跟踪框自适应的尺度变化目标跟踪算法  

Algorithm of scale change objects tracking with adaptive bandwidth

作　　者：李武[1] 侯志强[1] 魏国剑[1] 余旺盛[1] 

机构地区：[1]空军工程大学信息与导航学院,陕西西安710077

出　　处：《山东大学学报（工学版）》2014年第2期28-34,共7页Journal of Shandong University（Engineering Science）

基　　金：国家自然科学基金资助项目(61175029);陕西省自然科学基金资助项目(2011JM8015)

摘　　要：为解决尺度变化的目标跟踪问题,借助于对数极坐标变换良好的尺度旋转不变性,提出一种基于椭圆对数极坐标变换域下目标跟踪算法。算法利用一种显著性加权的Mean Shift进行空间定位,进而将目标区域变换到椭圆对数极坐标系下并沿尺度轴进行积分,通过一维的最大相关匹配确定目标的尺度参数。实验结果表明,该算法不仅空间跟踪误差较低,而且能够较稳定地适应目标尺度变化,具有较好的鲁棒性。Taking advantage of the invariant characters for translation and rotation of the Log-polar transformation,a scale tracking method based on the ellipse log-polar transform was investigated to resolve the problem of scale change object tracking. Firstly,a saliency weighted mean shift was presented to locate the object＆#39;s spatial orientation,then the candidate object region was translated to the ellipse log-polar transformation and integrated along the scale axis. The new proposed method estimated the target＆#39;s scale parameters according to the maximum correlation coefficient in the transform domain. Experimental results demonstrated that the algorithm could adapt to the object＆#39;s scale changes and the tracking error was lower. Compared with the traditional,it had a better robustness.

关 键 词：椭圆对数极坐标变换 显著性加权 均值漂移 相关匹配 尺度变化 目标跟踪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]