一种抗遮挡的背景感知相关滤波器
An Anti-Occlusion Background-Aware Correlation Filter
摘要: 在目标跟踪的应用中，背景相似的情况下的相关滤波器算法具有较好的鲁棒性，但是容易受到遮挡等因素干扰，导致跟踪失败。为了有效跟踪目标，本文提出了一种抗遮挡的背景感知相关滤波器，该滤波器采用多特征融合、尺度跟踪和引入置信度机制来提高跟踪效果的鲁棒性。在OTB100数据集上测试表明，本文算法在尺度位置变化、相似背景、低分辨率、遮挡等情况下都表现出了较高的准确性，尤其在抗遮挡性中表现出了良好的鲁棒性。
Abstract: In the application of target tracking, the correlation filter algorithm with similar background has good robustness, but it is easily interfered by occlusion and other factors, which leads to tracking failure. In order to effectively track the target, this paper proposes an anti-occlusion background perception correlation filter, which uses multi-feature fusion, scale tracking and confidence mechanism to improve the robustness of tracking effect. The test on OTB100 data set shows that the proposed algorithm shows high accuracy in the case of scale position change, similar background, low resolution, occlusion, etc., especially in anti-occlusion.
文章引用：陆妍, 谢颖华. 一种抗遮挡的背景感知相关滤波器[J]. 计算机科学与应用, 2022, 12(3): 746-754. https://doi.org/10.12677/CSA.2022.123076

参考文献

[1] Zha, Y.F., Bi, D.Y., Yang, Y., et al. (2015) Video Object Tracking Method. National Defense Industry Press, Beijing, 3-5.
[2] 尹明锋. 智能视频监控系统中目标跟踪问题的研究[D]: [博士学位论文]. 南京: 南京理工大学, 2020.
[3] Li, J.C., Bai, P.R., Liu, Q.Y., Cui, X., Zhang, H.H. and Zhu, L.L. (2019) Verified Background-Aware Filters and Re-Detection Tracking Algorithms. 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC), Xiamen, 5-7 July 2019, 742-747.
[4] 何福彤. 基于均值漂移的视频目标跟踪技术研究[D]: [硕士学位论文]. 哈尔滨: 黑龙江大学, 2020.[CrossRef] 
[5] 宋治国. 基于稀疏表示和相关滤波的视觉目标跟踪技术研究[D]: [博士学位论文]. 广州: 华南理工大学, 2020.[CrossRef] 
[6] 昝孟恩, 周航, 韩丹, 杨刚, 许国梁. 粒子滤波目标跟踪算法综述[J]. 计算机工程与应用, 2019, 55(5): 8-17+59.
[7] Bolme, D.S., Beveridge, J.R., Draper, B.A. and Lui, Y.M. (2010) Visual Object Tracking Using Adaptive Correlation Filters. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, 13-18 June 2010, 2544-2550. [Google Scholar] [CrossRef] 
[8] Henriques, J.F., Caseiro, R., Martins, P. and Batista, J. (2012) Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. European Conference on Computer Vision 2012, Springer, Berlin, Heidelberg, 702-715.
[9] Henriques, J.F., Caseiro, R., Martins, P. and Batista, J. (2014) High-Speed Tracking with Kernelized Correlation Filters. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 37, 583-596. [Google Scholar] [CrossRef] 
[10] Dalal, N. and Triggs, B. (2005) Histograms of Oriented Gra-dients for Human Detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 20-25 June 2005, 886-893.
[11] Danelljan, M., Häger, G., Khan, F.S. and Felsberg, M. (2014) Accurate Scale Estimation for Robust Visual Tracking. Proceedings British Machine Vision Conference 2014, Nottingham, 1-5 Septem-ber 2014, 1-14. [Google Scholar] [CrossRef] 
[12] Danelljan, M., Häger, G., Khan, F.S. and Felsberg, M. (2015) Learning Spa-tially Regularized Correlation Filters for Visual Tracking. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 4310-4318. [Google Scholar] [CrossRef] 
[13] Galoogahi, H.K., Sim, T. and Lucey, S. (2015) Correlation Filters with Limited Boundaries. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 4630-4638. [Google Scholar] [CrossRef] 
[14] Galoogahi, H.K., Fagg, A. and Lucey, S. (2017) Learning Background-Aware Correlation Filters for Visual Tracking. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 1144-1152. [Google Scholar] [CrossRef] 
[15] Danelljan, M., Häger, G., Khan, F.S. and Felsberg, M. (2015) Con-volutional Features for Correlation Filter Based Visual Tracking. 2015 IEEE International Conference on Computer Vi-sion Workshop (ICCVW), Santiago, 7-13 December 2015, 621-629. [Google Scholar] [CrossRef] 
[16] Danelljan, M., Robinson, A., Khan, F.S. and Felsberg, M. (2016) Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking. European Conference on Computer Vision 2016, Amsterdam, 11-14 October 2016, 472-488. [Google Scholar] [CrossRef] 
[17] Nam, H. and Han, B. (2015) Learning Multi-Domain Convo-lutional Neural Networks for Visual Tracking. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 4293-4302. [Google Scholar] [CrossRef] 
[18] Wang, L., Ouyang, W., Wang, X. and Lu, H. (2015) Visual Tracking with Fully Convolutional Networks. 2015 IEEE International Conference on Computer Vision (ICCV), Santia-go, 7-13 December 2015, 3119-3127. [Google Scholar] [CrossRef] 
[19] Xu, Y., Li, H., Li, Y., Wang, J., Xu, W., Zhang, Y. and Miao, Z. (2016) Combining Color Attributes for Scale Adaptive Correlation Tracking. 2016 3rd International Conference on In-formation Science and Control Engineering (ICISCE), Beijing, 8-10 July 2016, 267-271. [Google Scholar] [CrossRef] 
[20] Wang, M.M., Liu, Y. and Huang, Z.Y. (2017) Large Margin Object Tracking with Circulant Feature Maps. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 4800-4808. [Google Scholar] [CrossRef] 
[21] 逯彦, 黄庆享. 基于稀疏表示的目标跟踪新算法[J]. 西安科技大学学报, 2020, 40(5): 910-918. [Google Scholar] [CrossRef] 
[22] Ma, C., Yang, X.K., Zhang, C.Y., et al. (2015) Long-Term Correlation Tracking. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 7-12 June 2015, 5388-5396. [Google Scholar] [CrossRef] 
[23] Li, Y. and Zhu, J.K. (2014) A Scale Adaptive Kernel Correla-tion Filter Tracker with Feature Integration. Proceedings of the 13th European Conference on Computer Vision, Zurich, 6-7 and 12 September 2014, 254-265. [Google Scholar] [CrossRef] 
[24] Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O. and Torr. P.H.S. (2016) Staple: Complementary Learners for Real-Time Tracking. 2016 IEEE Conference on Computer Vi-sion and Pattern Recognition (S1063-6919), IEEE, Las Vegas, NV, 1401-1409.