Robust visual tracking based on scale invariance and deep learning

Abstract

Visual tracking is a popular research area in computer vision, which is very difficult to actualize because of challenges such as changes in scale and illumination, rotation, fast motion, and occlusion. Consequently, the focus in this research area is to make tracking algorithms adapt to these changes, so as to implement stable and accurate visual tracking. This paper proposes a visual tracking algorithm that integrates the scale invariance of SURF feature with deep learning to enhance the tracking robustness when the size of the object to be tracked changes significantly. Particle filter is used for motion estimation. The confidence of each particle is computed via a deep neural network, and the result of particle filter is verified and corrected by mean shift because of its computational efficiency and insensitivity to external interference. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods throughout the challenging factors in visual tracking, especially for scale variation.

Keywords

visual tracking / SURF / mean shift / particle filter / neural network

References

[1] Jia Y M. Robust control with decoupling performance for steering and traction of 4WS vehicles under velocity-varying motion. IEEE Transactions on Control Systems Technology, 2000, 8(3): 554–569

[2] Jia Y M. Alternative proofs for improved LMI representations for the analysis and the design of continuous-time systems with polytopic type uncertainty: a predictive approach. IEEE Transactions on Automatic Control, 2003, 48(8): 1413–1416

[3] Jia Y M. General solution to diagonal model matching control of multiple-output-delay systems and its applications in adaptive scheme. Progress in Natural Science, 2009, 19(1): 79–90

[4] Wang N Y, Yeung D Y. Learning a deep compact image representation for visual tracking. In: Proceedings of Advances in Neural Information Processing Systems. 2013, 809–817

[5] Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P A. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. The Journal ofMachine Learning Research, 2010, 11: 3371–3408

[6] Smeulders A W M, Chu D M, Rita C, Simone C, Afshin D, Mubarak S. Visual tracking: an experimental survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1442–1468

[7] Ali A, Jalil A, Niu J, Zhao X K, Rathore S, Ahmed J, Iftikhar M A. Visual object tracking—classical and contemporary approaches. Frontiers of Computer Science, 2016, 10(1): 167–188

[8] Wu Y, Lim J, Yang M H. Online object tracking: a benchmark. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2013, 9(4): 2411–2418

[9] Wu Y, Lim J, Yang M H. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834–1848

[10] Li X, Dick A, Shen C H, Anton V D H, Wang H Z. Incremental learning of 3D-DCT compact representations for robust visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(4): 863–881

[11] Gao J, Ling H B, Hu W M, Xing J L. Transfer learning based visual tracking with Gaussian processes regression. In: Proceedings of the 13th European Conference on Computer Vision. 2014, 188–203

[12] Henriques J F, Caseiro R, Martins P, Batista J. High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583–596

[13] Li X, Shen C H, Dick A, Zhang Z M, Zhuang Y. Online metricweighted linear representations for robust visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(5): 931–950

[14] Zhou Y, Bai X, Liu W Y, Latecki L J. Similarity fusion for visual tracking. International Journal of Computer Vision, 2016, 118(3): 337–363

[15] Zhong W, Lu H C, Yang M H. Robust object tracking via sparsitybased collaborative model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1838–1845

[16] Hare S, Saffari A, Torr P H S. Struck: structured output tracking with kernels. In: proceedings of IEEE Conference on Computer Vision. 2011, 263–270

[17] Li X, Dick A, Shen C H, Zhang Z F, Hengel A V D, Wang H Z. Visual tracking with spatio-temporal Dempster-Shafer information fusion. IEEE Transactions on Image Processing, 2013, 22(8): 3028–3040

[18] Gao C X, Chen F F, Yu J G, Huang R, Sang N. Robust visual tracking using exemplar-based detectors. IEEE Transactions on Circuits and Systems for Video Technology, 2015

[19] Li K, He F Z, Chen X. Real-time object tracking via compressive feature selection. Frontiers of Computer Science, 2016, 10(4): 689–701

[20] Zhang B C, Perina A, Li Z G, Murino V, Liu J Z, Ji R R. Bounding multiple gaussians uncertainty with application to object tracking. International Journal of Computer Vision, 2016, 118(3): 364–379

[21] Zhu Y Y, Zhang C Q, Zhou D Y, Wang X G, Bai X, Liu W Y. Traffic sign detection and recognition using fully convolutional network guided proposals. Neurocomputing, 2016, 214: 758–766

[22] Li H X, Li Y, Porikli F. DeepTrack: learning discriminative feature representations by convolutional neural networks for visual tracking. IEEE Transactions on Image Processing, 2015, 25(4): 1834–1848

[23] Hong S H, You T G, Kwak S H, Han B H. Online tracking by learning discriminative saliency map with convolutional neural network. 2015, arXiv:1502.06796v1

[24] Wang L, Liu T, Wang G, Chan K L, Yang Q X. Video tracking using learned hierarchical features. IEEE Transactions on Image Processing, 2015, 24(4): 1424–1435

[25] Ma C, Huang J B, Yang X K, Yang M H. Hierarchical convolutional features for visual tracking. In: proceedings of IEEE International Conference on Computer Vision. 2015, 3074–3082

[26] Wang N Y, Li S Y, Gupta A, Yeung D Y. Transferring rich feature hierarchies for robust visual tracking. 2015, arXiv:1501.04587v2

[27] Zhang K H, Liu Q S, Wu Y, Yang M H. Robust visual tracking via convolutional networks without training. IEEE Transactions on Image Processing, 2016, 25(4): 1779–1792

[28] Held D, Thrun S, Savarese S. Learning to track at 100 fps with deep regression networks. 2016, arXiv:1604.01802

[29] Wang L J, Ouyang W L, Wang X G, Lu H C. STCT: sequentially training convolutional networks for visual tracking. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016

[30] Zhai M Y, Roshtkhari M J, Mori G. Deep Learning of appearance models for online object tracking. 2016, arXiv:1607.02568

[31] Arulampalam M S, Maskell S, Gordon N, Clapp T. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing, 2002, 50(2): 174–188

[32] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564–577

[33] Torralba A, Fergus R, Freeman W T. 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(11): 1958–1970

[34] Zhang J M, Ma S G, Sclaroff S. MEEM: robust tracking via multiple experts using entropy minimization. In: proceedings of European Conference on Computer Vision. 2014, 188–203

[35] He S F, Yang Q X, Lau R W H, Wang J, Yang M H. Visual tracking via locality sensitive histograms. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2427–2434

[36] Jia X, Lu H C, Yang M H. Visual tracking via adaptive structural local sparse appearance model. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1822–1829

[37] Kwon J, Lee K M. Visual tracking decomposition. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2010, 1269–1276

[38] Ross D A, Lim J W, Lin R S, Yang M H. Incremental learning for robust visual tracking. International Journal of Computer Vision, 2008, 77(1): 125–141

[39] Dinh T B, Vo N, Medioni G. Context tracker: exploring supporters and distracters in unconstrained environments. In: proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2011, 1177–1184

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg