基于相关相似度的在线多示例学习目标跟踪算法
Relative Similarity Based Online Multiple In-stance Learning Algorithm in Object Track-ing
DOI: 10.12677/CSA.2019.92044, PDF,    国家自然科学基金支持
作者: 陈 敏*, 张清华, 陈晓森, 陈江湖, 谢思齐, 陈 思：厦门理工学院计算机与信息工程学院，福建 厦门
关键词: 目标跟踪；多示例学习；相关相似度；在线学习；Object Tracking； Multiple Instance Learning； Relative Similarity； Online Learning
摘要: 目标跟踪是计算机视觉领域的研究热点之一，并得到了广泛的应用。目前许多学者将机器学习方法引入目标跟踪，例如，基于多示例学习的目标跟踪算法(即MIL)已经被提出。然而，传统的MIL跟踪算法在正负样本的选择上存在一定的不稳定性，容易在时间的推移下出现目标漂移的现象。为了克服上述问题，提出了一种简单、有效且高效的基于相关相似度的在线多示例学习目标跟踪算法。该算法通过定义相关相似度来对正包中的样本进行进一步的选择与加权，从而提高目标跟踪的性能。与新近算法的实验对比表明，本文提出的算法在目标跟踪的准确性、精度、鲁棒性等方面均有一定的提高。
Abstract: Object tracking is one of the hot topics in computer vision and has wide applications. At present, many scholars have introduced machine learning methods into target tracking. For example, multiple instance learning (MIL) based object tracking has been proposed. However, the traditional MIL tracking algorithms have some instability under the selection of positive and negative samples, and they are easy to appear the phenomenon of target drifting over time. In order to overcome the above problems, this paper proposes a simple, effective and efficient object tracking algorithm using online multiple instance learning based on relative similarity. The algorithm further selects and weights the samples in the positive bag by defining the relative similarity so as to improve the performance of object tracking. By contrast to the recent algorithms, the experiments show that the algorithm in this paper has a certain increase in accuracy, precision, and the robustness of object tracking.
文章引用：陈敏, 张清华, 陈晓森, 陈江湖, 谢思齐, 陈思. 基于相关相似度的在线多示例学习目标跟踪算法[J]. 计算机科学与应用, 2019, 9(2): 393-405. https://doi.org/10.12677/CSA.2019.92044

参考文献

[1] Babenko, B., Yang, M.H. and Belongie, S. (2011) Robust Object Tracking with Online Multiple Instance Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 1619-1632. [Google Scholar] [CrossRef] 
[2] Black, M.J. and Jepson, A.D. (1998) Eigen Tracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation. IJCV, 26, 63-84.
[3] Avidan, S. (2004) Support Vector Track-ing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 1064-1072. [Google Scholar] [CrossRef] 
[4] Zhang, K. and Song, H. (2013) Real-Time Visual Tracking via Online Weighted Multiple Instance Learning. Pattern Recognition, 46, 397-411. [Google Scholar] [CrossRef] 
[5] Li, H.X., Shen, C.N. and Shi, Q. (2011) Real-Time Visual Tracking Using Compressive Sensing. Computer Vision and Pattern Recognition (CVPR), Providence, RI, 20-25 June 2011, 1305-1312.
[6] Havangi, R. (2017) Target Tracking Based on Improved Unscented Particle Filter with Markov Chain Monte Carlo. IETE Journal of Research, 64, 873-885.
[7] Bertinetto, L., Valmadre, J., Golodetz, S., et al. (2016) Staple: Complementary Learners for Real-Time Tracking. Computer Vision & Pattern Recognition, Las Vegas, 26 June-1 July 2016, 1401-1409.
[8] Grabner, H., Leistner, C. and Bischof, H. (2008) Semi-Supervised On-Line Boosting for Robust Tracking. Computer Vision, Marseille, 12-18 October 2008, 234-237. [Google Scholar] [CrossRef] 
[9] 刘雨情, 肖嵩, 李磊. 在线判别式超像素跟踪算法[J]. 西安电子科技大学学报, 2018, 45(3): 13-17.
[10] Ross, D.A., Lim, J., Lin, R.S., et al. (2008) In-cremental Learning for Robust Visual Tracking. International Journal of Computer Vision, 77, 125-141. [Google Scholar] [CrossRef] 
[11] Mei, X. and Ling, H. (2011) Robust Visual Tracking and Vehicle Classification via Sparse Representation. IEEE Transacti-ons on Pattern Analysis & Machine Intelligence, 33, 2259-2272. [Google Scholar] [CrossRef] 
[12] Vojir, T., Noskova, J. and Matas, J. (2014) Robust Scale-Adaptive Mean-Shift for Tracking. Pattern Recognition Letters, 49, 250-258. [Google Scholar] [CrossRef] 
[13] Lytu, N., Letien, T. and Mai, L. (2017) A Study on Particle Filter Based on KLD-Resampling for Wireless Patient Tracking. Industrial Engineering & Management Systems, 16, 92-102. [Google Scholar] [CrossRef] 
[14] Collins, R.T., Liu, Y. and Leordeanu, M. (2005) Online Selection of Discriminative Tracking Features. IEEE Transactions on Pattern Analysis & Machine Intelligence, 27, 1631-1643. [Google Scholar] [CrossRef] 
[15] Mueller, M., Smith, N. and Ghanem, B. (2017) Context-Aware Correlation Filter Tracking. IEEE Conference on Computer Vision & Pattern Recognition, 1387-1395.
[16] Grabner, H., Grabner, M. and Bischof, H. (2006) Real-Time Tracking via Online Boosting. Proceedings of the British Machine Vision Conference, BMVA, Edinburgh, 47-56.
[17] Bhat, G., Johnander, J., Danelljan, M., et al. (2018) Unveiling the Power of Deep Tracking. European Conference on Computer Vision, Springer, Cham, 493-509.
[18] Cui, Z., Xiao, S., Feng, J., et al. (2016) Recurrently Target-Attending Tracking. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, 1449-1458.
[19] 李义翠, 亓琳, 谭舒昆. 结合PN约束在线半监督boosting目标跟踪算法[J]. 计算机工程与应用, 2017, 53(23): 129-134.
[20] Nam, H., Baek, M. and Han, B. (2016) Modeling and Propagating CNNs in a Tree Structure for Visual Tracking. European Conference on Computer Vision, Amsterdam, 8-16 October 2016, 1-10.
[21] Viola, P., Platt, J.C. and Zhang, C. (2005) Multiple Instance Boosting for Object Detection. In: International Conference on Neural Information Processing Systems, MIT Press, Cambridge, 1417-1424.
[22] Liu, X. and Yu, T. (2015) Gradient Feature Selection for Online Boosting. 11th International Conference on Com-puter Vision, Rio de Janeiro, 14-21 October 2007, 1-8. [Google Scholar] [CrossRef] 
[23] Kalal, Z., Mikolajczyk, K. and Matas, J. (2012) Tracking-Learning-Detection. IEEE Transactions on Pattern Analysis & Machine Intelligence, 34, 1409-1422. [Google Scholar] [CrossRef] 
[24] Wu, Y., Lim, J. and Yang, M.H. (2015) Object Tracking Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1834-1848. [Google Scholar] [CrossRef] 
[25] Zhang, K., Zhang, L. and Yang, M.H. (2012) Real-Time Compressive Tracking. In: European Conference on Computer Vision, Springer-Verlag, Berlin, 864-877.
[26] Henriques, J.F., Caseiro, R., et al. (2012) Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. In: Computer Vision, Springer, Berlin, Heidelberg, 702-715.
[27] Grabner, H. and Bischof, H. (2006) On-Line Boosting and Vision. IEEE Computer Society Conference on Computer Vision & Pattern Recognition, New York, 17-22 June 2006, Vol. 1, 260-267.
[28] Wu, Y., Lim, J. and Yang, M.H. (2013) Online Object Tracking: A Benchmark. IEEE Conference on Computer Vision and Pattern Recognition, Portland, 23-28 June 2013, Vol. 9, 2411-2418.