Object tracking method based on particle filter of adaptive patches combined with multi-features fusion
- 39 Downloads
Object tracking has been one of the most important and active research areas in the field of computer vision. In this paper, we address the problem of object tracking under complex conditions in a video, which propose a object tracking method based on particle filter of adaptive patches combined color histograms with Histogram of Oriented Gradient(HOG). The adaptive patch is performed by horizontal and vertical projection based on object gray levels, which can improve the patch adaptability to the object appearance diversity and the accuracy of object tracking under occlusion conditions. The fusion of color histograms and HOG features is adopted to describe each sub-patch, which not only solves the tracking divergence problem of similar objects, but also reduces the effect of local deformation. In addition, the weighted Bhattacharyya coefficient is introduced to calculate the sub-patch matching degree of the particle, and the particle sub-patch weight will be adjusted by integrating the particle space information, and the feature model is also updated in time to achieve robust object tracking. Many simulation experiments show that our proposed algorithm achieves more favorable performance than these existing state-of-the-art algorithms in handing various challenging videos, especially occlusion and shape deformation.
KeywordsObject tracking Particle filter Color histogram Histogram of oriented gradient Adaptability Projection
1. The Scientific and Technological Research Program of Henan Province. No.172102210441.
2. Key Scientific Research projects in Henan Colleges and Universities.No.18B520034.
3. The Ministry of Public Security Technical Research Plan under grant. No.2016JSYJB38.
- 1.Babenko B, Yang M, Belongie S (2013) Visual tracking with online multiple instance learning[C]". IEEE Conf Comput Vision Pattern Recogn: 983–900Google Scholar
- 4.Danescu R, Oniga F, Nedevschi S et al. (2009) Tracking multiple objects using particle filters and digital elevation maps[C]//. Intell Vehic Sym 2009 IEEE. IEEE: 88–93Google Scholar
- 5.De Ath G, Everson R (2018) Visual object tracking: The initialisation problem[J] arXiv preprint arXiv:1805.01146Google Scholar
- 6.Du B, Sun Y, Cai S et al (2018) Object tracking in satellite videos by fusing the kernel correlation filter and the three-frame-difference algorithm[J]. IEEE Geosci Remote Sens Lett 15(2):168–172Google Scholar
- 7.Habbachi S, Sayadi M, Rezzoug N (2018) Partical filtering for orientation determining using inertial sensors IMU[C]//. Adv Technol Signal Image Process (ATSIP), 2018 4th Int Conf. IEEE: 1–5Google Scholar
- 10.Jia X, Lu H, Yang MH (2012) Visual tracking via adaptive structural local sparse appearance model. Proc IEEE Conf Comput Vision Pattern Recogn (CVPR): 1822–1829Google Scholar
- 11.Li YZ, Lu ZY, Li J (2012) Robust video object tracking algorithm based on multi-feature fusion[J]. J Xid Univ 39(4):1–6Google Scholar
- 12.Long C, Baolong G, Wei S (2011) Multi-object tracking algorithm based on FCM and particle filter [J]. Chin J Sci Instrum 11:021Google Scholar
- 13.Wen L, Cai Z, Lei Z, Yi D, Li S (2012) Online spatio-temporal structure context learning for visual tracking. In: ECCV. pp. 716–729Google Scholar
- 15.Zhang T, Ghanem B, Liu S, Ahuja N (2012) Visual tracking via discriminant sparse similarity map[J]. IEEE Conf Comput Vision Pattern Recogn :470–484Google Scholar
- 19.Zhong W, Lu H, Yang MH (2012) “robust object tracking via sparsity-based collaborative model. Proc IEEE Conf Comput Vision Pattern Recogn (CVPR): 1838–1845Google Scholar