Android Optical Flow with opencv

Im trying to implement optical stream in android using openCV http://code.google.com/p/android-opencv/ . Basically I want to create something like http://www.youtube.com/watch?v=P_Sjn67jIJY . Anyway, because im new to Android development, can anyone be guided somewhere to create something like a video? Ive already installed an opencv port for android and built a cvcamera example using eclipse. Thanks Thanos

+6
source share
4 answers

See this Stanford OpenCV optical stream stream link . Everything should work differently, except that the calls may be slightly different due to problems with 1.x versus 2.x C and C ++.

Just edit the CVCamera example and it should be fast. I made a real-time face detection application for about an hour for CVCamera to work.

+1
source

Although I'm also trying to do the same, in OpenCV4Android, it seems that the optical stream is more supported. Look at the API in org.opencv.video OpenCV Java Documentation I see calcOpticalFlowPyrLK and calcOpticalFlowFarneback. I managed to get calcOpticalFlowFarneback to work (although the results didn’t seem so big, maybe I needed to tweak the parameters) calcOpticalFlowPyrLK turns out to be complicated. I can't seem to convert the key points returned by the FeatureDetector (MatOfKeyPoint) class to the points needed for calcOpticalFlowFarneback (MatOfPoint2f) of another thread

+1
source

Visit http://opencv.willowgarage.com/wiki/Android2.3.0 , OpenCV 2.3.0 Release Candidate has good support for Android. It has an optical stream. He is used

0
source

This code will help you get the optical vectors. And he will track them

@Override public Mat onCameraFrame (CvCameraViewFrame inputFrame) {

mRgba = inputFrame.rgba(); if (mMOP2fptsPrev.rows() == 0) { //Log.d("Baz", "First time opflow"); // first time through the loop so we need prev and this mats // plus prev points // get this mat Imgproc.cvtColor(mRgba, matOpFlowThis, Imgproc.COLOR_RGBA2GRAY); // copy that to prev mat matOpFlowThis.copyTo(matOpFlowPrev); // get prev corners Imgproc.goodFeaturesToTrack(matOpFlowPrev, MOPcorners, iGFFTMax, 0.05, 20); mMOP2fptsPrev.fromArray(MOPcorners.toArray()); // get safe copy of this corners mMOP2fptsPrev.copyTo(mMOP2fptsSafe); } else { //Log.d("Baz", "Opflow"); // we've been through before so // this mat is valid. Copy it to prev mat matOpFlowThis.copyTo(matOpFlowPrev); // get this mat Imgproc.cvtColor(mRgba, matOpFlowThis, Imgproc.COLOR_RGBA2GRAY); // get the corners for this mat Imgproc.goodFeaturesToTrack(matOpFlowThis, MOPcorners, iGFFTMax, 0.05, 20); mMOP2fptsThis.fromArray(MOPcorners.toArray()); // retrieve the corners from the prev mat // (saves calculating them again) mMOP2fptsSafe.copyTo(mMOP2fptsPrev); // and save this corners for next time through mMOP2fptsThis.copyTo(mMOP2fptsSafe); } /* Parameters: prevImg first 8-bit input image nextImg second input image prevPts vector of 2D points for which the flow needs to be found; point coordinates must be single-precision floating-point numbers. nextPts output vector of 2D points (with single-precision floating-point coordinates) containing the calculated new positions of input features in the second image; when OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input. status output status vector (of unsigned chars); each element of the vector is set to 1 if the flow for the corresponding features has been found, otherwise, it is set to 0. err output vector of errors; each element of the vector is set to an error for the corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn't found then the error is not defined (use the status parameter to find such cases). */ Video.calcOpticalFlowPyrLK(matOpFlowPrev, matOpFlowThis, mMOP2fptsPrev, mMOP2fptsThis, mMOBStatus, mMOFerr); cornersPrev = mMOP2fptsPrev.toList(); cornersThis = mMOP2fptsThis.toList(); byteStatus = mMOBStatus.toList(); y = byteStatus.size() - 1; for (x = 0; x < y; x++) { if (byteStatus.get(x) == 1) { pt = cornersThis.get(x); pt2 = cornersPrev.get(x); Core.circle(mRgba, pt, 5, colorRed, iLineThickness - 1); Core.line(mRgba, pt, pt2, colorRed, iLineThickness); } } return mRgba; } 
0
source

Source: https://habr.com/ru/post/891546/


All Articles