我正在尝试使用ffmpeg从视频文件中捕获帧,但我甚至无法获得视频的持续时间。每次当我尝试用pFormatCtx->duration
访问它时我都会得到0.我知道指针已经初始化并包含正确的持续时间,因为如果我使用av_dump_format(pFormatCtx, 0, videoName, 0);
那么我实际上得到的持续时间数据以及其他信息该视频。
这是我使用av_dump_format(pFormatCtx, 0, videoName, 0);
时得到的:
输入#0,avi,来自'futurama.avi':
持续时间:00:21:36.28,开始:0.000000,比特率:1135 kb / s
Stream#0.0:视频:mpeg4(高级简单配置文件),yuv420p,512x384
[PAR 1:1 DAR 4:3],25 tbr,25 tbn,25 tbc
流#0.1:音频:ac3,48000 Hz,立体声,s16,192 kb / s
我不明白为什么av_dum_format
可以显示持续时间而我不能。我查看了函数定义,为了显示持续时间,该函数还使用了pFormatCtx-> duration。当我在main.cpp中调用它们时,其他成员变量也不会显示正确的数据
这是我的main.cpp:
extern "C" {
#include<libavcodec/avcodec.h>
#include<libavformat/avformat.h>
#include<libswscale/swscale.h>
}
int main(int argc, char *argv[]) {
AVFormatContext *pFormatCtx = NULL;
const char videoName[] = "futurama.avi";
// Register all formats and codecs.
av_register_all();
cout << "Opening the video file";
// Open video file
int ret = avformat_open_input(&pFormatCtx, videoName, NULL, NULL) != 0;
if (ret != 0) {
cout << "Couldn't open the video file." << ret ;
return -1;
}
if(avformat_find_stream_info(pFormatCtx, 0) < 0) {
cout << "problem with stream info";
return -1;
}
av_dump_format(pFormatCtx, 0, videoName, 0);
cout << pFormatCtx->bit_rate << endl; // different value each time, not initialized properly.
cout << pFormatCtx->duration << endl; // 0
return 0;
}
我不知道它是否有帮助但是,我在Ubuntu上使用QtCreator并静态链接这些库。
感谢您的帮助。
答案 0 :(得分:3)
持续时间属性为time_base
单位,而不是毫秒或秒。转换为毫秒非常简单,
double time_base = (double)video_stream->time_base.num / (double)video_stream->time_base.den;
double duration = (double)video_stream->duration * time_base * 1000.0;
持续时间现在以毫秒为单位,只需占用一层或每小时即可获得整数毫秒,无论你喜欢什么。
答案 1 :(得分:1)
如何从ffmpeg获取持续时间信息(等等)
前一段时间我和ffmpeg搞砸了,发现学习曲线相当陡峭。因此,即使OP在几个月前提出这个问题,我也会发布一些代码,以防其他人在SO上寻找类似的东西。下面的Open()函数已经完成,但有许多断言,缺乏正确的错误处理方式。
马上,我看到的一个直接差异是我使用了 av_open_input_file 而不是 avformat_open_input 。我也没有使用 av_dump_format 。
计算持续时间可能很棘手,尤其是对于H.264和MPEG-2;看看 durationSec 的计算方法如下。
注意:此示例还使用JUCE C++ Utility Library。
注意2:此代码是ffmpeg tutorial的修改版本。
void VideoCanvas::Open(const char* videoFileName)
{
Logger::writeToLog(String(L"Opening video file ") + videoFileName);
Close();
AVCodec *pCodec;
// register all formats and codecs
av_register_all();
// open video file
int ret = av_open_input_file(&pFormatCtx, videoFileName, NULL, 0, NULL);
if (ret != 0) {
Logger::writeToLog("Unable to open video file: " + String(videoFileName));
Close();
return;
}
// Retrieve stream information
ret = av_find_stream_info(pFormatCtx);
jassert(ret >= 0);
// Find the first video stream
videoStream = -1;
audioStream = -1;
for(int i=0; i<pFormatCtx->nb_streams; i++) {
if (pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_VIDEO && videoStream < 0) {
videoStream = i;
}
if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO && audioStream < 0) {
audioStream = i;
}
} // end for i
jassert(videoStream != -1);
jassert(audioStream != -1);
// Get a pointer to the codec context for the video stream
pCodecCtx=pFormatCtx->streams[videoStream]->codec;
jassert(pCodecCtx != nullptr);
/**
* This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identically 1.
* - encoding: MUST be set by user.
* - decoding: Set by libavcodec.
*/
AVRational avr = pCodecCtx->time_base;
Logger::writeToLog("time_base = " + String(avr.num) + "/" + String(avr.den));
/**
* For some codecs, the time base is closer to the field rate than the frame rate.
* Most notably, H.264 and MPEG-2 specify time_base as half of frame duration
* if no telecine is used ...
*
* Set to time_base ticks per frame. Default 1, e.g., H.264/MPEG-2 set it to 2.
*/
ticksPerFrame = pCodecCtx->ticks_per_frame;
Logger::writeToLog("ticks_per_frame = " + String(pCodecCtx->ticks_per_frame));
durationSec = static_cast<double>(pFormatCtx->streams[videoStream]->duration) * static_cast<double>(ticksPerFrame) / static_cast<double>(avr.den);
double fH = durationSec / 3600.;
int H = static_cast<int>(fH);
double fM = (fH - H) * 60.;
int M = static_cast<int>(fM);
double fS = (fM - M) * 60.;
int S = static_cast<int>(fS);
Logger::writeToLog("Video stream duration = " + String(H) + "H " + String(M) + "M " + String(fS, 3) + "S");
// calculate frame rate based on time_base and ticks_per_frame
frameRate = static_cast<double>(avr.den) / static_cast<double>(avr.num * pCodecCtx->ticks_per_frame);
Logger::writeToLog("Frame rate = " + String(frameRate) );
// audio codec context
if (audioStream != -1) {
aCodecCtx = pFormatCtx->streams[audioStream]->codec;
Logger::writeToLog("Audio sample rate = " + String(aCodecCtx->sample_rate));
Logger::writeToLog("Audio channels = " + String(aCodecCtx->channels));
}
jassert(aCodecCtx != nullptr);
// format:
// The "S" in "S16SYS" stands for "signed", the 16 says that each sample is 16 bits long,
// and "SYS" means that the endian-order will depend on the system you are on. This is the
// format that avcodec_decode_audio2 will give us the audio in.
// open the audio codec
if (audioStream != -1) {
aCodec = avcodec_find_decoder(aCodecCtx->codec_id);
if (!aCodec) {
Logger::writeToLog(L"Unsupported codec ID = " + String(aCodecCtx->codec_id) );
Close();
return; // TODO: should we just play video if audio codec doesn't work?
}
avcodec_open(aCodecCtx, aCodec);
}
// Find the decoder for the video stream
pCodec=avcodec_find_decoder(pCodecCtx->codec_id);
if(pCodec == nullptr) {
jassert(false);
// fprintf(stderr, "Unsupported codec!\n");
//return -1; // Codec not found
}
// Open video codec
ret = avcodec_open(pCodecCtx, pCodec);
jassert(ret >= 0);
// Allocate video frame
pFrame=avcodec_alloc_frame();
jassert(pFrame != nullptr);
// Allocate an AVFrame structure
pFrameRGB=avcodec_alloc_frame();
jassert(pFrameRGB != nullptr);
int numBytes = avpicture_get_size(PIX_FMT_RGB32, pCodecCtx->width, pCodecCtx->height);
jassert(numBytes != 0);
buffer=(uint8_t *)av_malloc(numBytes*sizeof(uint8_t));
jassert(buffer != nullptr);
// note: the pixel format here is RGB, but sws_getContext() needs to be PIX_FMT_BGR24 to match (BGR)
// this might have to do w/ endian-ness....make sure this is platform independent
if (m_image != nullptr) delete m_image;
m_image = new Image(Image::ARGB, pCodecCtx->width, pCodecCtx->height, true);
int dstW = pCodecCtx->width; // don't rescale
int dstH = pCodecCtx->height;
Logger::writeToLog(L"Video width = " + String(dstW));
Logger::writeToLog(L"Video height = " + String(dstH));
// this should only have to be done once
img_convert_ctx = sws_getContext(pCodecCtx->width, pCodecCtx->height, pCodecCtx->pix_fmt, dstW, dstH, PIX_FMT_RGB32, SWS_FAST_BILINEAR, NULL, NULL, NULL);
jassert(img_convert_ctx != nullptr);
setSize(pCodecCtx->width, pCodecCtx->height);
} // Open()
答案 2 :(得分:1)
av_open_input_file()
和avformat_open_input()
之间的差异可能是后者不读取流信息 - 因此duration
未初始化。致电avformat_find_stream_info()
为我解决了这个问题。
我从http://ffmpeg.org/doxygen/trunk/dump_8c_source.html#l00480获取了计算/显示的代码段(请注意,行号可能并且可能会在较新版本中更改)。并添加了一些初始化代码,“它适合我”。希望它有所帮助。
#include <libavutil/avutil.h>
#include <libavformat/avformat.h>
int main()
{
const char const* file = "sample.mpg";
AVFormatContext* formatContext = NULL;
av_register_all();
// Open video file
avformat_open_input(&formatContext, file, NULL, NULL);
avformat_find_stream_info(formatContext, NULL);
// Lower log level since av_log() prints at AV_LOG_ERROR by default
av_log_set_level(AV_LOG_INFO);
av_log(NULL, AV_LOG_INFO, " Duration: ");
if (formatContext->duration != AV_NOPTS_VALUE) {
int hours, mins, secs, us;
int64_t duration = formatContext->duration + 5000;
secs = duration / AV_TIME_BASE;
us = duration % AV_TIME_BASE;
mins = secs / 60;
secs %= 60;
hours = mins / 60;
mins %= 60;
av_log(NULL, AV_LOG_INFO, "%02d:%02d:%02d.%02d\n", hours, mins, secs, (100 * us) / AV_TIME_BASE);
}
return 0;
}
要编译,
gcc -o duration -lavutil -lavformat duration.c