Full Text:   <638>

Summary:  <224>

CLC number: TP391.41

On-line Access: 2017-04-12

Received: 2016-08-14

Revision Accepted: 2016-12-21

Crosschecked: 2017-03-28

Cited: 0

Clicked: 1799

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2017 Vol.18 No.4 P.545-558

http://doi.org/10.1631/FITEE.1601464


A robust object tracking framework based on a reliable point assignment algorithm


Author(s):  Rong-Feng Zhang, Ting Deng, Gui-Hong Wang, Jing-Lun Shi, Quan-Sheng Guan

Affiliation(s):  School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510641, China; more

Corresponding email(s):   dengting@scut.edu.cn

Key Words:  Local maximal wavelet coefficients, Reliable point assignment, Object tracking, Tracking learning detection (TLD), Kalman filter


Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan . A robust object tracking framework based on a reliable point assignment algorithm[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(4): 545-558.

@article{title="A robust object tracking framework based on a reliable point assignment algorithm",
author="Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan ",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="18",
number="4",
pages="545-558",
year="2017",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1601464"
}

%0 Journal Article
%T A robust object tracking framework based on a reliable point assignment algorithm
%A Rong-Feng Zhang
%A Ting Deng
%A Gui-Hong Wang
%A Jing-Lun Shi
%A Quan-Sheng Guan
%J Frontiers of Information Technology & Electronic Engineering
%V 18
%N 4
%P 545-558
%@ 2095-9184
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1601464

TY - JOUR
T1 - A robust object tracking framework based on a reliable point assignment algorithm
A1 - Rong-Feng Zhang
A1 - Ting Deng
A1 - Gui-Hong Wang
A1 - Jing-Lun Shi
A1 - Quan-Sheng Guan
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 18
IS - 4
SP - 545
EP - 558
%@ 2095-9184
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1601464


Abstract: 
Visual tracking, which has been widely used in many vision fields, has been one of the most active research topics in computer vision in recent years. However, there are still challenges in visual tracking, such as illumination change, object occlusion, and appearance deformation. To overcome these difficulties, a reliable point assignment (RPA) algorithm based on wavelet transform is proposed. The reliable points are obtained by searching the location that holds local maximal wavelet coefficients. Since the local maximal wavelet coefficients indicate high variation in the image, the reliable points are robust against image noise, illumination change, and appearance deformation. Moreover, a kalman filter is applied to the detection step to speed up the detection processing and reduce false detection. Finally, the proposed RPA is integrated into the tracking-learning-detection (TLD) framework with the kalman filter, which not only improves the tracking precision, but also reduces the false detections. Experimental results showed that the new framework outperforms TLD and kernelized correlation filters with respect to precision, f-measure, and average overlap in percent.

基于可靠特征点分配算法的鲁棒性跟踪框架

概要:视觉跟踪是近年来计算视觉最活跃的研究课题之一,已被广泛应用于许多视觉领域。然而,视觉跟踪技术仍然存在挑战,如目标发生光照变化、遮挡、外观形变等。为克服这些技术困难,本文提出基于小波变换的可靠特征点分配(Reliable point assignment, RPA)算法。通过搜索局部最大小波系数(Local maximal wavelet coefficients, LMWC)的位置,获得可靠特征点。在图像中,具有局部最大小波系数之处,表明该处图像信号发生了较大变化,因此,可靠特征点对图像噪声、光照变化和外观形变等情况都具有鲁棒性。此外,在检测中应用卡尔曼滤波器,以提高处理速度并减少误检率。最后,将所提出的RPA与卡尔曼滤波器集成到跟踪-学习-检测(Tracking-learning-detection,TLD)算法框架中,提高了跟踪精度,且降低了误检率。实验结果表明,新框架在精度、f值(f-measure)和平均重叠率(%)等方面均优于TLD和核化相关滤波器(KCF)这两个跟踪算法。

关键词:局部最大小波系数;可靠特征点分配;目标跟踪;跟踪-学习-检测(TLD);卡尔曼滤波器

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Bay, H., Ess, A., Tuytelaars, T., et al., 2008. Speeded-up robust features (SURF). Comput. Vis. Image Understand., 110(3):346-359.

[2]Brox, T., Bruhn, A., Papenberg, N., et al., 2004. High accuracy optical flow estimation based on a theory for warping. European Conf. on Computer Vision, p.25-36.

[3]Cheng, C.W., Ou, W.L., Fan, C.P., 2016. Fast ellipse fitting based pupil tracking design for human-computer interaction applications. IEEE Int. Conf. on Consumer Electronics, p.445-446.

[4]Dalal, N., Triggs, B., 2005. Histograms of oriented gradients for human detection. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.886-893.

[5]Elhamod, M., Levine, M.D., 2013. Automated real-time detection of potentially suspicious behavior in public transport areas. IEEE Trans. Intell. Transp. Syst., 14(2): 688-699.

[6]Elmenreich, W., Koplin, M.A., 2011. Time-triggered object tracking subsystem for advanced driver assistance systems. Elektrotechn. Inform., 128(6):203-208.

[7]Gonzalez, R.C., Woods, R.E., 2002. Digital Image Processing. Prentice Hall, Inc., New Jersey.

[8]Harris, C., Stephens, M., 1988. A combined corner and edge detector. Proc. Alvey Vision Conf., p.147-151.

[9]Henriques, J.F., Caseiro, R., Martins, P., et al., 2015. High-speed tracking with kernelized correlation filters. IEEE Trans. Patt. Anal. Mach. Intell., 37(3):583-596.

[10]Jeong, J.M., Yoon, T.S., Park, J.B., 2014. Kalman filter based multiple objects detection-tracking algorithm robust to occlusion. Proc. SICE Annual Conf., p.941-946.

[11]Jia, C.X., Wang, Z.L., Wu, X., et al., 2015. A tracking-learning-detection (TLD) method with local binary pattern improved. IEEE Int. Conf. on Robotics and Biomimetics, p.1625-1630.

[12]Jung, Y., Yoon, Y., 2015. Behavior tracking model in dynamic situation using the risk ratio EM. Int. Conf. on Information Networking, p.444-448.

[13]Kalal, Z., Mikolajczyk, K., Matas, J., 2010a. Forward-backward error: automatic detection of tracking failures. 20th Int. Conf. on Pattern Recognition, p.23-26.

[14]Kalal, Z., Matas, J., Mikolajczyk, K., 2010b. P-N learning: bootstrapping binary classifiers by structural constraints. IEEE Conf. on Computer Vision and Pattern Recognition, 49-56.

[15]Kalal, Z., Mikolajczyk, K., Matas, J., 2012. Tracking-learning-detection. IEEE Trans. Patt. Anal. Mach. Intell., 34(7):1409-1422.

[16]Kalman, R.E., 1960. A new approach to linear filtering and prediction problems. J. Basic Eng., 82(1):35-45.

[17]Kaur, H., Sahambi, J.S., 2015. Vehicle tracking using fractional order Kalman filter for non-linear system. Int. Conf. on Computing, Communication and Automation, p.474-479.

[18]Kong, H., Akakin, H.C., Sarma, S.E., 2013. A generalized Laplacian of Gaussian filter for blob detection and its applications. IEEE Trans. Cybern., 43(6):1719-1733.

[19]Li, Y., Zhu, J.K., Hoi, S.C.H., 2015. Reliable patch trackers: robust visual tracking by exploiting reliable patches. IEEE Conf. on Computer Vision and Pattern Recognition, p.353-361.

[20]Liu, S., Zhang, T.Z., Cao, X.C., et al., 2016. Structural correlation filter for robust visual tracking. IEEE Conf. on Computer Vision and Pattern Recognition, p.4312-4320.

[21]Liu, T., Wang, G., Yang, Q.X., 2015. Real-time part-based visual tracking via adaptive correlation filters. IEEE Conf. on Computer Vision and Pattern Recognition, p.4902-4912.

[22]Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91-110.

[23]Ning, G.H., Zhang, Z., Huang, C., et al., 2016. Spatially supervised recurrent convolutional neural networks for visual object tracking. arXiv:1607.05781v1.

[24]Prakash, U.M., Thamaraiselvi, V.G., 2014. Detecting and tracking of multiple moving objects for intelligent video surveillance systems. 2nd Int. Conf. on Current Trends in Engineering and Technology, p.253-257.

[25]Redmon, J., Divvala, S., Girshick, R., et al., 2016. You only look once: unified, real-time object detection. IEEE Conf. on Computer Vision and Pattern Recognition, p.779-788.

[26]Sun, X., Yao, H.X., Zhang, S.P., 2010. A refined particle filter method for contour tracking. SPIE, 7744:77441M.

[27]Tarkov, M.S., Dubynin, S.V., 2013. Real-time object tracking by CUDA-accelerated neural network. J. Comput. Sci. Appl., 1(1):1-4.

[28]Viola, P., Jones, M., 2001. Rapid object detection using a boosted cascade of simple features. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.511-518.

[29]Xu, F., Gao, M., 2010. Human detection and tracking based on HOG and particle filter. 3rd Int. Congress on Image and Signal Processing, p.1503-1507.

[30]Yu, H.M., Zeng, X., 2015. Visual tracking combined with ranking vector SVM. J. Zhejiang Univ. (Eng. Sci.), 49(6): 1015-1021 (in Chinese).

[31]Yu, W.S., Tian, X.H., Hou, Z.Q., et al., 2015. Multi-scale mean shift tracking. IET Comput. Vis., 9(1):110-123.

[32]Zhang, R.F., Xiao, H.H., Deng, T., et al., 2016. A robust point detection algorithm based on wavelet transform for visual tracking. Int. Congress on Image and Signal Processing, Biomedical Engineering and Informatics, p.1-5.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE