Vehicle recognition based on three-dimensional model

The recognition of three-dimensional (3-D) objects from single monocular intensity images is one of the fundamental problems in computer vision. The proposed vehicle recognition algorithm is based on the matching between 3-D model projection and target image. The improved modified Hausdorff distance is proposed to measure the degree of similarity between 3-D model projection and image outline. The simulated annealing algorithm with a mnemon and variant frequency is introduced to obtain the optimal solution of matching function. Recognition is then achieved based on the temporal consistency of the evaluation score. Experiments show the validation of the algorithm.