The most of the time the camera is moving very fast and since I compare frame x with frame x+y (y >= 5) the differences are more obvious, the problem is when the camera is not moving fast. While this is the result if I "cv::substract" two frames with very small movement of the camera: For example this is the result if I "cv::substract" two pseudo identically frames: But it is not very stable, I have videos from many different endoscope processors, cameras and grabbers. This was the code which worked the best so far. differences should be very small and easy to remove with median blur if image is totally black, it is not a screenshot, since parts of interest always have light reflection create binary image, shows only light reflection (landmarks) everything else is to dark So far the problem, time for a little code: // init mPrev with last elementĬv::Mat mPrev = cv::imread(imagePaths)(*rect).clone() ĬvtColor(mPrev, mPrev, cv::COLOR_BGR2GRAY)
I guess depending of the key frame in the video encoding process, the difference between those "identical" images is sometimes 0 and sometimes "huge". Since those image have been compressed/encoded they have a loss. If I take a look for those images, the images look really the same, I can not tell the difference, but the computer can. The idea now is to compare image x and image x+1 (or + y) and see if they are the "same" and if so, a screenshot was taken. This works just fine and the result is a folder with all the images in a high quality. So in the first place I extracted the image of the video: ffmpeg -hwaccel cuvid -c:v h264_cuvid -i '/myVideo.mkv' -vf "hwdownload,format=nv12" -start_number 0 -vsync vfr -q:v 1 '/myFrames/%05d.jpg' I'd like to know when those screenshots are made. You can see this in the video because for round about one second the image is not moving, so a couple of frames show the "same". I have H264 encoded video files, those files show records of a colonoscopy/gastroscopy.ĭuring the examination, the exterminator can make some kind of screenshot. There're several posts with a similar headline, so let me describe my problem first.
This sounds like an easy task, but I already spent hours on it.
0 kommentar(er)
