Vehicle tracking and motion prediction in complex urban scenarios

The recognition of potentially hazardous situations on road intersections is an indispensable skill of future driver assistance systems. In this context, this study focuses on the task of vehicle tracking in combination with a long-term motion prediction (1-2 s into the future) in a dynamic scenario. A motion-attributed stereo point cloud obtained using computationally efficient feature-based methods represents the scene, relying on images of a stereo camera system mounted on a vehicle. A two-stage mean-shift algorithm is used for detection and tracking of the traffic participants. A hierarchical setup depending on the history of the tracked object is applied for prediction. This includes prediction by optical flow, a standard kinematic prediction, and a particle filter based motion pattern method relying on learned object trajectories. The evaluation shows that the proposed system is able to track the road users in a stable manner and predict their positions at least one order of magnitude more accurately than a standard kinematic prediction method.

[1]  Fridtjof Stein,et al.  Efficient Computation of Optical Flow Using the Census Transform , 2004, DAGM-Symposium.

[2]  A. Barth,et al.  Where will the oncoming vehicle be the next second? , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[3]  Rita Cucchiara,et al.  Predictive and Probabilistic Tracking to Detect Stopped Vehicles , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[4]  Suchendra M. Bhandarkar,et al.  Tracking of Multiple Objects Using Optical Flow Based Multiscale Elastic Matching , 2006, WDV.

[5]  Wolfram Burgard,et al.  Probabilistic Robotics (Intelligent Robotics and Autonomous Agents) , 2005 .

[6]  Shai Avidan,et al.  Support Vector Tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Huadong Meng,et al.  An HMM-Based Algorithm for Vehicle Detection in Congested Traffic Situations , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[8]  Vincent Lepetit,et al.  Monocular Model-Based 3D Tracking of Rigid Objects: A Survey , 2005, Found. Trends Comput. Graph. Vis..

[9]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using orthonormal matrices , 1988 .

[10]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Bernt Schiele,et al.  Model-free tracking of cars and people based on color regions , 2006, Image Vis. Comput..

[12]  Christoph Hermes,et al.  Long-term vehicle motion prediction , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[13]  Frederic Devernay,et al.  A Variational Method for Scene Flow Estimation from Stereo Sequences , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Nitin S. Ujgare,et al.  Kernel Based Object Tracking Using Mean Shift Method , 2012 .

[15]  Tieniu Tan,et al.  A system for learning statistical motion patterns , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  T. Poggio,et al.  A Contour-Based Moving Object Detection and Tracking , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[17]  Gary R. Bradski,et al.  Real time face and object tracking as a component of a perceptual user interface , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[18]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  David C. Hogg,et al.  Learning the distribution of object trajectories for event recognition , 1996, Image Vis. Comput..

[20]  Hans-Hellmut Nagel,et al.  Initialization of Model-Based Vehicle Tracking in Video Sequences of Inner-City Intersections , 2007, International Journal of Computer Vision.

[21]  Christoph Hermes,et al.  3D pose estimation of vehicles using a stereo camera , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[22]  Hans-Hellmut Nagel,et al.  3D Pose Estimation by Directly Matching Polyhedral Models to Gray Value Gradients , 1997, International Journal of Computer Vision.

[23]  Bernd Heisele.  Motion-based Object Detection and Tracking in Color Image Sequence , 2000 .

[24]  Andrew J. Bulpitt,et al.  Learning spatio-temporal patterns for predicting object behaviour , 2000, Image Vis. Comput..

[25]  Stephen J. Maybank,et al.  Vehicle Trajectory Approximation and Classification , 1998, BMVC.

[26]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[27]  Dimitrios Gunopulos,et al.  Elastic Translation Invariant Matching of Trajectories , 2005, Machine Learning.