An Improved Road Network Modeling and Map Matching for Precise Vehicle Localization

This paper presents a precise and robust road model for Map Matching (MM). Map matching approach is generally used to move vehicle localization output to the nearest road segment in order to improve the accuracy of vehicle lateral localization. Most of the MM approaches adopted piece-wise line segment road network model, which will generate large bias at curve segment or turning point on the intersection. In this paper, a two-dimensional parabola road network model is employed in order to correctly represent vehicle's real state (position and orientation). Furthermore, an advanced longitudinal MM approach is also proposed here by comparing current road geometry model with visual lane detection results to improve longitudinal accuracy. Simulation and real road tests verified the proposed approaches.

[1]  Chenhao Wang,et al.  Vehicle Localization with Global Probability Density Function for Road Navigation , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[2]  Li Jie,et al.  Research on route planning and map-matching in vehicle GPS/dead-reckoning/electronic map integrated navigation system , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[3]  Ernst D. Dickmanns,et al.  Recursive 3-D Road and Relative Ego-State Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  David Bernstein,et al.  Some map matching algorithms for personal navigation assistants , 2000 .

[5]  Dinggang Shen,et al.  Lane detection and tracking using B-Snake , 2004, Image Vis. Comput..

[6]  Miki Haseyama,et al.  A Map Matching Method with the Innovation of the Kalman Filtering (Special Section of Letters Selected from the 1996 IEICE General Conference) , 1996 .

[7]  Earl G. Blackwell.  OVERVIEW OF DIFFERENTIAL GPS METHODS , 1985 .

[8]  H. Degawa,et al.  A New Navigation System With Multiple Information Sources , 1992, The 3rd International Conference on Vehicle Navigation and Information Systems,.

[9]  Keith Redmill,et al.  A simple vision system for lane keeping , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[10]  K. Uchimura,et al.  Fusion of vision, GPS and 3D gyro data in solving camera registration problem for direct visual navigation , 2006 .

[11]  Demin Xiong.  A THREE-STAGE COMPUTATIONAL APPROACH TO NETWORK MATCHING , 2000 .

[12]  Sridhar Lakshmanan,et al.  A deformable-template approach to lane detection , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[13]  J-S Kim.  NODE BASED MAP MATCHING ALGORITHM FOR CAR NAVIGATION SYSTEM , 1996 .

[14]  F. Chausse,et al.  Vehicle localization on a digital map using particles filtering , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[15]  P. G. Mattos.  Integrated GPS and dead reckoning for low-cost vehicle navigation and tracking , 1994, Proceedings of VNIS'94 - 1994 Vehicle Navigation and Information Systems Conference.