基于粒子滤波的视觉目标跟踪算法
Visual Target Tracking Algorithm Based on Particle Filter
DOI: 10.12677/CSA.2018.85070, PDF,   
作者: 陈思萌*, 邓 雨: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Target Tracking Particle Filter Color Characteristics
摘要: 随着社会智能化的发展,视觉目标跟踪成为计算机视觉领域的研究热点之一。在目标跟踪过程中,由于目标自身及环境的变化使得准确跟踪目标变得十分困难。在基本粒子滤波框架下,本文主要研究了一种基于颜色特征的粒子滤波视觉目标跟踪算法。通过引入核函数的RGB颜色空间对目标进行鲁棒的表达,为了适应跟踪过程中的目标变化,利用实时的观测信息对目标模板进行更新。实验表明,基于颜色特征的粒子滤波算法对光照变化和动态干扰具有较强的鲁棒性。
Abstract: With the development of social intelligence, visual target tracking has become one of the research hotspots in the field of computer vision. In the process of target tracking, it becomes very difficult to track the target accurately because of the change of the target itself and the environment. In the basic particle filter framework, this paper mainly studies a particle filter visual target tracking algorithm based on color features. By introducing the RGB color space of kernel function to the robust expression of the target, in order to adapt to the target change in the tracking process, the target template is updated with real-time observation information. Experiments show that the particle filter algorithm based on color features has strong robustness to light changes and dynamic interference.
文章引用:陈思萌, 邓雨. 基于粒子滤波的视觉目标跟踪算法[J]. 计算机科学与应用, 2018, 8(5): 619-626. https://doi.org/10.12677/CSA.2018.85070

参考文献

[1] Kalman, R.E. (1961) A New Approach to Linear Filtering and Prediction Problems. Journal of Basic Engineering, Transactions ASME Series, 83, 95-108. [Google Scholar] [CrossRef
[2] Reid, D.B. (1979) An Algorithm for Tracking Multiple Targets. IEEE Transactions on Automatic Control, 24, 843-854. [Google Scholar] [CrossRef
[3] Makris, D. and Ellis, T. (2005) Learning Semantic Scene Models from Observing Activity in Visual Surveillance. IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society, 35, 397-408. [Google Scholar] [CrossRef
[4] Kausler, B.X., Schiegg, M., Andres, B., et al. (2012) A Dis-crete Chain Graph Model for 3d+t Cell Tracking with High Misdetection Robustness. Computer Vision—ECCV 2012, Springer, Berlin, Heidelberg, 144-157.
[5] Xiang, J., Sang, N., Hou, J.H., Huang, R. and Gao, C.X. (2016) Mul-ti-Target Tracking Using Hough Forest Random Field. IEEE Transactions on Circuits and Systems for Video Technolo-gy, 26, 2028-2042. [Google Scholar] [CrossRef
[6] 侯建华, 黄奇, 项俊, 郑桂林. 一种尺度和方向适应性的Mean Shift跟踪算法[J]. 中南民族大学学报(自然科学版), 2015, 34(1): 83-88.
[7] Arulampalam, M., Maskell, S. and Gordon, N. (2002) A Tutorial on Particle Filters for Online Non-Linear/Non-Gaussian Bayesian Tracking. IEEE Transactions on Signal Processing, 50, 174-188. [Google Scholar] [CrossRef
[8] 胡士强, 敬忠良. 粒子滤波算法综述[J]. 控制与决策, 2005, 20(4): 361-365.
[9] Carpenter, J., Clifford, P. and Fearnhead, P. (1999) Im-proved Particle Filter for Nonlinear Problems. IEE Proceedings Radar, Sonar and Navigation, 146, 1-7.
[10] Isard, M. and Blake, A. (1998) Condensation—Conditional Density Propagation for Visual Tracking. International Journal of Computer Vision, 29, 5-28. [Google Scholar] [CrossRef
[11] Isard, M. and Maccormick, J. (2001) BraMBLe: A Bayesian Multiple-Blob Tracker. Proceedings of Eighth IEEE International Conference on Computer Vi-sion, 2, 34-41.
[12] Raja, Y., Mckenna, S.J. and Gong, S. (1998) Tracking and Segmenting People in Varying Lighting Conditions Using Colour. IEEE International Conference on Automatic Face and Gesture Recognition, Nara, 14-16 April 1998, 228-233.
[13] Nummiaro, K., Koller-Meier, E. and Gool, L.V. (2003) An Adaptive Color-Based Particle Filter. Image & Vision Computing, 21, 99-110. [Google Scholar] [CrossRef
[14] Liu, J.S. and Chen, R. (1998) Sequential Monte Carlo Methods for Dynamic Systems. Journal of the American Statistical Association, 93, 1032-1044. [Google Scholar] [CrossRef
[15] Arulampalam, M., Maskell, S. and Gordon, N. (2002) A Tutorial on Particle Filters for Online Non-Linear/Non-Gaussian Bayesian Tracking. IEEE Transactions on Signal Processing, 50, 174-188. [Google Scholar] [CrossRef