Please wait a minute...
Frontiers of Information Technology & Electronic Engineering  2017, Vol. 18 Issue (4): 545-558    DOI: 10.1631/FITEE.1601464
Regular Paper     
基于可靠特征点分配算法的鲁棒性跟踪框架
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
Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510641, China; School of Electronic and Information Engineering, Guangzhou College of South China University of Technology, Guangzhou 510800, China; Information Network Engineering and Research Center, South China University of Technology, Guangzhou 510641, China
 全文: PDF 
摘要: 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    
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.
Key words: Local maximal wavelet coefficients    Reliable point assignment    Object tracking    Tracking learning detection (TLD)    Kalman filter
收稿日期: 2016-08-14 出版日期: 2017-04-12
CLC:  TP391.41  
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
Rong-Feng Zhang
Ting Deng
Gui-Hong Wang
Jing-Lun Shi
Quan-Sheng Guan

引用本文:

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. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 545-558.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/FITEE.1601464        http://www.zjujournals.com/xueshu/fitee/CN/Y2017/V18/I4/545

1 Bay, H., Ess, A., Tuytelaars, T., et al., 2008. Speeded-up robust features (SURF). Comput. Vis. Image Understand., 110(3):346-359.
doi: 10.1016/j.cviu.2007.09.014
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.
doi: 10.1007/978-3-540-24673-2_3
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.
doi: 10.1109/ICCE.2016.7430685
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.
doi: 10.1109/CVPR.2005.177
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.
doi: 10.1109/TITS.2012.2228640
6 Elmenreich, W., Koplin, M.A., 2011. Time-triggered object tracking subsystem for advanced driver assistance systems. Elektrotechn. Inform., 128(6):203-208.
doi: 10.1007/s00502-011-0004-x
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.
doi: 10.5244/C.2.23
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.
doi: 10.1109/TPAMI.2014.2345390
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.
doi: 10.1109/SICE.2014.6935235
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.
doi: 10.1109/ROBIO.2015.7419004
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.
doi: 10.1109/ICOIN.2015.7057942
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.
doi: 10.1109/ICPR.2010.675
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.
doi: 10.1109/CVPR.2010.5540231
15 Kalal, Z., Mikolajczyk, K., Matas, J., 2012. Tracking-learning-detection. IEEE Trans. Patt. Anal. Mach. Intell., 34(7):1409-1422.
doi: 10.1109/TPAMI.2011.239
16 Kalman, R.E., 1960. A new approach to linear filtering and prediction problems. J. Basic Eng., 82(1):35-45.
doi: 10.1115/1.3662552
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.
doi: 10.1109/CCAA.2015.7148423
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.
doi: 10.1109/TSMCB.2012.2228639
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.
doi: 10.1109/CVPR.2015.7298632
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.
doi: 10.1109/CVPR.2016.467
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.
doi: 10.1109/CVPR.2015.7299124
22 Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91-110.
doi: 10.1023/B:VISI.0000029664.99615.94
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.
doi: 10.1109/ICCTET.2014.6966297
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.
doi: 10.1109/CVPR.2016.91
26 Sun, X., Yao, H.X., Zhang, S.P., 2010. A refined particle filter method for contour tracking. SPIE, 7744:77441M.
doi: 10.1117/12.863450
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.
doi: 10.12691/jcsa-1-1-1
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.
doi: 10.1109/CVPR.2001.990517
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.
doi: 10.1109/CISP.2010.5646273
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).
doi: 10.3785/j.issn.1008-973X.2015.06.003
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.
doi: 10.1049/iet-cvi.2014.0077
[1] Xiao-ming Gou, Zhi-wen Liu, Wei Liu, You-gen Xu. 三元数域自适应滤波与跟踪算法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(8): 834-840.
[2] Xie Wang, Mei-qin Liu, Zhen Fan, Sen-lin Zhang. 目标跟踪中一种新的基于H滤波器的噪声统计特征估计方法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(5): 449-457.
[3] Yun-fei Guo, Kong-shuai Fan, Dong-liang Peng, Ji-an Luo, Han Shentu. 改进的变速率粒子滤波及其在机动目标跟踪中的应用[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(11): 985-994.
[4] Peng-fei Qian, Guo-liang Tao, De-yuan Meng, Hao Liu. 用于气动系统的一种改进型直接自适应鲁棒运动跟踪控制器[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(10): 878-891.