Publikation
A Multiple Hypothesis Approach for a Ball Tracking System
Oliver Birbach; Udo Frese
In: Proceedings of the 7th International Conference on Computer Vision Systems. International Conference on Computer Vision Systems (ICVS-2009), October 13 - September 15, Liège, Belgium, 2009.
Zusammenfassung
This paper presents a computer vision system for tracking and predicting ying balls in 3-D from a stereo-camera. It pursues a "textbook-style" approach with a robust circle detector and probabilistic models for ball motion and circle detection handled by state-of-theart estimation algorithms. In particular we use a Multiple-Hypotheses Tracker (MHT) with an Unscented Kalman Filter (UKF) for each track,handling multiple ying balls, missing and false detections and rackinitiation and termination. The system also performs auto-calibration estimating physical parameters (ball radius, gravity relative to camera, air drag) simply from observing some ying balls. This reduces the setup time in a new environment.