Visual odometry and map fusion for GPS navigation assistance

This paper describes a new approach for improving the estimation of the global position of a vehicle in complex urban environments by means of visual odometry and map fusion. The visual odometry system is based on the compensation of the heterodasticity in the 3D input data using a weighted nonlinear least squares based system. RANdom SAmple Consensus (RANSAC) based on Mahalanobis distance is used for outlier removal. The motion trajectory information is used to keep track of the vehicle position in a digital map during GPS outages. The final goal is the autonomous vehicle outdoor navigation in large-scale environments and the improvement of current vehicle navigation systems based only on standard GPS. This research is oriented to the development of traffic collective systems aiming vehicle-infrastructure cooperation to improve dynamic traffic management. We provide examples of estimated vehicle trajectories and map fusion using the proposed method and discuss the key issues for further improvement.