De-cluttering with Integrated Probabilistic Data Association for Multisensor Multitarget ACC Vehicle Tracking

In the field of automotive environment perception, the state estimation problem of other road users with sensors like video, radar, lidar, or combinations of them has been solved for years now. However, driver assistance systems like ACC are only available for restricted environments like highways and rural roads today. Especially in complex environments, the uncertainty of target existence induced from missing and false detections becomes the dominating error source. Traditional approaches for track verification are rule based systems and trained classifiers. In this contribution, we present an automotive application of the integrated probabilistic data association (IPDA) filter superseding additional validation modules by modeling the probabilistic knowledge about both, state and existence, as temporal Markov chains and computing filter estimates for both issues. The temporal evolution and measurement update models for state and existence estimation are presented for the vehicle tracking problem as well as results from a sensor fusion setup with video and multibeam lidar.

[1]  O. Lohlein,et al.  Determining Posterior Probabilities on the Basis of Cascaded Classifiers as used in Pedestrian Detection Systems , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[2]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[3]  K. Dietmayer,et al.  Object tracking and classification using a multiple hypothesis approach , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[4]  S. Wender,et al.  An Adaptable Object Classification Framework , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[5]  Robin J. Evans,et al.  Integrated probabilistic data association , 1994, IEEE Trans. Autom. Control..

[6]  K. Dietmayer,et al.  FUSION OF LASERSCANNER AND VIDEO FOR ADVANCED DRIVER ASSISTANCE SYSTEMS , 2004 .

[7]  R. Mahler.  Random Sets : Unification and Computation for Information Fusion — A Retrospective Assessment , 2004 .

[8]  C. Hilario,et al.  Visual Perception and Tracking of Vehicles for Driver Assistance Systems , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[9]  R. Mahler.  Multitarget Bayes filtering via first-order multitarget moments , 2003 .

[10]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[11]  B. Vo,et al.  Bayesian approaches to track existence - IPDA and random sets , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[12]  Paul Levi,et al.  Robust vehicle tracking fusing radar and vision , 2001, Conference Documentation International Conference on Multisensor Fusion and Integration for Intelligent Systems. MFI 2001 (Cat. No.01TH8590).

[13]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[15]  M. Mahlisch,et al.  Sensorfusion Using Spatio-Temporal Aligned Video and Lidar for Improved Vehicle Detection , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[16]  J. Klappstein,et al.  Monocular Motion Detection Using Spatial Constraints in a Unified Manner , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[17]  Christian Wöhler,et al.  An adaptable time-delay neural-network algorithm for image sequence analysis , 1999, IEEE Trans. Neural Networks.