iccv iccv2013 iccv2013-217 iccv2013-217-reference knowledge-graph by maker-knowledge-mining

217 iccv-2013-Initialization-Insensitive Visual Tracking through Voting with Salient Local Features


Source: pdf

Author: Kwang Moo Yi, Hawook Jeong, Byeongho Heo, Hyung Jin Chang, Jin Young Choi

Abstract: In this paper we propose an object tracking method in case of inaccurate initializations. To track objects accurately in such situation, the proposed method uses “motion saliency ” and “descriptor saliency ” of local features and performs tracking based on generalized Hough transform (GHT). The proposed motion saliency of a local feature emphasizes features having distinctive motions, compared to the motions which are not from the target object. The descriptor saliency emphasizes features which are likely to be of the object in terms of its feature descriptors. Through these saliencies, the proposed method tries to “learn and find” the target object rather than looking for what was given at initialization, giving robust results even with inaccurate initializations. Also, our tracking result is obtained by combining the results of each local feature of the target and the surroundings with GHT voting, thus is robust against severe occlusions as well. The proposed method is compared against nine other methods, with nine image sequences, and hundred random initializations. The experimental results show that our method outperforms all other compared methods.


reference text

[1] A. Adam, E. Rivlin, and I. Shimshoni. Robust fragmentsbased tracking using the integral histogram. In CVPR, 2006.

[2] M. Asadi, A. Dore, A. Beoldo, and C. Regazzoni. Tracking by using dynamic shape model learning in the presence of occlusion. In AVSS, 2007.

[3] S. Avidan. Ensemble tracking. PAMI, 29(2):261 –271, 2007.

[4] B. Babenko, M.-H. Yang, and S. Belongie. Robust object tracking with online multiple instance learning. PAMI, 33(8): 1619 –1632, 2011.

[5] D. H. Ballard. Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition, 13(2): 111–122, 1981 .

[6] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speeded-up robust features (surf). CVIU, 110(3):346–359, 2008.

[7] D. Comaniciu, V. Ramesh, and P. Meer. Kernel-based object tracking. PAMI, 25(5):564 577, 2003.

[8] T. B. Dinh, N. Vo, and G. Medioni. Context tracker: Exploring supporters and distracters in unconstrained environments. In CVPR, 2011.

[9] M. Godec, P. Roth, and H. Bischof. Hough-based tracking of non-rigid objects. In CVPR, 2011.

[10] H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via on-line boosting. In BMVC, 2006.

[11] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised on-line boosting for robust tracking. In ECCV, 2008.

[12] H. Grabner, J. Matas, L. Van Gool, and P. Cattin. Tracking the invisible: Learning where the object might be. In CVPR, 2010.

[13] Z. Kalal, J. Matas, and K. Mikolajczyk. P-n learning: Bootstrapping binary classifiers by structural constraints. In –

[14]

[15]

[16]

[17]

[18]

[19]

[20]

[21]

[22] CVPR, 2010. J. Kwon and K. M. Lee. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive basin hopping monte carlo sampling. In CVPR, 2009. D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91–1 10, 2004. V. Mahadevan and N. Vasconcelos. Saliency-based discriminant tracking. In CVPR, 2009. X. Mei and H. Ling. Robust visual tracking using l1 minimization. In ICCV, 2009. D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental learning for robust visual tracking. IJCV, 77: 125–141, 2008. C. Rother, V. Kolmogorov, and A. Blake. ”grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph., 23:309–314, 2004. S. Stalder, H. Grabner, and L. van Gool. Beyond semisupervised tracking: Tracking should be as simple as detection, but not simpler than recognition. In ICCVW, 2009. C. Tomasi and T. Kanade. Detection and tracking of point features. Technical report, CMU, 1991 . A. Yilmaz, O. Javed, and M. Shah. Object tracking: A survey. ACM Comput. Surv., 38(4), 2006. 2918 quences were averaged. sBeoqldue dnecneost.es [ a bveesrta grees±ulstt among tdheev compared algorithms. 2(a) coke #2 56(b) coke #256106(c) tiger1 #106239(d) tiger2 #239 2(e) oc Cup #2 1 (f) oc Cup #21 14 (g) woman #14 301(h) woman #301 562(i) oc Face #5621093(j) sylvester #109375(k) mot cros 1 #75(l) mtn. bike #132 GT25PROPOABSEMIBEYONDHOUGHMILTLDMSTFRAG INVIS Figure 7: Critical frames for tracking results. Subcaptions denote sequence names and frame numbers. Best viewed in color. 2919