Towards robust multi-cue integration for visual tracking

Abstract. Even though many of today's vision algorithms are very successful, they lack robustness, since they are typically tailored to a particular situation. In this paper, we argue that the principles of sensor and model integration can increase the robustness of today's computer-vision systems substantially. As an example, multi-cue tracking of faces is discussed. The approach is based on the principles of self-organization of the integration mechanism and self-adaptation of the cue models during tracking. Experiments show that the robustness of simple models is leveraged significantly by sensor and model integration.

[1]  Michael Isard,et al.  Active Contours: The Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion , 2000 .

[2]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[3]  C. Malsburg,et al.  Self-organized integration of adaptive visual cues for face tracking , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[4]  Bernt Schiele,et al.  Towards Robust Multi-cue Integration for Visual Tracking , 2001, ICVS.

[5]  James L. Crowley,et al.  Multi-modal tracking of faces for video communications , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  B. Parhami.  Voting algorithms , 1994 .

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  Ulf Grenander,et al.  Hands: A Pattern Theoretic Study of Biological Shapes , 1990 .

[9]  Gregory D. Hager,et al.  Incremental focus of attention for robust visual tracking , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[11]  Gregory D. Hager,et al.  Incremental Focus of Attention for Robust Vision-Based Tracking , 1999, International Journal of Computer Vision.

[12]  Carsten G. Bräutigam.  A model-free voting approach to cue integration , 1998 .

[13]  Danica Kragic,et al.  Integration of visual cues for active tracking of an end-effector , 1999, Proceedings 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human and Environment Friendly Robots with High Intelligence and Emotional Quotients (Cat. No.99CH36289).

[14]  D. Ballard,et al.  Fast Temporal Dynamics of Visual Cue Integration , 2000, Perception.

[15]  Michael Isard,et al.  ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework , 1998, ECCV.

[16]  James J. Clark,et al.  Data Fusion for Sensory Information Processing Systems , 1990 .