3D Vehicle Location Based on Improved Hausdorff Distance and Distributed Estimation Algorithm

3D model is used for vision based vehicle location. An improved Hausdorff distance based on edge-strength is proposed to evaluate the similarity between 3D model projection and image feature, and to establish location optimization function In order to avoid local minimum during optimization, estimation of distribution algorithm concerning related multi-variables is used. The relationship between matching parameters are described with a probability model, and the distribution of parameter evolves towards the direction of dominant character through probability model learning and the corresponding operation, which is proposed to solve the problem of overmany iteration and slow constringency velocity. The experiments show that the optimal matching parameters between 3D model and 2D image feature can be found accurately and efficiently, and the algorithm outperforms other approaches in both accuracy and rapidity.