基于Kalman滤波与Camshift算法的水面目标跟踪

Water surface target tracking based on Kalman filtering and Camshift algorithm

根据水面监控图像的特点,对运动载体采集到的水面视频图像进行处理,从而实现对运动目标的跟踪。首先,利用Haar分类器检测出水面的运动目标,并用检测结果初始化Camshift跟踪器的搜索窗口;然后,运用Kalman滤波器与Camshift组合算法实现对运动目标的跟踪。其中,利用Kalman滤波算法预测目标在下一帧中出现的位置,Camshift算法用来跟踪目标,以此减小搜索范围,提高跟踪效率。实验结果表明,该算法能够实现对水面运动舰船的检测并进行有效跟踪。

According to the characteristics of the water surface monitoring image,the water surface video images collected by the motion carrier are processed to realize the tracking of the moving target.The Haar classifier is used to detect the moving target on the water surface,and the detection results are used to initialize the search window of Camshift tracker.The Kalman filter and Camshift combination algorithm is used to track the moving targets,in which the Kalman filtering algorithm is used to predict the location of the target appeared in the next frame,and the Camshift algorithm is used to track the targets to reduce the search range and improve the tracking efficiency.The experimental result shows that the algorithm can effectively detect and track the ships on the water surface.