基于特征融合的粒子滤波目标跟踪
Particle Filter Tracking Based on Feature Fusion
DOI: 10.12677/CSA.2020.105105, PDF,   
作者: 徐国寒*, 沙 洁：中南民族大学电子信息工程学院，湖北 武汉
关键词: 目标跟踪；粒子滤波；颜色特征；形状特征；信息融合；Target Tracking； Particle Filter； Color Feature； Shape Feature； Information Fusion
摘要: 针对复杂场景下单一视觉特征难以准确表征被跟踪目标问题，本文提出了一种自适应融合颜色特征与形状特征的粒子滤波跟踪方法。首先分别提取目标的颜色特征和形状特征，根据当前场景动态调整各特征权重，通过特征加权计算粒子的权值，然后预测目标状态，得到跟踪结果。实验结果表明，该算法能够克服背景噪声、短时间遮挡等干扰，比采用单一特征的跟踪方法具有更好的鲁棒性。
Abstract: In complex scenes, it is difficult for a single kind of visual feature to accurately represent tracked targets. This paper proposes a particle filter tracking method based on adaptively fusing color feature and shape feature. Firstly, we extract the color and shape features. The weight of each feature is then adjusted according to the dynamics of the current scene. The weighted features are used to calculate the weight for particles, by which we predict the target state and obtain the tracking result. Experiments show that the proposed algorithm can overcome background noise and short-term occlusion, showing more robust than those tracking algorithms using only single kind of visual feature.
文章引用：徐国寒, 沙洁. 基于特征融合的粒子滤波目标跟踪[J]. 计算机科学与应用, 2020, 10(5): 1018-1025. https://doi.org/10.12677/CSA.2020.105105

参考文献

[1] Collins, R.T., Lipton, A.J. and Kanade, T. (2000) Introduction to the Special Section on Video Surveillance. IEEE Transaction on Pattern Analysis & Machine Intelligence, 22, 745-746. [Google Scholar] [CrossRef] 
[2] Haritaoglu, I., Harwood, D. and Davis, L.S. (2000) W4: Re-al-Time Surveillance of People and Their Activities. IEEE Transactions on Pattern Analysis & Machine Intelligence, 22, 809-830. [Google Scholar] [CrossRef] 
[3] Erol, A., Bebis, G., Nicolescu, M., et al. (2007) Vision-Based Hand Pose Estimation: A Review. Computer Vision & Image Understanding, 108, 52-73. [Google Scholar] [CrossRef] 
[4] Ganapathi, V., Plagemann, C., Koller, D., et al. (2010) Real Time Motion Capture Using a Single Time-of-Flight Camera. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, 13-18 June 2010, 755-762. [Google Scholar] [CrossRef] 
[5] Gordon, N., Ristic, B. and Arulampalam, S. (2004) Beyond the Kalman Filter: Particle Filters for Tracking Applications. Artech House, London, 1077-2626.
[6] Arulampalam, M.S., Maskell, S., Gordon, N. and Clapp, T. (2002) A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking. IEEE Transaction on Signal Processing, 50, 174-188. [Google Scholar] [CrossRef] 
[7] 杨智雄, 余春超, 严敏, 等. 基于特征融合的粒子滤波红外目标跟踪算法[J]. 红外技术, 2016, 38(3): 211-217.
[8] Dai, Y. and Liu, B. (2016) Robust Video Object Tracking via Bayesian Model Averaging-Based Feature Fusion. Optical Engineering, 55, Article ID: 083102. [Google Scholar] [CrossRef] 
[9] Dou, J.F. and Li, J.X. (2014) Robust Visual Tracking Base on Adaptively Multi-Feature Fusion and Particle Filter. Optik, 125, 1680-1686. [Google Scholar] [CrossRef] 
[10] Carpenter, J., Clifford, P. and Fearnhead, P. (1999) Improved Par-ticle Filter for Nonlinear Problems. IEE Proceedings—Radar Sonar and Navigation, 146, 1-7. [Google Scholar] [CrossRef] 
[11] Pérez, P., Hue, C., Vermaak, J., et al. (2002) Color-Based Probabilis-tic Tracking. Proceedings of European Conference on Computer Vision (ECCV), 1, 661-675. [Google Scholar] [CrossRef] 
[12] Nummiaro, K., Koller-Meier, E. and Van Gool, L. (2003) An Adaptive Color-Based Particle Filter. Image and Vision Computing, 21, 99-110. [Google Scholar] [CrossRef] 
[13] Birchfield, S. (1998) Elliptical Head Tracking Using Intensity Gradients and Color Histograms. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1, 232-237. http://cecas.clemson.edu/~stb/research/headtracker/ [Google Scholar] [CrossRef]