动态特征和静态特征自适应融合的目标跟踪算法

doi:10.3969/j.issn.1001-2400.2015.06.028

J4 ›› 2015, Vol. 42 ›› Issue (6): 164-172.doi: 10.3969/j.issn.1001-2400.2015.06.028

动态特征和静态特征自适应融合的目标跟踪算法

张立朝;毕笃彦;查宇飞;汪云飞;马时平

(空军工程大学航空航天工程学院，陕西西安 710038)

收稿日期:2014-05-28 出版日期:2015-12-20 发布日期:2016-01-25
通讯作者: 查宇飞
作者简介:张立朝(1990-)，男, 空军工程大学硕士研究生，E-mail: zlichao2012@163.com．
基金资助:
国家自然科学基金资助项目(61472442, 61203268, 61202339)

Research on visual object tracking by fusing dynamic and static features

ZHANG Lichao;BI Duyan;ZHA Yufei;WANG Yunfei;MA Shiping

(School of Aeronautics and Astronautics Engineering, Air Force Engineering Univ, Xi'an 710038, China)

Received:2014-05-28 Online:2015-12-20 Published:2016-01-25
Contact: ZHA Yufei

摘要/Abstract

摘要：

由于大多数目标跟踪算法只采用单一静态特征或单一动态特征对目标建模，但静态特征模型不能描述目标的动态特性，并且很难适应场景复杂、快速移动和旋转等问题；而传统运动光流能够描述局部动态特性，却存在孔径问题．提出一种自适应融合动态特征和静态特征的跟踪方法：通过双向光流预测和误差度量自适应提取动态特征，并提取候选目标区域的静态特征，然后构造融合权重函数有效地融合动态特征和静态特征并以此构造协方差矩阵估计误差椭圆，准确描述目标尺度和方向，实现对目标精确表示；通过on-line参数更新机制对权重分配参数进行更新，实现动态特征和静态特征分配的自适应调节，能够适应目标运动速度的变化和场景变化．实验结果表明，在背景复杂的情况下，当目标快速移动或旋转时，与其他相关算法相比，该算法能够获得更好的跟踪效果．

关键词: 动态特征, 运动度量, 静态特征, 特征融合, 自适应

Abstract:

Traditionally, most tracking algorithms only use the single static feature or single dynamic feature to model the object. The static feature based model can not describe the object's dynamic characteristics and is difficult to adapt to the changing object with a background cluster, abrupt movement and rotations. While the classical optical flow is able to describe local dynamic characteristics, it has aperture issues. Therefore, we present a new tracking method based on fusing the dynamic and static features adaptively: the dynamic feature is extracted by the bidirectional optical flow and error metric adaptively, and is fused with the static feature by the fusion weight efficiently. The fusion weight based covariance is constructed to evaluate error ellipse which describes the object's scale and orientation exactly; the weight assignment parameter is updated by an on-line parameter updating mechanism, which balances the dynamic feature and static feature and ensures the tracking adaptation to the object's velocity and scene changes. Experiments show that the proposed algorithm can achieve better tracking results compared with the related algorithms, on the occasions when the object moves abruptly and rotates with a background cluster.

Key words: dynamic feature, motion metric, static feature, features fusion, adaptation

张立朝;毕笃彦;查宇飞;汪云飞;马时平. 动态特征和静态特征自适应融合的目标跟踪算法[J]. J4, 2015, 42(6): 164-172.

ZHANG Lichao;BI Duyan;ZHA Yufei;WANG Yunfei;MA Shiping. Research on visual object tracking by fusing dynamic and static features[J]. J4, 2015, 42(6): 164-172.

参考文献

［1］侯志强, 韩崇昭. 视觉跟踪技术综述［J］. 自动化学报, 2006, 32(4): 603-617.
Hou Zhiqiang, Han Chongzhao. A Survey of Visual Tracking［J］. Acta Automatica Sinica, 2006, 32(4): 603-617.
［2］ Yang H X, Shao L, Zheng F, et al. Recent Advances and Trends in Visual Tracking［J］. Eurocomputing, 2011, 74(8): 3823-3831.
［3］ Smeulders A, Chu D, Cucchiara R, et al. Visual Tracking: an Experimental Survey［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 36(7): 1442-1468.
［4］ Lowe D G. Scale & Affine Invariant Interest Point Detectors［J］. International Journal of Computer Vision, 2004, 60(1): 63–86.
［5］ Calonder M, Lepetit V, Fua P,et al. BRIEF: Binary Robust Independent Elementary Features［C］//Lecture Notes in Computer Science. Heidelberg: Springer Verlag, 2010: 778-792.
［6］ Leichter I. Mean Shift Trackers with Cross-Bin Metrics［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 695-706.
［7］ Bouguet J Y. Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the Algorithm［Z］. Intel Micro-processor Research Labs, 1999.
［8］ Comaniciu D, Ramesh V, Meer P. Kernel-based Object Tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
［9］ Lim J, Ross D A, Lin R S, et al. Incremental Learning for Visual Tracking［C］//Advances in Neural Information Processing Systems. Canada: NIPC. 2004: 793-800.
［10］ Ning J F, Zhang L, Zhang D, et al. Scale and Orientation Adaptive Mean Shift Tracking［J］. IET Computer Vision, 2012, 6(1): 52-61.
［11］ Mukundan R, Ramakrishnan K R. Moment Functions in Image Analysis: Theory and Applications［M］. Singapore: World Scientific Publishing, 1998.
［12］ Zivkovic Z, Krse B. An EM-like Algorithm for Color-Histogram-Based Object Tracking［C］//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2004: 798-803
［13］董文会, 常发亮, 李天平. 融合颜色直方图及SIFT特征的自适应分块目标跟踪方法［J］. 电子与信息学报, 2013, 35(4): 770-776.
Dong Wenhui, Chang Faliang, Li Tianping. Adaptive Fragments-based Target Tracking Method Fusing Color Histogram and SIFT Features［J］. Jounal of Electronics & Information Technology, 2013, 35(4): 770-776.
［14］ Bousetouane F, Dib L, Snoussi H. Improved Mean Shift Integrating Texture and Color Features for Robust Real Time Object Tracking［J］. The Visual Computer, 2013, 29(3): 155-170.
［15］ Yin H P, Chai Y, Yang S X, et al. An Improved Mean-shift Tracking Algorithm Based on Adaptive Multiple Feature Fusion［C］//Lecture Notes in Electrical Engineering. Heidelberg: Springer Verlag, 2012: 49-62.
［16］ Chen W H, Cao L J, Zhang J G, et al. An Adaptive Combination of Multiple Features for Robust Tracking in Real Scene［C］//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 129-136.
［17］ Chen E, Xu Y, Yang X, et al. Quaternion Based Optical Flow Estimation for Robust Object Tracking［J］. Digital Signal Processing, 2013, 23(1): 118-125.
［18］ Kalal Z, Mikolajczyk K, Matas J. Tracking Learning Detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 6(1):1-14.
［19］ Kalal Z, Mikolajczyk K, Matas J. Forward-backward Error: Automatic Detection of Tracking Failures［C］//Proceedings of International Conference on Pattern Recognition. Piscataway: IEEE, 2010: 2756-2759.
［20］ Babenko B, Belongie S, Yang M H. Visual Tracking with Online Multiple Instance Learning［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE Computer Society, 2009: 983-990.
［21］ Everingham M, Van Gool L, Williams C K, et al. The pascal Visual Object Classes (VOC) Challenge［J］. Interational Journal of Computer Vision, 2010, 88(2): 303-338
［22］ Oron S, Bar-Hillel A, Levi D, et al. Locally Orderless Tracking［J］. International Journal of Computer Vision, 2012, 111(2): 213-228.

[1]	张宇浩,程培涛,张书豪,王秀美. 一种自适应权重学习的轻量超分辨率重建网络[J]. 西安电子科技大学学报, 2021, 48(5): 15-22.
[2]	张飞,马时平,张立朝,何林远,仇祝令,韩永赛. 空间可靠性和相关滤波器联合学习的跟踪算法[J]. 西安电子科技大学学报, 2021, 48(5): 167-177.
[3]	毛昭勇,王亦晨,王鑫,沈钧戈. 面向高速公路的车辆视频监控分析系统[J]. 西安电子科技大学学报, 2021, 48(5): 178-189.
[4]	张书伟,李俊民. 一种复杂监控场景下的人体检测算法[J]. 西安电子科技大学学报, 2021, 48(5): 68-77.
[5]	张智,郑锦. 结合帧间目标回归网络的无人机视频车辆检测[J]. 西安电子科技大学学报, 2021, 48(4): 151-158.
[6]	闫群民,马瑞卿,马永翔,王俊杰. 一种自适应模拟退火粒子群优化算法[J]. 西安电子科技大学学报, 2021, 48(4): 120-127.
[7]	刘天宇,王翥. 一种多样性控制的多目标粒子群算法[J]. 西安电子科技大学学报, 2021, 48(3): 106-114.
[8]	柴艳娜,李坤伦,宋焕生. 智能汽车的入侵检测系统安全研究[J]. 西安电子科技大学学报, 2021, 48(3): 31-39.
[9]	梅淑琳,贾海蓉,王晓刚,武奕峰. 动态特征联合新掩模优化神经网络语音增强[J]. 西安电子科技大学学报, 2021, 48(3): 91-98.
[10]	许述文,王喆祥,水鹏朗. 海杂波背景下雷达目标贝叶斯检测算法[J]. 西安电子科技大学学报, 2021, 48(2): 15-26.
[11]	常文胜,陶海红,代保全,刘彦斌,孙光才. 一种收发互易的频带合成STAP-GMTI系统架构[J]. 西安电子科技大学学报, 2021, 48(2): 156-164.
[12]	孙骞,张家瑞,高岭,王宇翔,杨建锋. 一种改进的边缘层节点健康态势预估方法[J]. 西安电子科技大学学报, 2020, 47(3): 32-39.
[13]	余志超,张瑞红. 结合深度轮廓特征的改进孪生网络跟踪算法[J]. 西安电子科技大学学报, 2020, 47(3): 40-49.
[14]	陈保家,贺王鹏,胡洁,王赓,郭宝龙. 数据驱动的GMC稀疏增强诊断方法[J]. 西安电子科技大学学报, 2019, 46(4): 74-79.
[15]	周雪芹,冯象初,景明利. 一种自适应的拟牛顿投影稀疏信号恢复算法[J]. 西安电子科技大学学报, 2019, 46(3): 14-19.

动态特征和静态特征自适应融合的目标跟踪算法

Research on visual object tracking by fusing dynamic and static features

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0