Academic Journal of Computing & Information Science, 2019, 2(3); doi: 10.25236/AJCIS.020311.
Yibo Min, Jianwei Ma* and Shaofei Zang
School of Information Engineering, Henan University of Science and Technology Luoyang, China
*Corresponding author e-mail: [email protected]
Aiming at the problem of tracking drift caused by the variation of illumination variation, deformation and occlusion problems in the target tracking process, a traditional Mean Shift algorithm is proposed. Firstly, LBP and LPQ are used to perform texture feature extraction on the target image, and the extracted color features and texture features are weighted and fused. Secondly, a target tracking method combining kalman filter and mean shift tracking is proposed. The scale adaptive mechanism is used to effectively improve the tracking stability of mean shift when the target scale changes. Experiments show that the improved algorithm is more robust to target deformation, illumination, and occlusion.
Texture feature, Object Tracking, Kalman filter, Mean shift
Yibo Min, Jianwei Ma and Shaofei Zang. Object Tracking Based on Multi-Feature Fusion and Kalman Filter. Academic Journal of Computing & Information Science (2019), Vol. 2, Issue 3: 92-103. https://doi.org/10.25236/AJCIS.020311.
 Guo L., Ge PS., Zhang MH, et al. Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine [J]. Expert Systems with Applications, 2012, 39 (4): 4274-4286.
 Comaniciu D, Ramesh V, Meer P. Real-time tracking of nonrigid objects using Mean Shift [C] // Pro of International Conference on Information Fusion. 2012: 142-149.
 Ning Ji-feng, Zhang Lei, Zhang D, et al. Robust Mean Shift tracking with corrected background-weighted histogram [J]. IET Computer Vision, 2012, 6 (1): 62-69.
 Wu Y, Lim J, Yang M H. Online object tracking: a benchmark [C] // Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013: 2411-2418.
 SHEN Ding-cheng, XUE Yan-bing, ZHANG Hua, et al. Research on robust object tracking algorithm based on online boosting [J]. Journal of Optotelectronics Laser, 2013, 24 (1): 170-175.
 Ulker Y, Gunsel B. Multiple model target tracking with variable rate particle filters [J]. Digital Processing, 2015, (22): 417-429.
 Das S, Kale A, Vaswani N. Particle filter with a mode tracker for visual tracking across illumination changes [J]. IEEE Trans. Image Process, 2012, 21 (4): 2340-2346.
 Leichter I. Mean shift trackers with cross-bin metrics [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2012, 34 (4): 695-706.
 Li S, Wu O, Zhu C, et al. Visual object tracking using spatial Context Information and Global tracking skills [J]. Computer Vision and Image Understanding, 2014, (125): 1-15.
 Yao A, Lin X, Wang G, et al. A compact association of particle filtering and kernel based object tracking [J]. Pattern Recognition, 2012, (45): 2584-2597.
 Zulfiqar K H, Gu Irene Y H, Andrew G B. Robust visual object tracking using multi-mode anisotropic mean shift and particle filters [J]. IEEE Transactions on Circuits and Systems for Video Technology (CSVT), 2011, 21 (1): 74-87.
 Choi H, Kim I, Choi J. Combining histogram-wise and pixel-wise matching for kernel tracking through constrained optimization [J]. Computer Vision and Image Understanding, 2014, (118): 61-70.
 SU Yan-zhao, LI Ai-hua, JIN Guang-zhi, et al. Visual tracking of moving object based on double layer features optimization [J]. Journal of Optoelectronics Laser, 2015, 26 (1): 162-169.
 He S F,Yang Q X, Rynson W H, et al. Visual tracking via locality sensitive histograms [C]. IEEE Conference on Computer Vision and Pattern Recognition, Oregon, Porland, 2013, 2427-2434.
 Wang J Q, Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking [J]. IEEE Transactions on Image Processing, 2012, 17 (2): 235-240.