Moving target tracking algorithm based on improved Kernelized correlation filter

Xing Yunlong; Li Aihua; Cui Zhigao; Fang Hao

doi:10.3788/IRLA201645.S126004

As Kernelized correlation filter is difficult to deal with the problems of illumination changes and total occlusion of the target, a target tracking algorithm based on improved Kernelized correlation filter was proposed in this paper. Firstly, a Gaussian Kernel correlated operator based on the phase characteristics was proposed to improve the ability of the algorithm to adapt to the change of the light intensity. Then, a tracking mechanism of predicting-tracking-correction based on Kalman filter and an occlusion-handling mechanism were proposed to improve the accuracy of tracking while the target was totally occluded. In the aspect of model updating, an adaptive updating strategy was adopted. The models with better tracking effect were used to establish the alternative model and replace the models with bad tracking effect to correct the problems of model migration and characteristics losing. The experimental results show that the improved algorithm can effectively improve the ability to adapt to the illumination changes and keep a good tracking effect while the target is totally occluded.

Moving target tracking algorithm based on improved Kernelized correlation filter

1. The Rocket Foorce University of Engineering,Xi'an 710025,China

Received Date: 2016-01-10

Rev Recd Date: 2016-02-15

Publish Date: 2016-05-25

Key words:

Abstract: As Kernelized correlation filter is difficult to deal with the problems of illumination changes and total occlusion of the target, a target tracking algorithm based on improved Kernelized correlation filter was proposed in this paper. Firstly, a Gaussian Kernel correlated operator based on the phase characteristics was proposed to improve the ability of the algorithm to adapt to the change of the light intensity. Then, a tracking mechanism of predicting-tracking-correction based on Kalman filter and an occlusion-handling mechanism were proposed to improve the accuracy of tracking while the target was totally occluded. In the aspect of model updating, an adaptive updating strategy was adopted. The models with better tracking effect were used to establish the alternative model and replace the models with bad tracking effect to correct the problems of model migration and characteristics losing. The experimental results show that the improved algorithm can effectively improve the ability to adapt to the illumination changes and keep a good tracking effect while the target is totally occluded.

HTML

Reference (15)

[1]	Wu Y, Lim J, Yang M. Online object tracking:a benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2013:2411-2418.
[2]	Kinjal A, Darshak G. A survey on moving object detection and tracking in video surveillance system[J]. International Journal of Soft Computing and Engineering(IJSCE), 2012, 05(6):128-134.
[3]	Hong H, Wang L, Shi Z. Simplified particle PHD filter for multiple-target tracking:algorithm and architecture[J]. Progress in Electromagnetics Research, 2011, 120:481-498.
[4]	Wang F, Ye J. A novel fragments-based tracking algorithm using mean shift[C]//IEEE International Conference on Control Automation Robotics and Vision, 2008:694-698.
[5]	Li Jianfeng, Huang Zengxi, Liu Yiguang. An adaptive Mean-Shift algorithm based on optical-flow field estimation for target tracking[J]. Journal of OptoelectronicsLaster, 2012, 23(10):1996-2002. (in Chinese) 李剑锋, 黄增喜, 刘怡光. 基于光流场估计的自适应Mean-Shift目标跟踪算法[J]. 光电子激光, 2012, 23(10):1996-2002.
[6]	Denman S, Chandran V, Sridharan S. An adaptive optical flow technique for person tracking systems[J]. Pattern Recognition Letters, 2007, 28(10):1232-1239.
[7]	Bolme D, Beveridge J, Draper B, et al. Visual target tracking using adaptive correlation filters[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2010:2544-2550.
[8]	Mahalanobis A, Vijaya K, Casasent D. Minimum average correlation energy filters[J]. Applied Optics, 1987, 26(05):3633-3640.
[9]	Galoogahi H, Sim T, Lucey S. Multi-channel correlation filters[C]//IEEE International Conference on Computer Vision, 2013:3072-3079.
[10]	Rodriguez A, Boddeti V, Vijaya K, et al. Maximum margin correlation filters:a new approach for localization and classification[J]. IEEE Transaction on Image Processing, 2013, 22(02):631-643.
[11]	Henriques J, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2012, 37(3):583-596.
[12]	Shiuh W, Chung K, Shu T. Video target tracking using adaptive kalman filter[J]. Journal of Visual Communication and Image Representation, 2006, 17(6):1190-1208.
[13]	Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2005:886-893.
[14]	Rifkin R, Yeo G, Poggio T. Regularized least-squares classification[J]. Nato Science Series Sub Series Ⅲ Computer and Systems Sciences, 2004, 42(1):93-104.
[15]	Oron S, Hillel A, Avidan S. Extended lucas kanade tracking[C]//European Conference on Computer Vision, 2014:142-156.

Moving target tracking algorithm based on improved Kernelized correlation filter

doi: 10.3788/IRLA201645.S126004

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views