针对异常事件监控的需求,提出一种运动目标跟踪算法。该算法首先运用背景减法检测出运动目标.然后运用SURF(speeded—up robust features)对运动目标进行特征提取和特征匹配,结合扩展卡尔曼滤波器(EKF)实现目标跟踪。实验结果表明,该算法能够有效地解决静态场景下异常事件监控等问题,具有较好的实时性和鲁棒性。
Aiming at the requirement of abnormal event monitoring system, an object tracking algorithm is introduced. The algorithm firstly uses the background subtraction algorithm to detect moving targets, and then uses Speeded-Up Robust Features(SURF)to extract and match features, combined with Extended KalmanFiher (EKF)to track objectives. The experimental results show that the algorithm is an effective solution to the background of change, with good real-time and robustness.