D:\testsub.mp4
ffmpeg.exe -i %srcVidFile1% -i %srcSubFile% -i %srcIdxFile%
-filter_complex "[0:v][1:s]overlay" -c:s dvdsub -c:v
libx264 -crf 24 -c:a aac -b:a 160K -ar 48K -strict -2 -y
%destFile%This however only accepts 720x576 VOBsub files. And also the color gets inverted.
My video however is 1080p and do have a 1920x1080 VOBsub file pair, but when I trying use them, I get an error sub2video: rectange (xxx xxx xxx xxx) overflowing 720 576
The full output:
ffmpeg version N-81516-gbe07c25 Copyright (c) 2000-2016 the FFmpeg developers
built with gcc 5.4.0 (GCC)
configuration: --enable-gpl --enable-version3 --disable-w32threads --enable-dxva2 --enable-libmfx --enable-nvenc --enable-avisynth --enable-bzlib --enable-libebur128 --enable-fontconfig --enable-frei0r --enable-gnutls --enable-iconv --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libfreetype --enable-libgme --enable-libgsm --enable-libilbc --enable-libmodplug --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenh264 --enable-libopenjpeg --enable-libopus --enable-librtmp --enable-libschroedinger --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvo-amrwbenc --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs --enable-libxvid --enable-libzimg --enable-lzma --enable-decklink --enable-zlib
libavutil 55. 29.100 / 55. 29.100
libavcodec 57. 54.101 / 57. 54.101
libavformat 57. 48.101 / 57. 48.101
libavdevice 57. 0.102 / 57. 0.102
libavfilter 6. 58.100 / 6. 58.100
libswscale 4. 1.100 / 4. 1.100
libswresample 2. 1.100 / 2. 1.100
libpostproc 54. 0.100 / 54. 0.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'myvideo.mov':
Metadata:
major_brand : qt
minor_version : 537199360
compatible_brands: qt
creation_time : 2017-07-18T19:00:46.000000Z
timecode : 00:59:58;00
Duration: 00:01:19.01, start: 0.000000, bitrate: 146880 kb/s
Stream #0:0(eng): Video: dnxhd (DNXHD) (AVdn / 0x6E645641), yuv422p(tv, bt709/unknown/unknown), 1920x1080, 145344 kb/s, 29.97 fps,
29.97 tbr, 29970 tbn, 29970 tbc (default)
Metadata:
creation_time : 2017-07-18T19:00:46.000000Z
handler_name : Apple Alias Data Handler
encoder : Avid DNxHD Codec
Stream #0:1(eng): Audio: pcm_s16le (sowt / 0x74776F73), 48000 Hz, stereo, s16, 1536 kb/s (default)
Metadata:
creation_time : 2017-07-18T19:00:46.000000Z
handler_name : Apple Alias Data Handler
Stream #0:2(eng): Data: none (tmcd / 0x64636D74) (default)
Metadata:
creation_time : 2017-07-18T19:01:18.000000Z
handler_name : Apple Alias Data Handler
timecode : 00:59:58;00
Input #1, mpeg, from 'mysub.sub':
Duration: 00:00:52.88, start: 3600.042000, bitrate: 10 kb/s
Stream #1:0[0x20]: Subtitle: dvd_subtitle
Input #2, vobsub, from 'mysub.idx':
Duration: N/A, bitrate: N/A
Stream #2:0[0x0](en): Subtitle: dvd_subtitle, 1920x1080 (default)
[mpeg @ 0000000002de4580] sub2video: using 720x576 canvas
[libx264 @ 00000000005234c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 AVX2 LZCNT BMI2
[libx264 @ 00000000005234c0] profile High, level 4.0
[libx264 @ 00000000005234c0] 264 - core 148 r2705 3f5ed56 - H.264/MPEG-4 AVC codec - Copyleft 2003-2016 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=6 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=24.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
[mp4 @ 00000000005218a0] Using AVStream.codec to pass codec parameters to muxers is deprecated, use AVStream.codecpar instead.
Last message repeated 2 times
Output #0, mp4, to 'D:\testsub.mp4':
Metadata:
major_brand : qt
minor_version : 537199360
compatible_brands: qt
timecode : 00:59:58;00
encoder : Lavf57.48.101
Stream #0:0: Video: h264 (libx264) ([33][0][0][0] / 0x0021), yuv420p, 1920x1080, q=-1--1, 0.03 fps, 11988 tbn, 29.97 tbc (default)
Metadata:
encoder : Lavc57.54.101 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
Stream #0:1(eng): Audio: aac (LC) ([64][0][0][0] / 0x0040), 48000 Hz, stereo, fltp, delay 1024, padding 0, 160 kb/s (default)
Metadata:
creation_time : 2017-07-18T19:00:46.000000Z
handler_name : Apple Alias Data Handler
encoder : Lavc57.54.101 aac
Stream #0:2: Subtitle: dvd_subtitle (dvdsub) ([224][0][0][0] / 0x00E0), 720x480
Metadata:
encoder : Lavc57.54.101 dvdsub
Stream mapping:
Stream #0:0 (dnxhd) -> overlay:main (graph 0)
Stream #1:0 (dvdsub) -> overlay:overlay (graph 0)
overlay (graph 0) -> Stream #0:0 (libx264)
Stream #0:1 -> #0:1 (pcm_s16le (native) -> aac (native))
Stream #1:0 -> #0:2 (dvd_subtitle (dvdsub) -> dvd_subtitle (dvdsub))
Press [q] to stop, [?] for help
sub2video: rectangle (942 858 163 60) overflowing 720 576
Last message repeated 1 times
frame= 33 fps=0.0 q=0.0 size= 0kB time=00:00:07.08 bitrate= 0.1kbits/s speed=14.1x
frame= 63 fps= 62 q=30.0 size= 10kB time=00:00:07.08 bitrate= 11.1kbits/s speed=7.01x
frame= 91 fps= 59 q=30.0 size= 30kB time=00:00:07.08 bitrate= 34.7kbits/s speed= 4.6x
frame= 112 fps= 55 q=30.0 size= 197kB time=00:00:07.08 bitrate= 227.9kbits/s speed=3.45x
frame= 124 fps= 47 q=30.0 size= 407kB time=00:00:07.08 bitrate= 470.6kbits/s speed=2.69x
frame= 137 fps= 44 q=30.0 size= 639kB time=00:00:07.08 bitrate= 738.6kbits/s speed=2.26x
frame= 152 fps= 41 q=30.0 size= 861kB time=00:00:07.08 bitrate= 995.4kbits/s speed=1.89x
frame= 163 fps= 37 q=30.0 size= 1002kB time=00:00:07.08 bitrate=1158.6kbits/s speed=1.63x
frame= 175 fps= 36 q=30.0 size= 1412kB time=00:00:07.08 bitrate=1633.3kbits/s speed=1.46x
frame= 187 fps= 35 q=30.0 size= 1642kB time=00:00:07.31 bitrate=1838.4kbits/s speed=1.36x
frame= 202 fps= 34 q=30.0 size= 1892kB time=00:00:07.82 bitrate=1979.7kbits/s speed=1.31x
frame= 213 fps= 33 q=30.0 size= 2071kB time=00:00:08.19 bitrate=2071.2kbits/s speed=1.26x
sub2video: rectangle (419 785 1209 133) overflowing 720 576
frame= 225 fps= 32 q=30.0 size= 2363kB time=00:00:09.54 bitrate=2028.5kbits/s speed=1.36x
frame= 236 fps= 31 q=30.0 size= 2554kB time=00:00:09.54 bitrate=2192.6kbits/s speed=1.26x
frame= 249 fps= 31 q=30.0 size= 2760kB time=00:00:09.54 bitrate=2369.7kbits/s speed=1.18x
frame= 262 fps= 30 q=30.0 size= 2957kB time=00:00:09.83 bitrate=2463.4kbits/s speed=1.14x
frame= 272 fps= 29 q=30.0 size= 3111kB time=00:00:10.15 bitrate=2509.4kbits/s speed=1.09x
frame= 283 fps= 29 q=30.0 size= 3796kB time=00:00:10.51 bitrate=2957.1kbits/s speed=1.07x
sub2video: rectangle (942 858 163 60) overflowing 720 576
frame= 289 fps= 28 q=30.0 size= 4144kB time=00:00:13.62 bitrate=2491.4kbits/s speed=1.32x
frame= 297 fps= 27 q=30.0 size= 4613kB time=00:00:13.62 bitrate=2773.6kbits/s speed=1.26x
frame= 304 fps= 27 q=30.0 size= 5036kB time=00:00:13.62
[---TRUNCATED REST OF FRAMES---]
video:94601kB audio:1616kB subtitle:52kB other streams:0kB global headers:0kB muxing overhead: 0.085206%
[libx264 @ 00000000005234c0] frame I:35 Avg QP:23.92 size:153135
[libx264 @ 00000000005234c0] frame P:958 Avg QP:26.88 size: 69163
[libx264 @ 00000000005234c0] frame B:1375 Avg QP:26.60 size: 18365
[libx264 @ 00000000005234c0] consecutive B-frames: 22.2% 0.7% 1.3% 75.8%
[libx264 @ 00000000005234c0] mb I I16..4: 11.8% 84.0% 4.2%
[libx264 @ 00000000005234c0] mb P I16..4: 3.2% 22.6% 0.4% P16..4: 40.9% 10.7% 6.7% 0.0% 0.0% skip:15.4%
[libx264 @ 00000000005234c0] mb B I16..4: 0.3% 2.2% 0.0% B16..8: 44.9% 2.2% 0.4% direct: 2.8% skip:47.2% L0:45.9% L1:51.3% BI: 2.8%
[libx264 @ 00000000005234c0] 8x8 transform intra:86.2% inter:89.3%
[libx264 @ 00000000005234c0] coded y,uvDC,uvAC intra: 76.4% 65.9% 37.2% inter: 23.4% 29.3% 3.5%
[libx264 @ 00000000005234c0] i16 v,h,dc,p: 18% 42% 5% 34%
[libx264 @ 00000000005234c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 10% 9% 47% 5% 6% 5% 6% 5% 6%
[libx264 @ 00000000005234c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 18% 17% 7% 11% 9% 10% 6% 7%
[libx264 @ 00000000005234c0] i8c dc,h,v,p: 63% 16% 16% 5%
[libx264 @ 00000000005234c0] Weighted P-Frames: Y:5.2% UV:2.9%
[libx264 @ 00000000005234c0] ref P L0: 50.5% 14.8% 22.5% 11.6% 0.6%
[libx264 @ 00000000005234c0] ref B L0: 87.9% 9.7% 2.4%
[libx264 @ 00000000005234c0] ref B L1: 95.2% 4.8%
[libx264 @ 00000000005234c0] kb/s:9808.13
[aac @ 0000000000524340] Qavg: 574.088I would like to input the 1920x1080 VOBsub file pair and overlay it on the 1080p video with 24bit original colors.
Can somebody give me the correct command line for this?
-
FFMPEG: Decode only portion of a frame
17 April 2019, by SAMProI am using
libavlibraries to decode video and process frames in order to do some image processing. However I have limited resource to decode frames and no hardware acceleration at all. So decoding is the critical section in my project (regarding speed).Because only some section of frame is needed to processed, I’m wondering is it possible to decode only a region of interest (a rectangle) and the rest of the frame is not decoded? And does this make the decoding faster?
Edit:
I have decoding H.264 codec. -
ffmpeg record video plays too fast
29 April 2023, by Kris XiaI'm a college student and I am studying FFmpeg now.



I have wrote a software that can record desktops and audio('virtual-audio-capturer') with FFmpeg.And I am now writing Audio and Video Synchronization.
I met some problems that video recording plays too fast.



When I look for audio and video synchronization help on the Internet，I find a formula for calculating PTS ：



pts = n * (（1 / timbase）/ fps)



When I use this formula,I find a phenomenon.



1.The higher frame rate is,the faster the video playback speed.



2.The slower the frame rate, the faster the video playback.



Also I find while the framerate is 10，the video playback speed will be right.



Why has this situation happened?



I have thought this question for three days. I really hope someone can help me solve this problem.



I really appreciate the help.



#include "stdafx.h"

#ifdef __cplusplus
extern "C"
{
#endif
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libswscale/swscale.h"
#include "libavdevice/avdevice.h"
#include "libavutil/audio_fifo.h"

#include "libavfilter/buffersink.h"
#include "libavfilter/buffersrc.h"
#include "libavutil/imgutils.h"
#include "libavutil/mathematics.h"
#include "libavutil/samplefmt.h"
#include "libavutil/time.h"
#include "libavutil/opt.h"
#include "libavutil/pixdesc.h"
#include "libavutil/file.h"
#include "libavutil/mem.h"
#include "libavutil/frame.h"
#include "libavfilter/avfilter.h"
#include "libswresample/swresample.h"

#pragma comment(lib, "avcodec.lib")
#pragma comment(lib, "avformat.lib")
#pragma comment(lib, "avutil.lib")
#pragma comment(lib, "avdevice.lib")
#pragma comment(lib, "avfilter.lib")

#pragma comment(lib, "avfilter.lib")
#pragma comment(lib, "postproc.lib")
#pragma comment(lib, "swresample.lib")
#pragma comment(lib, "swscale.lib")
#ifdef __cplusplus
};
#endif

AVFormatContext *pFormatCtx_Video = NULL, *pFormatCtx_Audio = NULL, *pFormatCtx_Out = NULL;

AVCodecContext *outVideoCodecCtx = NULL;
AVCodecContext *outAudioCodecCtx = NULL;

AVStream *pVideoStream = NULL, *pAudioStream = NULL;

AVCodec *outAVCodec;
AVCodec *outAudioCodec;

AVCodecContext *pCodecCtx_Video;
AVCodec *pCodec_Video;
AVFifoBuffer *fifo_video = NULL;
AVAudioFifo *fifo_audio = NULL;
int VideoIndex, AudioIndex;
int codec_id;

CRITICAL_SECTION AudioSection, VideoSection;



SwsContext *img_convert_ctx;
int frame_size = 0;

uint8_t *picture_buf = NULL, *frame_buf = NULL;

bool bCap = true;

DWORD WINAPI ScreenCapThreadProc( LPVOID lpParam );
DWORD WINAPI AudioCapThreadProc( LPVOID lpParam );

int OpenVideoCapture()
{
 AVInputFormat *ifmt=av_find_input_format("gdigrab");
 AVDictionary *options = NULL;
 av_dict_set(&options, "framerate", "60", NULL);
 if(avformat_open_input(&pFormatCtx_Video, "desktop", ifmt, &options)!=0)
 {
 printf("Couldn't open input stream.（无法打开视频输入流）\n");
 return -1;
 }
 if(avformat_find_stream_info(pFormatCtx_Video,NULL)<0)
 {
 printf("Couldn't find stream information.（无法获取视频流信息）\n");
 return -1;
 }
 if (pFormatCtx_Video->streams[0]->codec->codec_type != AVMEDIA_TYPE_VIDEO)
 {
 printf("Couldn't find video stream information.（无法获取视频流信息）\n");
 return -1;
 }
 pCodecCtx_Video = pFormatCtx_Video->streams[0]->codec;
 pCodec_Video = avcodec_find_decoder(pCodecCtx_Video->codec_id);
 if(pCodec_Video == NULL)
 {
 printf("Codec not found.（没有找到解码器）\n");
 return -1;
 }
 if(avcodec_open2(pCodecCtx_Video, pCodec_Video, NULL) < 0)
 {
 printf("Could not open codec.（无法打开解码器）\n");
 return -1;
 }

 av_dump_format(pFormatCtx_Video, 0, NULL, 0);

 img_convert_ctx = sws_getContext(pCodecCtx_Video->width, pCodecCtx_Video->height, pCodecCtx_Video->pix_fmt, 
 pCodecCtx_Video->width, pCodecCtx_Video->height, PIX_FMT_YUV420P, SWS_BICUBIC, NULL, NULL, NULL); 

 frame_size = avpicture_get_size(pCodecCtx_Video->pix_fmt, pCodecCtx_Video->width, pCodecCtx_Video->height);
 fifo_video = av_fifo_alloc(30 * avpicture_get_size(AV_PIX_FMT_YUV420P, pCodecCtx_Video->width, pCodecCtx_Video->height));

 return 0;
}

static char *dup_wchar_to_utf8(wchar_t *w)
{
 char *s = NULL;
 int l = WideCharToMultiByte(CP_UTF8, 0, w, -1, 0, 0, 0, 0);
 s = (char *) av_malloc(l);
 if (s)
 WideCharToMultiByte(CP_UTF8, 0, w, -1, s, l, 0, 0);
 return s;
}

int OpenAudioCapture()
{
 AVInputFormat *pAudioInputFmt = av_find_input_format("dshow");
 char * psDevName = dup_wchar_to_utf8(L"audio=virtual-audio-capturer");

 if (avformat_open_input(&pFormatCtx_Audio, psDevName, pAudioInputFmt,NULL) < 0)
 {
 printf("Couldn't open input stream.（无法打开音频输入流）\n");
 return -1;
 }

 if(avformat_find_stream_info(pFormatCtx_Audio,NULL)<0) 
 return -1; 

 if(pFormatCtx_Audio->streams[0]->codec->codec_type != AVMEDIA_TYPE_AUDIO)
 {
 printf("Couldn't find video stream information.（无法获取音频流信息）\n");
 return -1;
 }

 AVCodec *tmpCodec = avcodec_find_decoder(pFormatCtx_Audio->streams[0]->codec->codec_id);
 if(0 > avcodec_open2(pFormatCtx_Audio->streams[0]->codec, tmpCodec, NULL))
 {
 printf("can not find or open audio decoder!\n");
 }

 av_dump_format(pFormatCtx_Audio, 0, NULL, 0);

 return 0;
}

int OpenOutPut()
{
 AVStream *pVideoStream = NULL, *pAudioStream = NULL;
 const char *outFileName = "test.mp4";
 avformat_alloc_output_context2(&pFormatCtx_Out, NULL, NULL, outFileName);

 if (pFormatCtx_Video->streams[0]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
 {
 VideoIndex = 0;
 pVideoStream = avformat_new_stream(pFormatCtx_Out, NULL);
 if (!pVideoStream)
 {
 printf("can not new stream for output!\n");
 return -1;
 }

 outVideoCodecCtx = avcodec_alloc_context3(outAVCodec);
 if ( !outVideoCodecCtx )
 {
 printf("Error : avcodec_alloc_context3()\n");
 return -1;
 }

 //set codec context param
 outVideoCodecCtx = pVideoStream->codec;
 outVideoCodecCtx->codec_id = AV_CODEC_ID_MPEG4;
 outVideoCodecCtx->width = pFormatCtx_Video->streams[0]->codec->width;
 outVideoCodecCtx->height = pFormatCtx_Video->streams[0]->codec->height;
 outVideoCodecCtx->time_base = pFormatCtx_Video->streams[0]->codec->time_base;
 outVideoCodecCtx->pix_fmt = AV_PIX_FMT_YUV420P;
 outVideoCodecCtx->codec_type = AVMEDIA_TYPE_VIDEO;

 if (codec_id == AV_CODEC_ID_H264)
 {
 av_opt_set(outVideoCodecCtx->priv_data, "preset", "slow", 0);
 }

 outAVCodec = avcodec_find_encoder(AV_CODEC_ID_MPEG4);
 if( !outAVCodec )
 {
 printf("\n\nError : avcodec_find_encoder()");
 return -1;
 }
 if (pFormatCtx_Out->oformat->flags & AVFMT_GLOBALHEADER)
 outVideoCodecCtx->flags |=CODEC_FLAG_GLOBAL_HEADER;

 if ((avcodec_open2(outVideoCodecCtx,outAVCodec, NULL)) < 0)
 {
 printf("can not open the encoder\n");
 return -1;
 }
 }

 if(pFormatCtx_Audio->streams[0]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
 {
 AVCodecContext *pOutputCodecCtx;
 AudioIndex = 1;
 pAudioStream = avformat_new_stream(pFormatCtx_Out, NULL);

 pAudioStream->codec->codec = avcodec_find_encoder(pFormatCtx_Out->oformat->audio_codec);

 pOutputCodecCtx = pAudioStream->codec;

 pOutputCodecCtx->sample_rate = pFormatCtx_Audio->streams[0]->codec->sample_rate;
 pOutputCodecCtx->channel_layout = pFormatCtx_Out->streams[0]->codec->channel_layout;
 pOutputCodecCtx->channels = av_get_channel_layout_nb_channels(pAudioStream->codec->channel_layout);
 if(pOutputCodecCtx->channel_layout == 0)
 {
 pOutputCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
 pOutputCodecCtx->channels = av_get_channel_layout_nb_channels(pOutputCodecCtx->channel_layout);

 }
 pOutputCodecCtx->sample_fmt = pAudioStream->codec->codec->sample_fmts[0];
 AVRational time_base={1, pAudioStream->codec->sample_rate};
 pAudioStream->time_base = time_base;
 //audioCodecCtx->time_base = time_base;

 pOutputCodecCtx->codec_tag = 0; 
 if (pFormatCtx_Out->oformat->flags & AVFMT_GLOBALHEADER) 
 pOutputCodecCtx->flags |= CODEC_FLAG_GLOBAL_HEADER;

 if (avcodec_open2(pOutputCodecCtx, pOutputCodecCtx->codec, 0) < 0)
 {
 printf("编码器打开失败，退出程序\n");
 return -1;
 }
 }

 if (!(pFormatCtx_Out->oformat->flags & AVFMT_NOFILE))
 {
 if(avio_open(&pFormatCtx_Out->pb, outFileName, AVIO_FLAG_WRITE) < 0)
 {
 printf("can not open output file handle!\n");
 return -1;
 }
 }

 if(avformat_write_header(pFormatCtx_Out, NULL) < 0)
 {
 printf("can not write the header of the output file!\n");
 return -1;
 }

 return 0;
}

int _tmain(int argc, _TCHAR* argv[])
{
 av_register_all();
 avdevice_register_all();
 if (OpenVideoCapture() < 0)
 {
 return -1;
 }
 if (OpenAudioCapture() < 0)
 {
 return -1;
 }
 if (OpenOutPut() < 0)
 {
 return -1;
 }
// int fps;
 /*printf("输入帧率：");
 scanf_s("%d",&fps);
 if ( NULL == fps)
 {
 fps = 10;
 }*/

 InitializeCriticalSection(&VideoSection);
 InitializeCriticalSection(&AudioSection);

 AVFrame *picture = av_frame_alloc();
 int size = avpicture_get_size(pFormatCtx_Out->streams[VideoIndex]->codec->pix_fmt, 
 pFormatCtx_Out->streams[VideoIndex]->codec->width, pFormatCtx_Out->streams[VideoIndex]->codec->height);
 picture_buf = new uint8_t[size];

 avpicture_fill((AVPicture *)picture, picture_buf, 
 pFormatCtx_Out->streams[VideoIndex]->codec->pix_fmt, 
 pFormatCtx_Out->streams[VideoIndex]->codec->width, 
 pFormatCtx_Out->streams[VideoIndex]->codec->height);



 //star cap screen thread
 CreateThread( NULL, 0, ScreenCapThreadProc, 0, 0, NULL);
 //star cap audio thread
 CreateThread( NULL, 0, AudioCapThreadProc, 0, 0, NULL);
 int64_t cur_pts_v=0,cur_pts_a=0;
 int VideoFrameIndex = 0, AudioFrameIndex = 0;

 while(1)
 {
 if (_kbhit() != 0 && bCap)
 {
 bCap = false;
 Sleep(2000);
 }
 if (fifo_audio && fifo_video)
 {
 int sizeAudio = av_audio_fifo_size(fifo_audio);
 int sizeVideo = av_fifo_size(fifo_video);
 //缓存数据写完就结束循环
 if (av_audio_fifo_size(fifo_audio) <= pFormatCtx_Out->streams[AudioIndex]->codec->frame_size && 
 av_fifo_size(fifo_video) <= frame_size && !bCap)
 {
 break;
 }
 }

 if(av_compare_ts(cur_pts_v, pFormatCtx_Out->streams[VideoIndex]->time_base, 
 cur_pts_a,pFormatCtx_Out->streams[AudioIndex]->time_base) <= 0)
 {
 if (av_fifo_size(fifo_video) < frame_size && !bCap)
 {
 cur_pts_v = 0x7fffffffffffffff;
 }
 if(av_fifo_size(fifo_video) >= size)
 {
 EnterCriticalSection(&VideoSection);
 av_fifo_generic_read(fifo_video, picture_buf, size, NULL); //将数据从avfifobuffer馈送到用户提供的回调。
 LeaveCriticalSection(&VideoSection);

 avpicture_fill((AVPicture *)picture, picture_buf,
 pFormatCtx_Out->streams[VideoIndex]->codec->pix_fmt,
 pFormatCtx_Out->streams[VideoIndex]->codec->width,
 pFormatCtx_Out->streams[VideoIndex]->codec->height); //根据指定的图像参数和提供的图像数据缓冲区设置图片字段。

 //pts = n * (（1 / timbase）/ fps);
 //picture->pts = VideoFrameIndex * ((pFormatCtx_Video->streams[0]->time_base.den / pFormatCtx_Video->streams[0]->time_base.num) / 24);
 picture->pts = VideoFrameIndex * ((outVideoCodecCtx->time_base.den * 100000 / outVideoCodecCtx->time_base.num) / 180);

 int got_picture = 0;
 AVPacket pkt;
 av_init_packet(&pkt);

 pkt.data = NULL;
 pkt.size = 0;
 //从帧中获取输入的原始视频数据
 int ret = avcodec_encode_video2(pFormatCtx_Out->streams[VideoIndex]->codec, &pkt, picture, &got_picture);
 if(ret < 0)
 {
 continue;
 }

 if (got_picture==1)
 {
 pkt.stream_index = VideoIndex;
 /*int count = 1;
 pkt.pts = pkt.dts = count * ((pFormatCtx_Video->streams[0]->time_base.den / pFormatCtx_Video->streams[0]->time_base.num) / 15);
 count++;*/

 //x = pts * (timebase1.num / timebase1.den )* (timebase2.den / timebase2.num);

 pkt.pts = av_rescale_q_rnd(pkt.pts, pFormatCtx_Video->streams[0]->time_base, 
 pFormatCtx_Out->streams[VideoIndex]->time_base, (AVRounding)(AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX)); 
 pkt.dts = av_rescale_q_rnd(pkt.dts, pFormatCtx_Video->streams[0]->time_base, 
 pFormatCtx_Out->streams[VideoIndex]->time_base, (AVRounding)(AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX)); 


 pkt.duration = ((pFormatCtx_Out->streams[0]->time_base.den / pFormatCtx_Out->streams[0]->time_base.num) / 60);
 //pkt.duration = 1000/60;
 //pkt.pts = pkt.dts = Count * (ofmt_ctx->streams[stream_index]->time_base.den) /ofmt_ctx->streams[stream_index]->time_base.num / 10;

 //Count++;


 cur_pts_v = pkt.pts;

 ret = av_interleaved_write_frame(pFormatCtx_Out, &pkt);
 //delete[] pkt.data;
 av_free_packet(&pkt);
 }
 VideoFrameIndex++;
 }
 }
 else
 {
 if (NULL == fifo_audio)
 {
 continue;//还未初始化fifo
 }
 if (av_audio_fifo_size(fifo_audio) < pFormatCtx_Out->streams[AudioIndex]->codec->frame_size && !bCap)
 {
 cur_pts_a = 0x7fffffffffffffff;
 }
 if(av_audio_fifo_size(fifo_audio) >= 
 (pFormatCtx_Out->streams[AudioIndex]->codec->frame_size > 0 ? pFormatCtx_Out->streams[AudioIndex]->codec->frame_size : 1024))
 {
 AVFrame *frame;
 frame = av_frame_alloc();
 frame->nb_samples = pFormatCtx_Out->streams[AudioIndex]->codec->frame_size>0 ? pFormatCtx_Out->streams[AudioIndex]->codec->frame_size: 1024;
 frame->channel_layout = pFormatCtx_Out->streams[AudioIndex]->codec->channel_layout;
 frame->format = pFormatCtx_Out->streams[AudioIndex]->codec->sample_fmt;
 frame->sample_rate = pFormatCtx_Out->streams[AudioIndex]->codec->sample_rate;
 av_frame_get_buffer(frame, 0);

 EnterCriticalSection(&AudioSection);
 av_audio_fifo_read(fifo_audio, (void **)frame->data, 
 (pFormatCtx_Out->streams[AudioIndex]->codec->frame_size > 0 ? pFormatCtx_Out->streams[AudioIndex]->codec->frame_size : 1024));
 LeaveCriticalSection(&AudioSection);

 AVPacket pkt_out;
 av_init_packet(&pkt_out);
 int got_picture = -1;
 pkt_out.data = NULL;
 pkt_out.size = 0;

 frame->pts = AudioFrameIndex * pFormatCtx_Out->streams[AudioIndex]->codec->frame_size;
 if (avcodec_encode_audio2(pFormatCtx_Out->streams[AudioIndex]->codec, &pkt_out, frame, &got_picture) < 0)
 {
 printf("can not decoder a frame");
 }
 av_frame_free(&frame);
 if (got_picture) 
 {
 pkt_out.stream_index = AudioIndex;
 pkt_out.pts = AudioFrameIndex * pFormatCtx_Out->streams[AudioIndex]->codec->frame_size;
 pkt_out.dts = AudioFrameIndex * pFormatCtx_Out->streams[AudioIndex]->codec->frame_size;
 pkt_out.duration = pFormatCtx_Out->streams[AudioIndex]->codec->frame_size;

 cur_pts_a = pkt_out.pts;

 int ret = av_interleaved_write_frame(pFormatCtx_Out, &pkt_out);
 av_free_packet(&pkt_out);
 }
 AudioFrameIndex++;
 }
 }
 }

 delete[] picture_buf;

 av_fifo_free(fifo_video);
 av_audio_fifo_free(fifo_audio);

 av_write_trailer(pFormatCtx_Out);

 avio_close(pFormatCtx_Out->pb);
 avformat_free_context(pFormatCtx_Out);

 if (pFormatCtx_Video != NULL)
 {
 avformat_close_input(&pFormatCtx_Video);
 pFormatCtx_Video = NULL;
 }
 if (pFormatCtx_Audio != NULL)
 {
 avformat_close_input(&pFormatCtx_Audio);
 pFormatCtx_Audio = NULL;
 }

 return 0;
}

DWORD WINAPI ScreenCapThreadProc( LPVOID lpParam )
{
 AVPacket packet;
 int got_picture;
 AVFrame *pFrame;
 pFrame=av_frame_alloc();

 AVFrame *picture = av_frame_alloc();
 int size = avpicture_get_size(pFormatCtx_Out->streams[VideoIndex]->codec->pix_fmt, 
 pFormatCtx_Out->streams[VideoIndex]->codec->width, 
 pFormatCtx_Out->streams[VideoIndex]->codec->height);

 avpicture_fill((AVPicture *)picture, picture_buf, 
 pFormatCtx_Out->streams[VideoIndex]->codec->pix_fmt, 
 pFormatCtx_Out->streams[VideoIndex]->codec->width, 
 pFormatCtx_Out->streams[VideoIndex]->codec->height);

 FILE *p = NULL;
 p = fopen("proc_test.yuv", "wb+");
 av_init_packet(&packet);
 int height = pFormatCtx_Out->streams[VideoIndex]->codec->height;
 int width = pFormatCtx_Out->streams[VideoIndex]->codec->width;
 int y_size=height*width;
 while(bCap)
 {
 packet.data = NULL;
 packet.size = 0;
 if (av_read_frame(pFormatCtx_Video, &packet) < 0)
 {
 continue;
 }
 if(packet.stream_index == 0)
 {
 if (avcodec_decode_video2(pCodecCtx_Video, pFrame, &got_picture, &packet) < 0)
 {
 printf("Decode Error.（解码错误）\n");
 continue;
 }
 if (got_picture)
 {
 sws_scale(img_convert_ctx, 
 (const uint8_t* const*)pFrame->data,
 pFrame->linesize, 
 0, 
 pFormatCtx_Out->streams[VideoIndex]->codec->height,
 picture->data,
 picture->linesize);

 if (av_fifo_space(fifo_video) >= size)
 {
 EnterCriticalSection(&VideoSection); 
 av_fifo_generic_write(fifo_video, picture->data[0], y_size, NULL);
 av_fifo_generic_write(fifo_video, picture->data[1], y_size/4, NULL);
 av_fifo_generic_write(fifo_video, picture->data[2], y_size/4, NULL);
 LeaveCriticalSection(&VideoSection);
 }
 }
 }
 av_free_packet(&packet);
 }
 av_frame_free(&pFrame);
 av_frame_free(&picture);
 return 0;
}

DWORD WINAPI AudioCapThreadProc( LPVOID lpParam )
{
 AVPacket pkt;
 AVFrame *frame;
 frame = av_frame_alloc();
 int gotframe;
 while(bCap)
 {
 pkt.data = NULL;
 pkt.size = 0;
 if(av_read_frame(pFormatCtx_Audio,&pkt) < 0)
 {
 continue;
 }

 if (avcodec_decode_audio4(pFormatCtx_Audio->streams[0]->codec, frame, &gotframe, &pkt) < 0)
 {
 av_frame_free(&frame);
 printf("can not decoder a frame");
 break;
 }
 av_free_packet(&pkt);

 if (!gotframe)
 {
 printf("没有获取到数据，继续下一次");
 continue;
 }

 if (NULL == fifo_audio)
 {
 fifo_audio = av_audio_fifo_alloc(pFormatCtx_Audio->streams[0]->codec->sample_fmt, 
 pFormatCtx_Audio->streams[0]->codec->channels, 30 * frame->nb_samples);
 }

 int buf_space = av_audio_fifo_space(fifo_audio);
 if (av_audio_fifo_space(fifo_audio) >= frame->nb_samples)
 {
 EnterCriticalSection(&AudioSection);
 av_audio_fifo_write(fifo_audio, (void **)frame->data, frame->nb_samples);
 LeaveCriticalSection(&AudioSection);
 }
 }
 av_frame_free(&frame);
 return 0;
}



Maybe there is another way to calculate PTS and DTS



I hope whatever the frame rate is,video playback speed is right.Not too fast or too slow.


Subscribe to the whole site
