张颖,李孟歆,英宇

• 1:沈阳建筑大学信息与控制工程学院

摘要(Abstract)：

智能视频监控系统中的目标跟踪问题存在许多干扰因素,其中运动目标运动时的动态干扰及大面积遮挡问题是影响跟踪失败的最主要的原因。此外,光照和颜色近似干扰问题也是影响跟踪准确度的主要因素。为了达到运动目标的抗干扰及准确跟踪,在Meanshift算法完成目标准确跟踪的基础上,提出一种基于双重判别的自适应跟踪算法,将Meanshift算法与Kalman滤波算法相结合,在出现长时间大面积遮挡及动态背景干扰、光照,颜色近似干扰的情况下,完成目标的准确跟踪。实验结果表明,提出的方法有较好的稳定性和准确性。

关键词(KeyWords)： 目标跟踪;Meanshift算法;Bhattacharrya系数;Kalman滤波;双重判别;抗遮挡

Abstract:

Keywords:

基金项目(Foundation): 住宅与城乡建设部项目(2015-K8-011);; 辽宁省教育厅项目(L2013225)~~

作者(Author): 张颖,李孟歆,英宇

DOI: 10.16652/j.issn.1004-373x.2018.17.013

参考文献(References)：

• [1]WALIA G S,KAPOOR R.Robust object tracking based upon adaptive multi-cue integration for video surveillance[J].Multimedia tools&applications,2016,75(23):1-27.
• [2]ALI A,JALIL A,AHMED J,et al.Correlation,Kalman filter and adaptive fast mean shift based heuristic approach for robust visual tracking[J].Signal image and video processing,2015,9(7):1567-1585.
• [3]ASGARIZADEH M,POURGHASSEM H.A robust object tracking synthetic structure using regional mutual information and edge correlation-based tracking algorithm in aerial surveillance application[J].Signal image and video processing,2015,9(1):175-189.
• [4]PREVITALI F,BLOISI D D,IOCCHI L.A distributed approach for real-time multi-camera multiple object tracking[J].Machine vision and applications,2017,28(1):1-10.
• [5]DUBUISSON S,GONZALES C.A survey of database for visual tracking[J].Machine vision and applications,2016(27):23-52.
• [6]BADENAS J,SANCHIZ J M,PLA F.Motion-based segmentation and region tracking in image sequences[J].Pattern recognition,2001,34(3):661-670.
• [7]ROWGHANIAN V,ASL K A.Non iterated mean shift and particle filtering[C]//2014 Iranian Conference on Electrical Engineering.Piscataway:IEEE,2014:226-231.
• [8]HWANG J P,BAEK J,CHOI B,et al.A novel part-based approach to mean-shift algorithm for visual tracking[J].International journal of control,automation and systems,2015,13(2):443-453.
• [9]朱钾,李化.一种基于Meanshift算法的目标跟踪改进[J].中北大学学报,2016,37(6):633-637.ZHU J,LI H.An improved Meanshift algorithm for target tracking[J].Journal of North University of China,2016,37(6):633-637.
• [10]ROWGHANIAN V,ANSARI-ASL K.Object tracking by mean shift and radial basis function neural networks[J].Journal of real-time image processing,2015(8):1-18.