Vehicle geo-localization using IMM-UKF multi-sensor data fusion based on virtual 3D city model as a priori information

The major contribution of this paper concerns vehicle geo-localization in urban environment by integrating a new source of information that is a virtual 3D city model. The 3D model provides a realistic representation of the vehicle's navigation environment. To optimize the performance of vehicle geo-localization system, several sources of information are used for their complementarity and redundancy: a GPS receiver, proprioceptive sensors (odometers and gyrometer), exteroceptive sensors (video camera or laser scanner) and a virtual 3D city model as a priori information. The proprioceptive sensors allow to continuously estimate the dead-reckoning position and orientation of the vehicle. Moreover, two concepts based on 3D virtual model and exteroceptive sensors could be envisaged to compensate the drift of the dead-reckoning localization when GPS measurements are unavailable for a long time. The first proposed approach is based on the matching between the virtual image extracted from the 3D city model and the real image acquired by the camera. This observation construction is composed of two major parts. The first part consists in detecting and matching the feature points of the real and virtual images. Three features are compared: Harris corner, SIFT (Scale Invariant Feature Transform) and SURF (Speed Up Robust Features). The second part is the pose computation using POSIT algorithm and the previously matched features set. The second approach uses an on-board horizontal laser scanner which provides a set of distances. This set of distances (real laser scan data) is matched with depth information of virtual laser scan data obtained using the virtual 3D city model which is managed in real-time by a 3D Geographical Information System (3D-GIS). GPS measurements, proprioceptive sensors based pose estimation, and camera/3D model based pose estimation are integrated in IMM UKF data fusion formalism. The developed approaches have been tested on a real sequence and the obtained results proved the feasibility of the approach.

[1]  Maan El Badaoui El Najjar,et al.  Towards an Estimate of Confidence in a Road-Matched Location , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[2]  Simone B. Bortolami,et al.  Localization of the subjective vertical during roll, pitch, and recumbent yaw body tilt , 2006, Experimental Brain Research.

[3]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[4]  Yunhui Liu,et al.  3D reconstruction based on SIFT and Harris feature points , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[5]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[6]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[7]  Marie-José Aldon,et al.  Mobile robot attitude estimation by fusion of inertial data , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[8]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[9]  Zhengyou Zhang,et al.  Iterative point matching for registration of free-form curves and surfaces , 1994, International Journal of Computer Vision.

[10]  Fredrik Gustafsson,et al.  Particle filters for positioning, navigation, and tracking , 2002, IEEE Trans. Signal Process..

[11]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[12]  Larry S. Davis,et al.  Model-based object pose in 25 lines of code , 1992, International Journal of Computer Vision.

[13]  Mohinder S. Grewal,et al.  Global Positioning Systems, Inertial Navigation, and Integration , 2000 .

[14]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[15]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[16]  D. Powell,et al.  Land-vehicle navigation using GPS , 1999, Proc. IEEE.

[17]  J.-S. Gutmann,et al.  AMOS: comparison of scan matching approaches for self-localization in indoor environments , 1996, Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96).