Project DetailsTable tennis is a fast game that requires quick reactions and great hand-eye coordination. Many of the points that are scored during the game are a direct result of a good serve which relies heavily on the strategic use of spin. This project aims to leverage smartphone slow-motion cameras and image processing techniques to analyze and quantify the spin of a table tennis ball during service. We use YOLO v7 for object detection on slow-motion videos in which the ball is uniquely patterned for effective feature detection. Additionally, we apply BRIEF feature descriptor and brute-force matching algorithm which we use to extract matching features across frames. Then, we transform these features to quaternions which enable estimating the spin via an optimization process using the gradient descent algorithm.
We demonstrate our method on videos of ping-pong servs that we collect using a smart phone camera. The tests and results that we present consider relatively low spin speed due to the smart phone camera’s technological limitations, specifically limited frames per second (FPS). However, our method holds true irrespective of the camera’s FPS and could thus be applied to high-spin scenarios as well, given a good enough camera.
