广西师范大学学报(自然科学版) ›› 2017, Vol. 35 ›› Issue (3): 37-44.doi: 10.16088/j.issn.1001-6600.2017.03.005

• • 上一篇    下一篇

基于联合直方图的红外与可见光目标融合跟踪

蔡冰, 张灿龙*, 李志欣   

  1. 广西多源信息挖掘与安全重点实验室,广西桂林541004
  • 出版日期:2017-07-25 发布日期:2018-07-25
  • 通讯作者: 张灿龙(1975—),男,湖南娄底人,广西师范大学副教授,博士。E-mail:zcltyp@163.com
  • 基金资助:
    国家自然科学基金(61365009,61462008,61663004);广西自然科学基金(2014GXNSFAA118368,2013GXNSFAA019336,2016GXNSFAA380146);广西师范大学博士科研启动基金(师政科技[2015]13号);广西信息科学实验室中心经费资助课题

Tracking Infrared-visible Target with Joint Histogram

CAI Bing, ZHANG Canlong*, LI Zhixin   

  1. Guangxi Key Lab of Multi-source Information Mining and Security, Guilin Guangxi 541004, China
  • Online:2017-07-25 Published:2018-07-25

摘要: 针对传统单核跟踪算法只能单独跟踪红外或可见光运动目标,导致目标的跟踪效果不是很理想,甚至跟踪失败的问题,本文提出了一种基于均值漂移的红外与可见光目标融合跟踪算法。该算法仍以直方图为目标表示模型,通过将红外目标的相似度和可见光目标的相似度进行加权融合,来构建新的目标函数,并依据核跟踪推理机制导出目标的联动位移公式;最后使用均值漂移程序实现目标的自动搜索。多个视频序列对的测试结果表明,本文提出的融合跟踪方法在处理场景拥簇、光照变化等方面要优于传统的单源跟踪方法,同时具有较高的实时性。

关键词: 均值漂移, 直方图, 融合跟踪, 红外与可见光, 相似度

Abstract: Due to traditional kernel tracking algorithm can only track infrared or visible target, its performance is poor, even unsuccessful. This paper proposes a fusion tracking method for infrared-visible target by using a mean shift algorithm. Firstly, the histogram is still adopted to represent the infrared target and visible target, and the similarity between infrared candidate and its target, and the similarity between visible candidate and its target, are integrated into a novel objective function with different weight. Secondly, similar to mean shift on the objective function, a joint target location-shift formula is induced to the new method. Finally, the optimal target location is gained recursively by applying the mean shift procedure. Experimental results of several infrared-visible image sequences demonstrate that the proposed fusion algorithm is superior to the single-sensor tracking algorithm in handling illumination change and background clutter.

Key words: mean shift, histogram, fusion tracking, infrared-visible, similarity

中图分类号: 

  • TP391.41
[1] COMANICIU D, RAMESH V, MEER P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.DOI:10.1109/TPAMI.2003.1195991.
[2] WU Yi, LIM J, YANG M H. Online object tracking: a benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA: IEEE Computer Society,2013:2411-2418.DOI:10.1109/CVPR.2013.312.
[3] ZHANG Weizheng, JI Jiangao, JING Zhongzhao, et al. Adaptive real-time compressive tracking[C]// International Conference on Network and Information Systems for Computers. Piscataway, NJ:IEEE Press, 2015:236-240. DOI:10.1109/ICNISC.2015.152.
[4] 齐苑辰,吴成东,陈东岳,等. 基于稀疏表达的超像素跟踪算法[J].电子与信息学报,2015,37(3):529-535. DOI:10.11999/JEIT140374.
[5] LEICHTER I. Mean Shift Trackers with cross-bin metrics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):695-706.DOI:10.1109/TPAMI.2011.167.
[6] 张灿龙,唐艳平,李志欣,等. 基于二阶空间直方图的双核跟踪[J].电子与信息学报,2015,37(7):1660-1666. DOI:10.11999/JEIT141321.
[7] ZHANG Shunli, SUI Yao, YU Xin, et al. Hybrid support vector machines for robust object tracking[J]. Pattern Recognition,2015,48(8):2474-2488.DOI:10.1016/j.patcog.2015.02.008.
[8] ZHANG Kaihua, SONG Huihui. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition,2013,46(1):397-411.DOI:10.1016/j.patcog.2012.07.013.
[9] 刘哲,陈恳,郑紫微. 基于HOG与多实例在线学习的目标跟踪算法[J].计算机工程,2015,41(1):158-163. DOI:10.3969/j.issn.1000-3428.2015.01.029.
[10] ROSS D A, LIM J, LIN R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision,2008,77(1/2/3):125-141.DOI:10.1007/s11263-007-0075-7.
[11] MEI Xue, LING Haibin. Robust visual tracking using 1 minimization[C]//IEEE 12th International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2009:1436-1443.DOI:10.1109/ICCV.2009.5459292.
[12] LIU Huaping, SUN Fuchun. Fusion tracking in color and infrared images using joint sparse representation[J]. Science China Information Sciences,2012,55(3):590-599.DOI:10.1007/s11432-011-4536-9.
[13] 赵高鹏,薄煜明,陈益. 多特征提取的红外和可见光目标跟踪方法[J].兵工学报,2011,32(4):445-451.
[14] YUN Xiao, JING Zhongliang, XIAO Gang, et al. A compressive tracking based on time-space Kalman fusion model[J]. Science China Information Sciences,2016,59(1):1-15.DOI:10.1007/s11432-015-5356-0.
[15] LIU Yanjun, TONG Shaocheng, CHEN C L P. Adaptive fuzzy control via observer design for uncertain nonlinear systems with unmodeled dynamics[J]. IEEE Transactions on Fuzzy Systems,2013,21(2):275-288.DOI: 10.1109/TFUZZ.2012.2212200.
[16] XIAO Gang, YUN Xiao, WU Jianmin. A multi-cue mean-shift target tracking approach based on fuzzified region dynamic image fusion[J]. Science China Information Sciences,2012,55(3):577-589. DOI:10.1007/s11432-012-4553-3.
[1] 张灿龙, 苏建才, 李志欣, 王智文. 基于AdaBoost置信图的红外与可见光目标跟踪[J]. 广西师范大学学报(自然科学版), 2018, 36(4): 42-50.
[2] 李子彦, 刘伟铭. 一种基于局部HOG特征的运动车辆检测方法[J]. 广西师范大学学报(自然科学版), 2017, 35(3): 1-13.
[3] 夏海英. 基于改进的SLIC区域合并的宫颈细胞图像分割[J]. 广西师范大学学报(自然科学版), 2016, 34(4): 93-100.
[4] 孙水发, 李乐鹏, 董方敏, 邹耀斌, 陈鹏. 基于迭代阈值的子块部分重叠双直方图均衡算法[J]. 广西师范大学学报(自然科学版), 2013, 31(3): 119-126.
[5] 王峰, 靳小波, 于俊伟, 王贵财. V-最优直方图及其在车牌分类中的应用研究[J]. 广西师范大学学报(自然科学版), 2013, 31(3): 138-143.
[6] 马盈仓, 张美, 崔美英. Frank三角范数的三值模糊逻辑系统的真度理论[J]. 广西师范大学学报(自然科学版), 2011, 29(3): 84-88.
[7] 孟凡辉, 王浩, 方宝富, 彭伟. 可扩展梯度直方图人体检测算法研究与实现[J]. 广西师范大学学报(自然科学版), 2011, 29(3): 168-172.
[8] 沙贝贝, 谢丽聪. 一种基于频繁项集的搜索引擎聚类浏览算法[J]. 广西师范大学学报(自然科学版), 2011, 29(2): 151-155.
[9] 周鑫, 郝志峰, 蔡瑞初, 温雯. 带噪声的文本聚类及其在反垃圾邮件中的应用[J]. 广西师范大学学报(自然科学版), 2011, 29(2): 156-160.
[10] 张新明, 张玉珊, 李振云. 一种改进的矩不变图像分割方法[J]. 广西师范大学学报(自然科学版), 2011, 29(2): 185-190.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报(自然科学版)编辑部
地址:广西桂林市三里店育才路15号 邮编:541004
电话:0773-5857325 E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发