Java Deep Learning Projects

Step 3 – Feeding generated frames into Tiny YOLO model

Now that we know some properties of the clip, we can start generating the frames to be passed to the Tiny YOLO pre-trained model. First, let's look at a less important but transparent approach:

private volatile Mat[] v = new Mat[1]; 
private String windowName = "Object Detection from Video"; 
try { 
    for(int i = 1; i < frameGrabber.getLengthInFrames();     
    i+ = (int)frameRate) { 
                frameGrabber.setFrameNumber(i); 
                frame = frameGrabber.grab(); 
                v[0] = new OpenCVFrameConverter.ToMat().convert(frame); 
                model.markObjectWithBoundingBox(v[0], frame.imageWidth,                                                frame.imageHeight, true, windowName); 
                imshow(windowName, v[0]); 
 
                char key = (char) waitKey(20); 
                // Exit on escape: 
                if (key == 27) { destroyAllWindows(); ...