Visual tracking for soccer robot based on adaptive kalman filter

Abstract

Moving object detection and tracking is the base of the soccer robot system. Kalman filter has been used in the estimation of the positions of moving object in soccer robot system. Because of the maneuverability of soccer robot and the uncertainty of the prior estimate of noise, estimation of kalman filter is divergent. Adaptive kalman filter can adjust the parameters of model on line, to get accurate predictor. A real-time adaptive kalman filter tracking model is applied in soccer robot system in this paper. The efficiency of the algorithm is validated by the experimental results.