Robust Tracking via Dual Constrained Filters
In this paper, we propose a novel correlation filter framework constrained by dual filters. The Minimum Output Sum of Squared Error (MOSSE) filter is the unbiased estimate of the filter which easily to cause overfitting. The trained filter by linear ridge regression is the biased estimate of the filter which can deal with the overfitting. We combine the advantages of the two filters to constrain the trained filter which optimizes our model. To deal with background clutter, clipping background patches around the target position up, down, left, and right, we add the cropped background patches to the learning filter. To overcome the challenge of occlusion, we introduce a novel criterion, Average Peak-to-Correlation Energy (APCE). Extensive experiments on the CVPR 2013 Benchmark well demonstrate that our tracker can effectively solve the background clutter and occlusion. Both quantitative analysis and qualitative analysis show that our tracker outperforms some state-of-the-art trackers.
KeywordsDual filters Background clutter Occlusion CVPR 2013 Benchmark
This work was supported by the Major Science Instrument Program of the National Natural Science Foundation of China under grant 61527802, and the General Program of National Nature Science Foundation of China under grants 61371132 and 61471043.
- 1.Bolme DS, Beveridge JR. Visual object tracking using adaptive correlation filters. In: IEEE computer vision and pattern recognition; 2010. p. 2544–50.Google Scholar
- 5.Li Y, Zhu J. Adaptive kernel correlation filter tracker with feature integration, vol. 8926. Springer; 2014. p. 254–65.Google Scholar
- 6.Wang MM, Liu Y, Huang ZY. Large margin object tracking with circulant feature maps. In: IEEE computer vision and pattern recognition; 2017. p. 4800–8.Google Scholar
- 7.Wu Y, Lmi J, Yang MH. Online object tracking: a benchmark. In: IEEE computer vision and pattern recognition; 2013. p. 2411–8.Google Scholar
- 8.Mueller M, Smith N, Ghanem B. Context-aware correlation filter tracking. In: IEEE computer vision and pattern recognition; 2017. p. 1387–95.Google Scholar
- 9.Sunando S. Struck: structured output tracking with kernels. IEEE Trans Pattern Anal Mach Intell. 2015;38(10):2096–109.Google Scholar
- 11.Kwon J, Lee KM. Visual tracking decomposition. In: IEEE computer vision and pattern recognition; 2010. p. 1269–76.Google Scholar
- 12.Medioni G. Exploring supporters and distracters in unconstrained environments. In: IEEE computer vision and pattern recognition; 2011. p. 1177–84.Google Scholar