基于边缘信息的灰度目标跟踪算法

doi:10.13700/j.bh.1001-5965.2014.0827

北京航空航天大学学报 ›› 2015, Vol. 41 ›› Issue (12): 2240-2249.doi: 10.13700/j.bh.1001-5965.2014.0827

基于边缘信息的灰度目标跟踪算法

郑海超¹, 毛峡¹, 梁晓庚^1,2

1. 北京航空航天大学电子信息工程学院, 北京 100191;
2. 中国空空导弹研究院, 洛阳 471000

收稿日期:2014-12-30 修回日期:2015-04-03 出版日期:2015-12-20 发布日期:2016-01-04
通讯作者: 毛峡(1952-),女,浙江义乌人,教授,moukyou@buaa.edu.cn,主要研究方向为计算机视觉、模式识别和人机交互. E-mail:moukyou@buaa.edu.cn
作者简介:郑海超(1986-),男,河北承德人,博士研究生,zhenghaichao_buaa@163.com
基金资助:
高等学校博士学科点专项科研基金(20121102130001);中央高校基本科研业务费专项资金(YWF-14-DZXY-015);航天支撑技术基金

Gray target tracking algorithm based on edge information

ZHENG Haichao¹, MAO Xia¹, LIANG Xiaogeng^1,2

1. School of Electronic and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;
2. China Airborne Missile Academy, Luoyang 471000, China

Received:2014-12-30 Revised:2015-04-03 Online:2015-12-20 Published:2016-01-04

摘要/Abstract

摘要： 提出了一种基于边缘信息的跟踪算法,其可以实现对剧烈变化的灰度目标的精确跟踪.首先,利用基于双同心圆窗口算子的非线性边缘检测算法得到高质量的边缘信息;其次,为了解决单一边缘特征空间不能充分表征目标的难题,提出了一种通过组合边缘图像构建特征空间的方法,以便为目标建模提供充分信息;再次,在构建的特征空间中使用核估计方法对目标进行建模;在目标定位阶段,利用Kalman滤波器对目标进行预估后,再由Mean Shift算法在预估位置邻近区域实现目标定位;最后,提出了一种基于形态学的动态模型更新策略,使得算法不仅可以获得精确的目标区域,还可以实现对目标尺寸和形状变化的自适应.实验结果表明,本算法不仅可以有效跟踪剧烈变化的灰度目标,而且跟踪窗口可以实现对目标尺寸和形状的自适应.

关键词: 计算机视觉, 目标跟踪, 灰度目标, 跟踪算法, 边缘检测, Mean Shift

Abstract: To precisely track the gray targets undergoing drastic changes in the image sequence, a new tracking algorithm based on edge information was proposed. Firstly, obtained by the two-concentric-circular-window operator, a nonlinear edge detection algorithm was proposed to get high quality edge information. Secondly, a novel method to construct feature space by synthesizing edge images was proposed in order to solve the problem that single edge feature space was not able to characterize the target thoroughly. The proposed method provided enough information to construct target model. Then, an approach to construct the target model with the kernel-based estimation method was proposed in constructed feature space. In target localization stage, the target position was preliminarily predicted by Kalman filter, and then the Mean Shift algorithm is utilized to locate the target in the region around the predicted position. Finally, a new dynamic model update strategy based on morphological operations was proposed. It can offer the proposed algorithm the ability to obtain precise target region and automatically adjust to the changing target size and target shape. Experimental results demonstrate that the proposed algorithm can perform well in image sequences where the targets undergo drastic changes. Meanwhile, the proposed algorithm can obtain the precise target region, and the track window can automatically adjust to the changing target size and target shape.

Key words: computer vision, target tracking, gray target, tracking algorithm, edge detection, Mean Shift

中图分类号:

TP391.4

郑海超, 毛峡, 梁晓庚. 基于边缘信息的灰度目标跟踪算法[J]. 北京航空航天大学学报, 2015, 41(12): 2240-2249.

ZHENG Haichao, MAO Xia, LIANG Xiaogeng. Gray target tracking algorithm based on edge information[J]. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2015, 41(12): 2240-2249.

参考文献

[1] 刘彬杰.复杂场景下灰度图像目标的精确跟踪方法研究[D].成都:电子科技大学,2011. Liu B J.Target tracking technology of grayscale image under complex background[D].Chengdu:University of Electronic Science and Technology of China,2011(in Chinese).
[2] Wu Y,Lim J,Yang M H.Online object tracking:A benchmark[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2013:2411-2418.
[3] Wang X,Liu L,Tang Z M.Infrared human tracking with improved mean shift algorithm based on multicue fusion[J].Applied Optics,2009,48(21):4201-4212.
[4] Leichter I.Mean shift trackers with cross-bin metrics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):695-706.
[5] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[6] 孔军,汤心溢,蒋敏,等.基于多尺度特征提取的Kalman滤波跟踪[J].红外与毫米波学报,2011,30(5):446-450. Kong J,Tang X Y,Jiang M,et al.Target tracking based on multi-scale feature extraction Kalman filter[J].Journal of Infrared and Millimeter Waves,2011,30(5):446-450(in Chinese).
[7] Isard M,Blake A.Condensation-conditional density propagation for visual tracking[J].International Journal of Computer Vision,1998,29(1):5-28.
[8] Pan P,Schonfeld D.Video tracking based on sequential particle filtering on graphs[J].IEEE Transactions on Image Processing,2011,20(6):1641-1651.
[9] Ling J G,Liu E,Liang H Y,et al.Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measure[J].Applied Optics,2007,46(16):3239-3252.
[10] Zhang S,Qin Y P,Jin G.Analyzing of mean-shift algorithm in gray target tracking technology[M]//Artificial Intelligence and Computational Intelligence.Berlin:Springer,2011:155-162.
[11] 宋新,王鲁平,王平,等.基于改进均值位移的红外目标跟踪方法[J].红外与毫米波学报,2007,26(6):429-432. Song X,Wang L P,Wang P,et al.IR target tracking based on improved mean shift method[J].Journal of Infrared and Millimeter Waves,2007,26(6):429-432(in Chinese).
[12] 赵倩,袁健全,鲁新平,等.结合目标预估计与Mean Shift理论的运动目标跟踪算法[J].红外与激光工程,2010,39(6):1152-1156. Zhao Q,Yuan J Q,Lu X P,et al.Moving object tracking algorithm based on object estimation and Mean Shift theory[J].Infrared and Laser Engineering,2010,39(6):1152-1156(in Chinese).
[13] 程建,杨杰.一种基于均值移位的红外目标跟踪新方法[J].红外与毫米波学报,2005,24(3):231-235. Cheng J,Yang J.Novel infrared object tracking method based on mean shift[J].Journal of Infrared and Millimeter Waves,2005,24(3):231-235(in Chinese).
[14] Wang Z,Hou Q,Hao L.Improved infrared target-tracking algorithm based on mean shift[J].Applied Optics,2012,51(21):5051-5059.
[15] 贾静平,张艳宁,柴艳妹,等.目标多自由度Mean Shift序列图像跟踪算法[J].西北工业大学学报,2005,23(5):618-622. Jia J P,Zhang Y N,Chai Y M,et al.Making tracking of object in image sequences steady despite complex movement of objects[J].Journal of Northwestern Polytechnical University,2005,23(5):618-622(in Chinese).
[16] Zivkovic Z,Krose B.An EM-like algorithm for color-histogram-based object tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2004:798-803.
[17] 刘兴淼,王仕成,赵静,等.基于自适应核窗宽的红外目标跟踪算法[J].控制与决策,2012,27(1):114-119. Liu X M,Wang S C,Zhao J,et al.Infrared target tracking algorithm based on adaptive bandwidth of Mean Shift[J].Control and Decision,2012,27(1):114-119(in Chinese).
[18] 徐蓉萍,杨磊.红外复杂背景中一种融合两类跟踪框架优点的小目标跟踪算法[J].红外与毫米波学报,2008,27(5):354-360. Xu R P,Yang L.Small target tracking approach combined the merits of two tracking frameworks under infrared complex background[J].Journal of Infrared and Millimeter Waves,2008,27(5):354-360(in Chinese).
[19] Li X H,Zhang T Y,Shen X D,et al.Object tracking using an adaptive Kalman filter combined with mean shift[J].Optical Engineering,2010,49(2):020503-1-020503-3.
[20] Yilmaz A,Javed O,Shah M.Object tracking:A survey[J].Acm Computing Surveys (CSUR),2006,38(4):1-45.
[21] 宋新.红外地面目标的检测、识别与跟踪技术研究及实现[D].长沙:国防科学技术大学,2007. Song X.Research and implementation of infrared ground target detection,recognition and tracking[D].Changsha:National University of Defense Technology,2007(in Chinese).
[22] 梁燕,刘文耀.一种新型非线性边缘检测算法[J].光电子·激光,2003,14(12):1332-1335. Liang Y,Liu W Y.A new nonlinear algorithm for edge detection[J].Journal of Optoelectronics·Laser,2003,14(12):1332-1335(in Chinese).
[23] di Sciasio E,Guaragnella C.Simple nonlinear dual-window operator for edge detection[J].Optical Engineering,2002,41(9): 2181-2185.
[24] Yuan S,Li J H,Han J.An adaptive target tracking algorithm based on multi-feature fusion[C]//Proceedings of International Conference on Biomedical Engineering and Computer Science.Piscataway,NJ:IEEE Press,2010:1-4.
[25] 刁伟鹤,毛峡,常乐.自动目标识别中的图像序列质量评价方法[J].电子与信息学报,2010,32(8):1729-1735. Diao W H,Mao X,Chang L.Quality estimation of image sequence for automatic target recognition[J].Journal of Electronics & Information Technology,2010,32(8):1729-1735(in Chinese).
[26] Sevilla-Lara L,Learned-Miller E.Distribution fields for tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2012:1910-1917.
[27] Wang D,Lu H,Yang M H.Least soft-threshold squares tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2013:2371-2378.
[28] Zhang K,Zhang L,Yang M H.Real-time compressive tracking[M]//Proceedings of European Conference on Computer Vision.Berlin:Springer,2012:864-877.
[29] Zhang K H,Zhang L,Yang M H.Fast compressive tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(10):2002-2015.
[30] Zhang T Z,Ghanem B,Liu S,et al.Robust visual tracking via multi-task sparse learning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2012:2042-2049.

基于边缘信息的灰度目标跟踪算法

Gray target tracking algorithm based on edge information

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	庞策, 单甘霖, 段修生. 多传感器协同识别跟踪多目标管理方法[J]. 北京航空航天大学学报, 2019, 45(8): 1674-1680.
[2]	李惠峰, 易文峰, 程晓明. 基于近似动态规划的目标追踪控制算法[J]. 北京航空航天大学学报, 2019, 45(3): 597-605.
[3]	肖楚晗, 李炯, 雷虎民, 王华吉. 基于AVSIMM算法的高超声速再入滑翔目标跟踪[J]. 北京航空航天大学学报, 2019, 45(2): 413-421.
[4]	欧能杰, 汪圣利, 张直. 基于非等维状态的IMM混合估计方法[J]. 北京航空航天大学学报, 2019, 45(10): 2115-2122.
[5]	王国宏, 白杰, 孙殿星. 速度欺骗干扰下的机动目标跟踪技术[J]. 北京航空航天大学学报, 2018, 44(7): 1359-1370.
[6]	刘畅, 杨锁昌, 汪连栋, 张宽桥. 基于自适应强跟踪CQKF的目标跟踪算法[J]. 北京航空航天大学学报, 2018, 44(5): 982-990.
[7]	周卫东, 刘璐, 唐佳. 基于模糊逻辑的交互式多模型滤波算法[J]. 北京航空航天大学学报, 2018, 44(3): 413-419.
[8]	张凯, 熊家军, 付婷婷, 席秋实. 基于耦合气动参数的HGV多模型估计[J]. 北京航空航天大学学报, 2018, 44(10): 2156-2164.
[9]	甘林海, 刘进忙, 王刚, 李松. 多模型GGIW-GLMB算法跟踪机动群目标[J]. 北京航空航天大学学报, 2018, 44(10): 2185-2192.
[10]	朱日东, 杨小远, 王敬凯. 基于傅里叶域卷积表示的目标跟踪算法[J]. 北京航空航天大学学报, 2018, 44(1): 151-159.
[11]	滑维鑫, 慕德俊, 郭达伟, 刘航. 基于目标性权值度量的多示例学习目标跟踪[J]. 北京航空航天大学学报, 2017, 43(7): 1364-1372.
[12]	刘玉双, 赵剡, 吴发林. 基于外定界椭球集员估计的纯方位目标跟踪[J]. 北京航空航天大学学报, 2017, 43(3): 497-505.
[13]	汪溁鹤, 陈裕雄, 马世龙, 吕江花. 实时鲁棒的频域空间目标跟踪方法[J]. 北京航空航天大学学报, 2017, 43(12): 2457-2465.
[14]	石泉, 李景文, 杨威, 曾虹程, 张豪杰. 基于小波变换的多方位角SAR图像融合方法[J]. 北京航空航天大学学报, 2017, 43(10): 2135-2142.
[15]	袁常顺, 王俊, 向洪, 魏少明, 张耀天. 非线性量测下自适应噪声协方差PHD滤波[J]. 北京航空航天大学学报, 2017, 43(1): 53-60.