Multiple vehicle 3D tracking using an unscented Kalman

This article describes a system to track vehicles on images taken from a mobile platform. The objective is to determine the position and velocity of vehicles ahead of the mobile platform, in order to make possible the prediction of their position in future instants of time. This problem is addressed by modeling a 3D dynamic system, where both the acquisition platform and the tracked vehicles are represented in a state vector. From measurements obtained in every frame, this state vector is re-estimated using an unscented Kalman filter, instead of the extended Kalman filter used in previous works. Assuming that vehicles progress on a flat surface, a novel model of their dynamics is proposed, which explicitly considers constraints on the velocity. With respect to previous approaches, this model improves tracking reliability, since the estimation of unfeasible states is avoided. Experiments on real sequences display promising results, although a more systematic evaluation of the system should be done.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Frank Dellaert,et al.  Model-based car tracking integrated with a road-follower , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[3]  L. Davis,et al.  Real-time multiple vehicle detection and tracking from a moving vehicle , 2000, Machine Vision and Applications.

[4]  E. D. Dickmanns,et al.  The development of machine vision for road vehicles in the last decade , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[5]  Frank Dellaert,et al.  Robust car tracking using Kalman filtering and Bayesian templates , 1998, Other Conferences.

[6]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[7]  Ernst D. Dickmanns,et al.  Obstacle Detection, Tracking And State Estimation For Autonomous Road Vehicle Guidance , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Rudolph van der Merwe,et al.  The square-root unscented Kalman filter for state and parameter-estimation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

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

[10]  Simon J. Julier,et al.  The scaled unscented transformation , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[11]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[12]  Markus Maurer,et al.  A compact vision system for road vehicle guidance , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[13]  Jean-Yves Bouguet,et al.  Camera calibration toolbox for matlab , 2001 .

[14]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .