Abstract
Discriminative methods have been widely applied to construct the appearance model for visual tracking. Most existing methods incorporate online updating strategy to adapt to the appearance variations of targets. The focus of online updating for discriminative methods is to select the positive samples emerged in past frames to represent the appearances. However, the appearances of positive samples might be very dissimilar to each other; traditional online updating strategies easily overfit on some appearances and neglect the others. To address this problem, we propose an effective method to learn a discriminative template, which maintains the multiple appearances information of targets in the long-term variations. Our method is based on the obvious observation that the target appearances vary very little in a certain number of successive video frames. Therefore, we can use a few instances to represent the appearances in the scope of the successive video frames. We propose exclusive group sparse to describe the observation and provide a novel algorithm, called coefficients constrained exclusive group LASSO, to solve it in a single objective function. The experimental results on CVPR2013 benchmark datasets demonstrate that our approach achieves promising performance.
Similar content being viewed by others
Notes
In this paper, we assume all the feature vectors are normalized, which means \(\frac{<\mathbf {x}_1, \mathbf {x}_2>}{\Vert \mathbf {x}_1\Vert _2\Vert \mathbf {x}_2\Vert _2} = <\mathbf {x}_1, \mathbf {x}_2> = \mathbf {x}_1^T \mathbf {x}_2\).
References
Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 798–805 (2006)
Ahmed, J., Jafri, M.N., Shah, M., Akbar, M.: Real-time edge-enhanced dynamic correlation and predictive open-loop car-following control for robust tracking. Mach. Vis. Appl. 19(1), 1–25 (2008)
Avidan, S.: Support vector tracking. IEEE Trans. Pattern Anal. Mach. Intell. 26(8), 1064–1072 (2004)
Baker, S., Matthews, I.: Lucas-kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56(3), 221–255 (2004)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust l1 tracker using accelerated proximal gradient approach. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1830–1837 (2012)
Black, M.J., Jepson, A.D.: Eigentracking: robust matching and tracking of articulated objects using a view-based representation. Int. J. Comput. Vis. 26(1), 63–84 (1998)
Chen, L., Philip Chen, C.L., Lu, M.: A multiple-kernel fuzzy c-means algorithm for image segmentation. IEEE Trans. Syst. Man Cybern. 41(5), 1263–1274 (2011)
Chen, W., Zhao, Y.: Supervised kernel nonnegative matrix factorization for face recognition. Neurocomputing 205, 165–181 (2016)
Chen, W.-S., Dai, X., Pan, B., Tang, Y.Y.: Semi-supervised discriminant analysis method for face recognition. Int. J. Wavelets Multiresolut. Inf. Process. 13(06), 1550049 (2015)
Chen, X., Yuan, X.-T., Chen, Q., Yan, S., Chua, T.-S.: Multi-label visual classification with label exclusive context. In: IEEE International Conference on Computer Vision (ICCV), pp. 834–841 (2011)
Chen, X., Yuan, X., Yan, S., Tang, J., Rui, Y., Chua, T.-S.: Towards multi-semantic image annotation with graph regularized exclusive group lasso. In: International Conference on Multimedia, pp. 263–272 (2011)
Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 142–149 (2000)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 886–893 (2005)
Danelljan, M., Häger, G., Khan, F., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference (BMVC), pp. 65.1–65.11 (2014)
Gao, J., Ling, H., Hu, W., Xing, J.: Transfer learning based visual tracking with Gaussian processes regression. In: European Conference on Computer Vision (ECCV), pp. 188–203 (2014)
Ge, Q., Jing, X.-Y., Wu, F., Wei, Z., et al.: Structure-based low-rank model with graph nuclear norm regularization for noise removal. IEEE Trans. Image Process. 26, 3098–3112 (2016)
Gu, B., Sheng, V.S.: A robust regularization path algorithm for \(\nu \)-support vector classification. IEEE Trans. Neural Netw. Learn. Syst. 28, 1241–1248 (2017)
Han, Z., Jiao, J., Zhang, B., Ye, Q., Liu, J.: Visual object tracking via sample-based adaptive sparse representation (AdaSR). Pattern Recognit. 44(9), 2170–2183 (2011)
Hare, S., Golodetz, S., Saffari, A., et al.: Struck: structured output tracking with kernels. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2096–2109 (2016)
He, Z., Li, X., You, X., Tao, D., Tang, Y.Y.: Connected component model for multi-object tracking. IEEE Trans. Image Process. 25(8), 3698–3711 (2016)
He, Z., Chung, A.C.: 3-D B-spline wavelet-based local standard deviation (bwlsd): its application to edge detection and vascular segmentation in magnetic resonance angiography. Int. J. Comput. Vis. 87(3), 235–265 (2010)
He, Z., Yi, S., Cheung, Y.-M., You, X., Tang, Y.Y.: Robust object tracking via key patch sparse representation. IEEE Trans. Cybern. 47, 1–11 (2016)
He, Z., You, X., Tang, Y.Y.: Writer identification of Chinese handwriting documents using hidden Markov tree model. Pattern Recognit. 41(4), 1295–1307 (2008)
He, Z., You, X., Zhou, L., Cheung, Y., Jianwei, D.: Writer identification using fractal dimension of wavelet subbands in gabor domain. Integr. Comput. Aided Eng. 17(17), 157–165 (2010)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)
Isard, M., Blake, A.: Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)
Jia, X., Lu, H., Yang, M.-H.: Visual tracking via adaptive structural local sparse appearance model. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1822–1829 (2012)
Jing, X., Wu, F.: Multi-spectral low-rank structured dictionary learning for face recognition. Pattern Recognit. 59(4), 14–25 (2016)
Kong, D., Fujimaki, R., Liu, J., Nie, F., Ding, C.: Exclusive feature learning on arbitrary structures via \(\ell _{1,2}\)-norm. In: Advances in Neural Information Processing Systems, pp. 1655–1663 (2014)
Lai, Z., Yong, X., Jin, Z., Zhang, D.: Human gait recognition via sparse discriminant projection learning. IEEE Trans. Circuits Syst. Video Technol. 24(10), 1651–1662 (2014)
Lawson, C.L., Hanson, R.J.: Solving Least Squares Problems, vol. 161. SIAM, Philadelphia (1974)
Li, X., Shen, C., Dick, A., van den Hengel, A.: Learning compact binary codes for visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2419–2426 (2013)
Li, X., Shen, C., Shi, Q., Dick, A., Van den Hengel, A.: Non-sparse linear representations for visual tracking with online reservoir metric learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1760–1767 (2012)
Li, X., Liu, Q., He, Z., Wang, H., Zhang, C., Chen, W.-S.: A multi-view model for visual tracking via correlation filters. Knowl. Based Syst. 113, 88–99 (2016)
Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1313–1320 (2011)
Liu, B., Yang, L., Huang, J., Meer, P., Gong, L., Kulikowski, C.: Robust and fast collaborative tracking with two stage sparse optimization. In: European Conference on Computer Vision, pp. 624–637. Springer (2010)
Liu, L., Chen, L.: Weighted joint sparse representation for removing mixed noise in image. IEEE Trans. Cybern. 47, 600–611 (2016)
Liu, Q., Ma, X., Ou, W., Zhou, Q.: Visual object tracking with online sample selection via lasso regularization. Signal Image Video Process. 11, 881–888 (2017)
Liu, R., Tang, Y.: Topological coding and its application in the refinement of sift. IEEE Trans. Cybern. 44(11), 2155–2166 (2014)
Lu, H., Li, B., Zhu, J., et al.: Wound intensity correction and segmentation with convolutional neural networks. Concurr. Comput. Pract. Exp. 29, 6 (2016)
Matthews, I., Ishikawa, T., Baker, S.: The template update problem. IEEE Trans. Pattern Anal. Mach. Intell. 26(6), 810–815 (2004)
Mei, X., Ling, H.: Robust visual tracking using \(\ell _{1}\) minimization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1436–1443 (2009)
Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient \(\ell _{1}\) tracker with occlusion detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1257–1264 (2011)
Ou,W., Yuan, D., Liu, Q., Cao, Y.: Object tracking based on online representative sample selection via non-negative least square. Multimed. Tools Appl. (2017). https://doi.org/10.1007/s11042-017-4672-3
Qian, J., Fang, B., Yang, W., Luan, X.: Accurate tilt sensing with linear model. IEEE Sens. J. 11(10), 2301–2309 (2011)
Ross, D.A., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1–3), 125–141 (2008)
Schweitzer, H., Bell, J.W., Wu, F.: Very fast template matching. In: European Conference on Computer Vision (ECCV), pp. 358–372. Springer (2002)
Wang, N., Shi, J., Yeung, D.-Y., Jia, J.: Understanding and diagnosing visual tracking systems. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3101–3109 (2015)
Wang, Q., Chen, F., Xu, W., Yang, M.-H.: Online discriminative object tracking with local sparse representation. In: IEEE Workshop on Applications of Computer Vision (WACV), pp. 425–432 (2012)
Weihua, O., You, X., Tao, D., Zhang, P., Tang, Y., Zhu, Z.: Robust face recognition via occlusion dictionary learning. Pattern Recognit. 47(4), 1559–1572 (2014)
Weihua, O., Shujian, Y., Li, G., Jian, L., Zhang, K., Xie, G.: Multi-view non-negative matrix factorization by patch alignment framework with view consistency. Neurocomputing 204, 116–124 (2016)
Wong, W.K., Lai, Z., Xu, Y., Wen, J., Ho, C.P.: Joint tensor feature analysis for visual object recognition. IEEE Trans. Cybern. 45(11), 2425–2436 (2015)
Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2411–2418 (2013)
Yang, M., Wu, Y., Pei, M., Ma, B., Jia, Y.: Coupling semi-supervised learning and example selection for online object tracking. In: Asian Conference on Computer Vision (ACCV), pp. 476–491 (2014)
Zhang, T., Ghanem, B., Liu, S., Changsheng, X., Ahuja, N.: Robust visual tracking via exclusive context modeling. IEEE Trans. Cybern. 46(1), 51–63 (2016)
Zhong, W., Lu, H., Yang, M.-H.: Robust object tracking via sparsity-based collaborative model. In: IEEE Conference on Computer vision and pattern recognition (CVPR), pp. 1838–1845 (2012)
Zhou, Q., Zheng, B., Zhu, W., Latecki, L.J.: Multi-scale context for scene labeling via flexible segmentation graph. Pattern Recognit. 59(C), 312–324 (2016)
Zhou, Y., Jin, R., Hoi, S.: Exclusive lasso for multi-task feature selection. In: International Conference on Artificial Intelligence and Statistics, pp. 988–995 (2010)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Nos. 61762021, 61402122, 61672183, 61272252, 61401228, 61461008), Science and Technology Planning Project of Guanddong Province (No. 2016B090918047), Shenzhen Research Council (No.JCYJ20160406161948211, JCYJ2016022 6201453085, JSGG20150331152017052), Natural Science Foundation of Guangdong Province (No. 2015A030313544), the 2014 Ph.D. Recruitment Program of Guizhou Normal University, Natural Science Foundation of Guizhou Province (No. 2017[1130]), the Outstanding Innovation Talents of Science and Technology Award Scheme of Education Department in Guizhou Province (Qian jiao KY word[2015]487), the China Scholarship Council (No. 201508525007), Fund of Guizhou Educational Department (KY[2016]027), China Postdoctoral Science Foundation (Grant No. 2015M581841) and Postdoctoral Science Foundation of Jiangsu Province (Grant No. 1501019A).
Author information
Authors and Affiliations
Corresponding author
Additional information
Xiao Ma and Qiao Liu contributed equally to this work and should be considered co-first authors. Weihua Ou and Quan Zhou are the corresponding authors.
Rights and permissions
About this article
Cite this article
Ma, X., Liu, Q., Ou, W. et al. Visual object tracking via coefficients constrained exclusive group LASSO. Machine Vision and Applications 29, 749–763 (2018). https://doi.org/10.1007/s00138-018-0930-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-018-0930-2