Multisensor simultaneous vehicle tracking and shape estimation

This work focuses on vehicle automation applications that require both the estimation of kinematic and geometric information of surrounding vehicles, e.g., automated overtaking or merging. Rather then using one sensor that is able to estimate a vehicle's geometry from each sensor frame, e.g., a lidar, a multisensor simultaneous vehicle tracking and shape estimation approach is proposed. Advanced measurement models and adequate Bayesian filters enable the shape estimation that is impossible with any of the sensors individually. The use of multiple sensors increases robustness, lowers the complexity of the sensors involved and leads to a gradual loss of performance in case a sensor fails. A series of real world experiments is performed to analyze the performance of the proposed method.

[1]  Joris De Schutter,et al.  Shape-Based Online Multitarget Tracking and Detection for Targets Causing Multiple Measurements: Variational Bayesian Clustering and Lossless Data Association , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Sebastian Thrun,et al.  Model based vehicle detection and tracking for autonomous urban driving , 2009, Auton. Robots.

[3]  Sergiu Nedevschi,et al.  Stereovision-Based Multiple Object Tracking in Traffic Scenarios Using Free-Form Obstacle Delimiters and Particle Filters , 2015, IEEE Transactions on Intelligent Transportation Systems.

[4]  Torsten Bertram,et al.  Track-to-Track Fusion With Asynchronous Sensors Using Information Matrix Fusion for Surround Environment Perception , 2012, IEEE Transactions on Intelligent Transportation Systems.

[5]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[6]  Christian Lundquist,et al.  Estimating the shape of targets with a PHD filter , 2011, 14th International Conference on Information Fusion.

[7]  Werner Huber,et al.  Experience, Results and Lessons Learned from Automated Driving on Germany's Highways , 2015, IEEE Intelligent Transportation Systems Magazine.

[8]  M.L. Miller,et al.  Optimizing Murty's ranked assignment method , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[9]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[10]  Krzysztof Wegner,et al.  Vehicle dimensions estimation scheme using AAM on stereoscopic video , 2013, 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[11]  Peter Mühlfellner,et al.  Object tracking from medium level stereo camera data providing detailed shape estimation using local grid maps , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[12]  J. Munkres.  ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[13]  Silvio Savarese,et al.  Robust real-time tracking combining 3D shape, color, and motion , 2016, Int. J. Robotics Res..

[14]  Joseph L. Mundy,et al.  Vehicle Surveillance with a Generic, Adaptive, 3D Vehicle Model , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[16]  Mark E. Campbell,et al.  Joint tracking and non-parametric shape estimation of arbitrary extended objects , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Klaus C. J. Dietmayer,et al.  Simultaneous tracking and shape estimation with laser scanners , 2013, Proceedings of the 16th International Conference on Information Fusion.