一种动态模板匹配的卡尔曼滤波跟踪方法

Object Tracking Algorithm Based on Combining Dynamics Template Matching and Kalman Filter

在视频跟踪系统中,运动目标检测是实现跟踪的前提和难点。为了能够有效地检测出目标,提出了一种基于动态模板匹配和卡尔曼滤波的目标跟踪算法。首先将前两帧图像差分检测运动目标区域,提取特征点;然后利用卡尔曼滤波在搜索区域中找到与目标模型最匹配的候选目标位置并与当前帧目标模板进行匹配;最后将特征点流失率作为限定阈值,采用模板更新策略动态更新模板。跟踪实验表明,该算法具有很好的匹配精度与实时性,对目标姿态变化、大小变化、遮挡问题等有很好的鲁棒性。

The moving object detection is a prerequisite and difficult point in the video tracking system to realize tracking In order to detect moving object effectively, an object tracking algorithm is proposed based on combining dynamics template matching and Kalman filter. First, make the former two frames inter-difference to get the area of the moving object and extract the feature points. Then, find the best match with the object model candidate object location by Kalman filter in the search area and match it with the object template of the current frame. Finally, the loss rate of feature points will serve as the limited threshold, and we update template according to dynamic template update strategy. Several experiments of the object tracking show that the approach is accurate and fast, and it has a better robust performance during the posture changing, the size changing and the shelter instance.