一种改进的核相关滤波目标跟踪方法研究  

An improved kernel correlation filter object tracking method

作　　者：朱伟杰 唐晶磊[1] 王栋 冀马超 ZHU Wei-jie;TANG Jing-lei;WANG Dong;JI Ma-chao(College of Information Engineering,Northwest A＆F University,Yangling 712100,China;College of Computer Science and Engineering,Northeastern University,Shenyang 110169,China)

机构地区：[1]西北农林科技大学信息工程学院,陕西杨凌712100 [2]东北大学计算机科学与工程学院,辽宁沈阳110169

出　　处：《激光与红外》2018年第11期1430-1435,共6页Laser & Infrared

摘　　要：针对目标跟踪领域视频图像序列经常出现遮挡、光照变化和快速移动等难点,提出了一种融合目标上下文信息和超像素级特征的核相关滤波跟踪方法,目标与其周围的信息存在相关性,利用中层视觉特征(超像素)构建目标的上下文滤波模型,在相关滤波框架下,实现对目标的快速训练和定位。实验结果表明,和其他相关滤波类算法相比,所提出的算法在处理以上跟踪难点时,精确度更高,且鲁棒性更强,同时能以较快的速度运行,满足实时性的要求。Aiming at the difficult points of occlusion, illumination change and fast moving of video sequences in object tracking area, a new filtering method based on object context information and superpixel feature is proposed. There is a correlation between the object and the surrounding information. The object context filter model of the target is construe-ted by using the mid-level vision feature （superpixels）. Under the frame of correlation filtering, the fast training and positioning of the target can be achieved. The experimental results show that compared with other correlation filters al-gorithms, the proposed algorithm has higher accuracy and robustness in dealing with the above tracking difficulties, and can run at a faster speed,meeting the real-time requirements.

关 键 词：视频图像序列 上下文 超像素 目标跟踪 相关滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]