MS's profile - activity

If your paper background is quite plain, you can do some simple binary thresholding to get the pencil lines. Then projecting the lines onto the y axis and doing a min for a range will give you the lowest point of a particular pencil line and you can set some predefined points in y that you are looking for to be logged. Whenever the min(projection(y)) is lower than your predefined line, you trigger the rest of the code. However the assumption is that the various pencil lines do not overlap in the projection space.

Please provide some more information - are you using skin tone to detect hand or shape or something else ?

Hi, I am trying to get the timestamp of a frame from a video that is variable frame rate. I tried to get the time stamps of frames through ffprobe, and it seems that the first frame has a timestamp of 20 msec, the second one 60msec, the third one 80 msec, fourth one 120 msec (so it oscillates between 20msec and 40 msec frame time diff and averages to approximately 30fps). When I use opencv (2.3.1 in Ubuntu 12.04) to query the timestamp in the following piece of code :

for(int frame_count = 0; frame_count < totalFrameCount-1; frame_count ++) { cap >> img_scene; // get a new frame from the file frameTimeStamp = cap.get(CV_CAP_PROP_POS_MSEC); cout << "FrameTimeStamp is " << frameTimeStamp; }

I get timestamps as 20 msec, 40 msec (instead of 60 msec), 60 msec and so on. So it is different that what ffprobe tells me. Is this a known issue ? (framenumber etc. seem to be a known issue, but frame msec seemed to be more stable).

Any help would be great,

Thanks