Efficient and robust vehicle localization

We propose a novel algorithm for efficient and robust pose determination of vehicles in traffic scenes from single monocular intensity images using calibrated cameras. We consider the pose determination process as a series of evolutions from initial pose to correct pose in 3D space, which can be decomposed into two independent 3D motions: translation and rotation. The translation parameters are obtained based on point-to-line-segment distance (PLS distance), while the rotation parameters are determined by geometric relationships among a set of specially constructed but imaginary planes. Closed-form solutions to both sub-problems are obtained, thus avoiding the usual shortcoming of relatively high computational cost of traditional 3D-model based approaches. In addition, vertex neighborhood constraint (VNC) is introduced to improve the robustness of the method. Experimental results show that the algorithm works well even under severe occlusion and clutter