自适应尺度的快速相关滤波跟踪算法.PDFVIP

第29 卷 第3 期 计算机辅助设计与图形学学报 Vol. 29 No.3 2017 年3 月 Journal of Computer-Aided Design Computer Graphics Mar. 2017 自适应尺度的快速相关滤波跟踪算法 1) 1) 2) 马晓楠 , 刘晓利 , 李银伢 1) (南京理工大学瞬态物理国家重点实验室 南京 210094) 2) (南京理工大学自动化学院 南京 210094) (njustmxn@163.com) : 针对常规的相关滤波跟踪算法不能很好地适应目标尺度变化, 而基于尺度金字塔的相关滤波跟踪算法虽然取 得较高的跟踪精度, 却在跟踪速度上大打折扣的问题, 提出一种简单快速的自适应目标尺度的相关滤波跟踪算法. 首 先对目标模板进行对数极坐标变换, 把目标的尺度变化转化为位移信号; 然后对目标模板变换前后分别提取HOG 特征, 并建立位移与尺度的滤波模型; 最后在相关滤波框架下同步跟踪目标的位移与尺度因子, 并将二者融合得到目标跟踪 框. 实验结果表明, 该算法的跟踪精度略低于基于尺度金字塔的相关跟踪算法, 而跟踪速度却达到后者的2 倍以上. ：目标跟踪; 尺度自适应; 相关滤波器; 对数极坐标变换 ：TP391.41 Fast Scale-Adaptive Correlation Tracking Ma Xiaonan1), Liu Xiaoli1), and Li Yinya2) 1) (National Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094) 2) (School of Automation, Nanjing University of Science and Technology, Nanjing 210094) Abstract: Since conventional correlation tracking algorithm cannot adapt to scale variations of the target well, and the scale-pyramid based correlation trackers gain higher precision but sacrifice more speed, this paper pro- poses a simple and efficient scale-adaptive correlation tracking method. Firstly, we converted the target scale to translation signals by taking log-polar transformation. Then, we extracted HOG features from target in Cartesian and log-polar coordinates, and built translation and scale correlation filter models. Finally, the translation and scale factor were tracked synchronously in the framework of correlation filter and fused into tracking bounding rectangle. Experiment results demonstrate that our tracker achieves much little loss in precision comparing with scale-pyramid based correlation trackers, but performs more