A PHD approach for multiple vehicle tracking based on a polar detection method in laser range data

This paper presents a detection and tracking approach of multiple vehicles in scanning laser range data. The proposed solution relies on a new detection method based on object geometric invariant that uses the raw measurements directly in polar coordinates. The multitarget management problem is solved in the PHD framework by a particle filter.

[1]  Jean-Charles Noyer,et al.  Feature Extraction in Scanning Laser Range Data Using Invariant Parameters: Application to Vehicle Detection , 2012, IEEE Transactions on Vehicular Technology.

[2]  Robert A. MacLachlan,et al.  Tracking of Moving Objects from a Moving Vehicle Using a Scanning Laser Rangefinder , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

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

[4]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[5]  Roland Siegwart,et al.  A comparison of line extraction algorithms using 2D range data for indoor mobile robotics , 2007, Auton. Robots.

[6]  Trung-Dung Vu,et al.  Laser-based detection and tracking moving objects using data-driven Markov chain Monte Carlo , 2009, 2009 IEEE International Conference on Robotics and Automation.

[7]  B. Vo,et al.  Improved Probability Hypothesis Density (PHD) Filter for Multitarget Tracking , 2005, 2005 3rd International Conference on Intelligent Sensing and Information Processing.

[8]  Claudio Garcia,et al.  Obstacle Detection and Tracking Using Laser 2D , 2010, 2010 Latin American Robotics Symposium and Intelligent Robotics Meeting.

[9]  Michael Thuy,et al.  Non-linear, shape independent object tracking based on 2D lidar data , 2009, 2009 IEEE Intelligent Vehicles Symposium.