Abstract
Tracking can be seen as an online learning problem, where the focus is on discriminating object from background. From this point of view, features play a key role as the tracking accuracy depends on how well the feature distinguishes object and background. Current discriminative trackers use traditional features such as intensity, RGB and full body shape features. In this paper, we propose to use color invariant SURF features in the discriminative tracking. This set of invariant features has been shown to be of increased invariance and discriminative power. The resulting tracker inherits a good discrimination between object and background while keeping advantages of the discriminative tracking framework. Experiments on a dataset of 80 videos covering a wide range of tracking circumstances show that the tracker is robust to changes in object appearance, lighting conditions and able to track objects under cluttered scenes and partial occlusion.
Chapter PDF
Similar content being viewed by others
References
Zivkovic, Z., Kröse, B.: An EM-like algorithm for color-histogram-based object tracking. In: CVPR (2004)
Nguyen, H., Smeulders, A.: Robust track using foreground-background texture discrimination. IJCV 68(3), 277–294 (2006)
Ross, D., Lim, J., Lin, R.S.: Incremental learning for robust visual tracking. IJCV 77, 125–141 (2008)
Nguyen, H., Smeulders, A.: Fast occluded object tracking by a robust appearance filter. PAMI 26, 1099–1104 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). CVIU 110, 346–359 (2008)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27, 1615–1630 (2005)
Burghouts, G.J., Geusebroek, J.M.: Performance evaluation of local colour invariants. CVIU 113, 48–62 (2009)
Van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. PAMI 32, 1582–1596 (2010)
Uijlings, J., Smeulders, A., Scha, R.: Real-time bag of words, approximately. In: CIVR (2009)
Alper Yimaz, O.J., Shah, M.: Object tracking: a survey. ACM Computing Surveys 38 (2006)
Sheikh, Y., Javed, O., Kanade, T.: Background subtraction for freely moving cameras. In: ICCV (2009)
Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: BMVC (2006)
Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR (2009)
Chu, D.M., Smeulders, A.W.M.: Thirteen hard cases in visual tracking. In: AVSS (2010)
Grabner, M., Grabner, H., Bischof, H.: Learning features for tracking. In: CVPR (2007)
Avidan, S.: Ensemble tracking. PAMI 29, 261–271 (2007)
Grabner, H., Leistner, C., Bischof, H.: Semi-supervised On-Line Boosting for Robust Tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 234–247. Springer, Heidelberg (2008)
Mahadevan, V., Vasconcelos, N.: Saliency-based discriminant tracking. In: CVPR (2009)
Tremeau, A., Tominaga, S., Plataniotis, K.N.: Color in image and video processing: most recent trends and future research directions. EURASIP Journal on Image and Video Processing 2008 (2008)
He, W., Yamashita, T., Lu, H., Lao, S.: Surf tracking. In: ICCV (2009)
Zhou, H., Yuan, Y., Shi, C.: Object tracking using sift features and mean shift. CVIU 113, 345–352 (2009)
Tran, S., Davis, L.: Robust object tracking with regional affine invariant features. In: ICCV (2007)
Stern, H., Efros, B.: Adaptive color space switching for tracking under varying illumination. IVC 23, 353–364 (2005)
Wang, J., Yagi, Y.: Integrating color and shape-texture features for adaptive real-time object tracking. TIP 17, 235–240 (2008)
Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. PAMI 27, 1631–1643 (2005)
Geusebroek, J.M., van den Boomgaard, R., Smeulders, A.W.M., Geerts, H.: Color invariance. PAMI 23, 1338–1350 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chu, D.M., Smeulders, A.W.M. (2012). Color Invariant SURF in Discriminative Object Tracking. In: Kutulakos, K.N. (eds) Trends and Topics in Computer Vision. ECCV 2010. Lecture Notes in Computer Science, vol 6554. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35740-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-35740-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35739-8
Online ISBN: 978-3-642-35740-4
eBook Packages: Computer ScienceComputer Science (R0)