Abstract
A major reason leading to tracking failure is the spatial distractions that exhibit similar visual appearances as the target, because they also generate good matches to the target and thus distract the tracker. It is in general very difficult to handle this situation. In a selective attention tracking paradigm, this paper advocates a new approach of discriminative spatial attention that identifies some special regions on the target, called attentional regions (ARs). The ARs show strong discriminative power in their discriminative domains where they do not observe similar things. This paper presents an efficient two-stage method that divides the discriminative domain into a local and a semi-local one. In the local domain, the visual appearance of an attentional region is locally linearized and its discriminative power is closely related to the property of the associated linear manifold, so that a gradient-based search is designed to locate the set of local ARs. Based on that, the set of semi-local ARs are identified through an efficient branch-and-bound procedure that guarantees the optimality. Extensive experiments show that such discriminative spatial attention leads to superior performances in many challenging target tracking tasks.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Peters, R., Itti, L.: Beyond bottom-up: incorporating task-dependent influences into a computational model of spatial attention. In: CVPR (2007)
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on PAMI, 1254–1259 (1998)
Hager, G., Dewan, M., Stewart, C.: Multiple kernel tracking with ssd. In: CVPR (2004)
Fan, Z., Yang, M., Wu, Y., Hua, G., Yu, T.: Efficient optimal kernel placement for reliable visual tracking. In: CVPR (2006)
Yang, M., Yuan, J., Wu, Y.: Spatial selection for attentional visual tracking. In: CVPR (2007)
Gao, D., Vasconcelos, N.: Discriminant interest points are stable. In: CVPR (2007)
Parameswaran, V., Ramesh, V., Zoghlami, I.: Tunable kernels for tracking. In: CVPR (2006)
Donoser, M., Bischof, H.: Efficient maximally stable extremal region (mser) tracking. In: CVPR (2006)
Collins, R., Liu, Y.: On-line selection of discriminative tracking features. In: ICCV (2003)
Shi, J., Tomasi, C.: Good features to track. In: CVPR (1994)
Kadir, T., Brandy, M.: Saliency, scale and image description. IJCV (2001)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. IJCV (2005)
Kwon, J., Lee, K.: Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive basin hopping monte carlo sampling. In: CVPR (2009)
Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: CVPR (2009)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2004)
Wu, Y., Fan, J.: Contextual flow. In: CVPR (2009)
Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: CVPR (2000)
Palmer, S.: Vision science: photons to phenomenology. The MIT Press, Cambridge (1999)
Avidan, S.: Ensemble tracking. In: CVPR (2005)
Fan, J., Wu, Y., Dai, S.: Discriminative spatial attention for robust tracking. Northwestern University Technical Report (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fan, J., Wu, Y., Dai, S. (2010). Discriminative Spatial Attention for Robust Tracking. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6311. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15549-9_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-15549-9_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15548-2
Online ISBN: 978-3-642-15549-9
eBook Packages: Computer ScienceComputer Science (R0)