A target color kernel correlation tracking algorithm for UAVs

Qu Yunjie; Mo Hongwei; Wang Changhong

doi:10.3788/IRLA201847.0326001

The CSK algorithm was used to extract a least square classification of moving objects from image fragments in this paper, and the multichannel color features was introduced to calibrate the moving objects. Through the cyclic hypothesis of periodicity of the kernel function in the current image fragments, the CSK algorithm was applied to compensate the lack of target gray-level features describing capacity with CSK algorithm in some extent. The PCA was used to reduce the feature dimension, remove feature redundant information, improve the updating speed of classifier parameters. The problem of moving target tracking could be solved when CSK algorithm classifier parameters were updated linearly and could not adapt to large changes of target. Experiments were performed on the algorithm dataset of the benchmark test platform and the dataset of test data. The experimental results of target color kernel tracking algorithm (TCKCT) show that the algorithm has a better tracking effect in the case of the illumination changing, the background clutter, the target deformation existing, the target moving velocity is faster and the target motion amplitude is larger. The experimental results of UAV tracking remote control car further verify the characteristics of TCKCT algorithm and good real-time performance can meet the target tracking requirements of UAV. It has a good practical application prospect.

A target color kernel correlation tracking algorithm for UAVs

1. School of Astronautics,Harbin Institute of Technology,Harbin 150006,China;

2. College of Automation,Harbin Engineering University,Harbin 150001,China

Received Date: 2017-10-31

Rev Recd Date: 2017-11-30

Publish Date: 2018-03-25

Key words:

Abstract: The CSK algorithm was used to extract a least square classification of moving objects from image fragments in this paper, and the multichannel color features was introduced to calibrate the moving objects. Through the cyclic hypothesis of periodicity of the kernel function in the current image fragments, the CSK algorithm was applied to compensate the lack of target gray-level features describing capacity with CSK algorithm in some extent. The PCA was used to reduce the feature dimension, remove feature redundant information, improve the updating speed of classifier parameters. The problem of moving target tracking could be solved when CSK algorithm classifier parameters were updated linearly and could not adapt to large changes of target. Experiments were performed on the algorithm dataset of the benchmark test platform and the dataset of test data. The experimental results of target color kernel tracking algorithm (TCKCT) show that the algorithm has a better tracking effect in the case of the illumination changing, the background clutter, the target deformation existing, the target moving velocity is faster and the target motion amplitude is larger. The experimental results of UAV tracking remote control car further verify the characteristics of TCKCT algorithm and good real-time performance can meet the target tracking requirements of UAV. It has a good practical application prospect.

HTML

Reference (18)

[1]	You Peihan, Hu Yu, Sheng Ping, et al. A self-adjust image matching tracking system design based on DSP and FPGA[J]. Journal of Projectiles, Rockets, Missiles and Guidance,2013, 33(5):16-22. (in Chinese)游培寒, 胡瑜, 盛平, 等. 一种基于DSP和FPGA的自适应模版匹配跟踪系统设计[J]. 弹箭与制导学报, 2013, 33(5):16-22.
[2]	Jiang Xuejun, Wan Xiaodong. Research on target tracking algorithm for template drift correction[J]. Modern Computer (Professional Edition), 2013, 24(16):25-29. (in Chinese)姜学军,万晓东. 模版漂移纠正的目标跟踪算法研究[J]. 现代计算机(专业版), 2013, 24(16):25-29.
[3]	Adam A, Rivlin E, Shimshoni I. Robust fragments-based tracking using the integral histogram[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2006.
[4]	He S, Yang Q, Lau R, et al. Visual tracking via locality sensitive histograms[C]//2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2013.
[5]	Zhang K, Zhang L, Yang M. Real-time compressive tracking[C]//Computer Vision-ECCV, 2012:864-877.
[6]	Yu Jizhou, Liu Huixia, Liu Chengyu, et al. Application of AMAUKF on the condition of target re-tracked by UAV[J]. Computer Measurement Control, 2012, 20(2):516-519. (in Chinese)余霁洲, 刘慧霞, 刘承禹,等. AMAUKF应用于无人机跟踪目标再捕获研究[J]. 计算机测量与控制, 2012, 20(2):516-519.
[7]	Sevilla-Lara L, Learned-Miller E. Distribution fields for tracking[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2012.
[8]	Dong Liang. Theory and method of video multi-target tracking[D]. Xi'an:Xidian University, 2014. (in Chinese)董亮. 视频多目标跟踪的理论与方法[D].西安:西安电子科技大学, 2014.
[9]	Zhong W, Lu H, Yang M H. Robust object tracking via sparsity-based collaborative model[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2012.
[10]	Zhang K, Zhang L, Yang M, et al. Fast tracking via spatio-temporal context learning[C]//ECCV, 2014.
[11]	Zhang Miaohui, Xin Ming, Yang Jie. Adaptive multi-feature tracking in particle swarm optimization based particle filter framework[J]. Journal of Systems Engineering and Electronics, 2012, 23(5):775-783.
[12]	Dai Fenglin. An object free adaptive multi view tracking system[D]. Shanghai:Fudan University, 2012. (in Chinese)戴凤麟. 无标定的自适应多视角跟踪系统[D]. 上海:复旦大学, 2012.
[13]	Zhao Lingling. Research on particle filter and probability hypothesis density filtering in target tracking[D]. Harbin:Harbin Institute of Technology, 2011. (in Chinese)赵玲玲. 目标跟踪中的粒子滤波与概率假设密度滤波研究[D]. 哈尔滨:哈尔滨工业大学, 2011.
[14]	Kalal Z, Matas J, Mikolajczyk K. P-N learning:Bootstrapping binary classifiers by structural constraints[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2010.
[15]	Wu Y, Lim J, Yang M H. Online object tracking:A benchmark[C]//2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2013.
[16]	Scholkopf B, Smola A J. Learning with Kernels:Support Vector Machines, Regularization, Optimization, and Beyond[M]. Cambridge:The MIT Press, 2002.
[17]	Liu Y, Zhang D, Lu G, et al. Region-based image retrieval with high-level semantic color names[C]//2005 Proceedings of the 11th International Multi-Media Modeling Conference(MMM'05), 2005.
[18]	Kalal Z, Mikolajczyk K, Matas J. Tracking-Learning-Detection[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012, 34(7):1409-1422.

A target color kernel correlation tracking algorithm for UAVs

doi: 10.3788/IRLA201847.0326001

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views