Using the condensation algorithm to implement tracking for mobile robots

The detection of objects in every frame of a sequence is often not sufficient for scene interpretation. Tracking can increase the robustness, especially when occlusions occur or when objects temporally disappear. The standard approach for tracking is to use a Kalman filter for every object. This, however requires the use of a high complexity management system to deal with the multiple hypotheses necessary to track all anticipated objects. We present a stochastic approach which is based on the CONDENSATION algorithm-conditional density propagation over time-that is capable of tracking multiple objects with multiple hypotheses in range images. A probability density function describing the likely state of the objects is propagated over time using a dynamic model. The measurements influence the probability function and allow the incorporation of new objects into the tracking scheme. Additionally, the representation of the density function with a fixed number of samples ensures a constant running time per iteration step. Results on different data sources are shown for mobile robot applications.

[1]  M. Kilger,et al.  Video-based traffic monitoring , 1992 .

[2]  K.D. Baker,et al.  Performance assessment of model-based tracking , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[3]  Liang Zhao,et al.  Qualitative and quantitative car tracking from a range image sequence , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[4]  Jitendra Malik,et al.  Robust Multiple Car Tracking with Occlusion Reasoning , 1994, ECCV.

[5]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[6]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[7]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[8]  M. Kilger,et al.  A shadow handler in a video-based real-time traffic monitoring system , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

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

[10]  Jitendra Malik,et al.  A real-time computer vision system for measuring traffic parameters , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Jitendra Malik,et al.  Combining Multiple Motion Estimates for Vehicle Tracking , 1996 .

[12]  P. Abbeel,et al.  Kalman filtering , 2020, IEEE Control Systems Magazine.

[13]  A. Pentland,et al.  Toward augmented control systems , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.