Abstract
A novel scheme for non-rigid video object tracking using segment-based object candidates is proposed in this paper. Rather than using a conventional bounding box, the tracker is based on segments and considers the target object to be a combination of segments, where the hierarchical hue-saturation-value histogram is extracted as a feature. The objectness method is employed and integrated into the tracker to generate candidates for a similarity measure. Moreover, segment-based motion weights are introduced to give higher weights to candidates with motion consistency. A confidence-collecting scheme is proposed for similar candidates. To validate our method, experiments were conducted using several image sequences with different non-rigid challenges. The experimental results show that the proposed scheme can achieve better performance than other state-of-the-art methods.
Similar content being viewed by others
References
Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Su (2010) “SLIC superpixels compared to state-of-the-art superpixel methods,”. Pattern Anal Mach Intell IEEE Trans 34:2274–2282
Alexe B, Deselaers T, Ferrari V (2010) “What is an object?,”. Comput Vision Pattern Recognition (CVPR), 2010 I.E. Conf 73–80
Babenko B, Ming-Hsuan Y, Belongie S (2011) “Robust object tracking with online multiple instance learning,”. Pattern Anal Mach Intell IEEE Trans 33:1619–1632
Chockalingam P, Pradeep N, Birchfield S (2009) “Adaptive fragments-based tracking of non-rigid objects using level sets,”. Comput Vision, 2009 I.E. 12th Int Conf 1530–1537
Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24:603–619
Forsyth D, Torr P, Zisserman A, Vedaldi A, Soatto S (2008) Quick shift and Kernel methods for mode seeking, computer vision. vol. 5305. Springer, Berlin Heidelberg, pp 705–718
Fuxin L, Taeyoung K, Humayun A, Tsai D, Rehg JM (2013) “Video segmentation by tracking many figure-ground segments,”. Comput Vision (ICCV), 2013 I.E. Int Conf 2192–2199
Gall J, Razavi N, Gool L. v (2010) “On-line adaption of class-specific codebooks for instance tracking”. BMVC
Godec M, Roth PM, Bischof H (2011) “Hough-based tracking of non-rigid objects,”. Comput Vision (ICCV), 2011 I.E. Int Conf 81–88
Grabner H, Bischof H (2006) “On-line boosting and vision,”. Comput Vision Pattern Recognition, 2006 I.E. Comput Soc Conf 260–267
Grabner H, Grabner M, Bischof H (2006) “Real-time tracking via on-line boosting,”. Proc British Mach Conf 6.1–6.10
Isard M, Blake A (1998) Condensation-onditional density propagation for visual tracking. Int J Comput Vis 29:5–28
Jang S-I, Choi K, Toh K-A, Teoh ABJ, Kim J (2015) Object tracking based on an online learning network with total error rate minimization. Pattern Recogn 48:126–139
Junseok K, Kyoung Mu L (2013) “Highly nonrigid object tracking via patch-based dynamic appearance modeling,”. Pattern Anal Mach Intell IEEE Trans 35:2427–2441
Kalal Z, Matas J, Mikolajczyk K (2010) “P-N learning: bootstrapping binary classifiers by structural constraints,”. Comput Vision Pattern Recognition (CVPR), 2010 I.E. Conf 49–56
Kwon J, Lee KM (2009) “Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling,”. Comput Vision Pattern Recognition, 2009. CVPR 2009. IEEE Conf 1208–1215
Levinshtein A, Stere A, Kutulakos KN, Fleet DJ, Dickinson SJ, Siddiqi K (2009) “TurboPixels: fast superpixels using geometric flows,”. Pattern Anal Mach Intell IEEE Trans 31:2290–2297
Liu T, Sun J, Zheng N-N, Tang X, Shum H-Y (2007) “Learning to detect a salient object,”. Comput Vision Pattern Recognition, 2007. CVPR ’07. IEEE Conf 1–8
Manen S, Guillaumin M, Van Gool L (2013) “Prime object proposals with randomized prim’s algorithm,”. Comput Vision (ICCV), 2013 I.E. Int Conf 2536–2543
Marfil R, Molina-Tanco L, Rodríguez JA, Sandoval F (2007) Real-time object tracking using bounded irregular pyramids. Pattern Recogn Lett 28:985–1001
Mei X, Ling H (2011) “Robust visual tracking and vehicle classification via sparse representation,”. Pattern Anal Mach Intell IEEE Trans 33:2259–2272
Ming-Ming C, Ziming Z, Wen-Yan L, Torr P (2014) “BING: binarized normed gradients for objectness estimation at 300fps,”. Comput Vision Pattern Recognition (CVPR), 2014 I.E. Conf 3286–3293
Mori G (2005) Computer vision, 2005. ICCV 2005. Tenth IEEE Int Conf 2:1417–1423
Quinlan JR (1993) “C4.5: Programs for machine learning”. Morgan Kaufmann
Ross D, Lim J, Lin R-S, Yang M-H (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77:125–141
Rother C, Kolmogorov V, Blake A (2004) “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23:309–314
Schapire RE (1999) “A brief introduction to boosting,”. Proc 16th Int Joint Conf Artificial Intellig - volume 2, Stockholm, Sweden
Tissainayagam P, Suter D (2005) Object tracking in image sequences using point features. Pattern Recogn 38:105–113
Van de Sande KEA, Uijlings JRR, Gevers T, Smeulders AWM (2011) “Segmentation as selective search for object recognition,”. Comput Vision (ICCV), 2011 I.E. Int Conf 1879–1886
VLFeat Matlab toolbox. Available: http://www.vlfeat.org/overview/quickshift.html
Wang S, Lu H, Yang F, Yang M-H (2011) “Superpixel tracking,”. Computer Vision (ICCV), 2011 I.E. Int Conf 1323–1330
Wu Y, Lim J, Yang M-H (2013) “Online object tracking: a benchmark,”. Comput Vision Pattern Recognition (CVPR), 2013 I.E. Conf 2411–2418
Xiaodi H, Liqing Z (2007) “Saliency detection: a spectral residual approach,”. Comput Vision Pattern Recognition, 2007. CVPR ’07. IEEE Conf 1–8
Xue M, Haibin L (2009) “Robust visual tracking using L1 minimization,”. Comput Vision, 2009 I.E. 12th Int Conf 1436–1443
Zhang K, Zhang L, Yang M-H (2012) “Real-time compressive tracking,”. Europ Conf Comput Vision (ECCV 2012), Florence, Italy
Zhou H, Yuan Y, Shi C (2009) Object tracking using SIFT features and mean shift. Comput Vis Image Underst 113:345–352
Acknowledgments
This research was supported in part by the Research Committee of the University of Macau (MYRG2015-00011-FST, MYRG2015-00012-FST) and the Science and Technology Development Fund of Macau SAR (008/2013/A1, 093-2014-A2).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, C., Pun, CM. & Huang, G. Highly non-rigid video object tracking using segment-based object candidates. Multimed Tools Appl 76, 9565–9586 (2017). https://doi.org/10.1007/s11042-016-3563-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3563-3