论文部分内容阅读
为了解决红外序列图像目标跟踪尺度更新问题,提出了一种基于kalman-meanshift的自适应跟踪算法.在meanshift算法的基础上,利用卡尔曼滤波器预测目标匹配的起始位置,并利用互信息量与目标尺寸之间的关系,增加一个跟踪窗口尺度更新项,对运动目标,特别是尺寸变化的目标进行自适应跟踪.实验表明该算法提高了meanshift跟踪算法的适应性,有效地解决了长时间跟踪过程中尺度变化目标定位困难的问题.“,”In order to solve the problem of scale updating in target tracking for infrared sequences images, an adaptive tracking algorithm based on Kalman-Mean shift method is proposed. Based on the Mean shift algorithm,the starting position of target matching is predicted by Kalman filter at present,and then A scale updating item of tracking window is appended in the mean shift algorithm based on the relation between mutual information and the object scale. Through the scale updating, the moving object, especially the object of scale variance, is adaptively tracked. Experimental results demonstrate that the adaptability of Mean shift method is enhanced by the improved algorithm, which is effectively applied in the tracking problem for the object of scale variance in the process of Long time tracking.