2020-09-30 00:36:14 -0600 received badge ● Student (source) 2014-03-22 20:18:00 -0600 asked a question frame coherence in feature detection Summary: Given an input video steam, how to we solve the problem of features not getting detected intermittently. One can possibly do a more robust feature detection. But if the input video stream is noisy or ill-illuminated, then even robust feature detection can cause intermittent failures in feature detection from frame to frame. Is there a general method where by we use the previous frame's features if detection fails for a frame? Could somebody please point me to the general direction (theory and practice) of solving this? Specific case: We are trying to detect a big circular object in the video stream using the code below. We employ HoughCircle-s. The code is given below. The output green circle flickers from frame to frame.  int main(int argc, char **argv) { VideoCapture cap(0); namedWindow( "video"); bool firstWrite = true; for(;;) { Mat frame; cap >> frame; if( frame.empty() ) break; Mat image, tempImage, grayImage; cvtColor(frame, tempImage, CV_BGR2GRAY); pyrDown(tempImage, grayImage, Size(frame.cols/2, frame.rows/2)); pyrDown(frame, image, Size(frame.cols/2, frame.rows/2)); vector circles; HoughCircles( grayImage, //input image circles, //output circles CV_HOUGH_GRADIENT, 1, // grayImage.rows/8, // 250, //upperThresholdForInternalCannyEdgeDetect 50, //thresholdForCenterDetect 0, //minRadius 100 //maxRadius, ); if(circles.size()>0) { //draw only the first circle Point circlePoint( round(circles[0][0]), round(circles[0][1])); double circleRadius = circles[0][2]; circle( image, circlePoint, circleRadius, Scalar(0, 255, 0), -1, 8, 0); if(firstWrite) { //write only one-time imwrite( "detected.jpg", image ); firstWrite = false; } } imshow("video", image); } }  2014-03-20 07:54:45 -0600 received badge ● Editor (source) 2014-03-20 07:51:07 -0600 asked a question suggestion for a suitable android device Hi, I am starting to develop opencv applications in android. (AR, object tracking, feature detection etc) Could you please suggest a suitable device (tablet preferred).? What do you say about Nexus 7 from Google by Asus (32 GB)? It has a tegra 3.0 chip, so should be able to support neon. It doesn't have any memory expansion slot? The price looks reasonable. Anybody developing opencv applications in a google nexus 7? -thanks -koshy 2014-02-17 19:33:18 -0600 asked a question suggestion for a suitable android device I am starting to develop opencv applications , face detection, object tracking, AR etc in android tablets. What would be a good tablet device to buy?