一种立体匹配的新算法

A Novel Stereo Matching Algorithm

提出了一种基于遗传算法进行立体匹配,并获得高密度视差图的方法。遗传算法比其它优化方法具有更强的搜索能力,因此非常适用于求解全局优化问题。利用这一特点,该文将每一幅视差图看作是一个个体,将视差值编码形成染色体,这样每个个体中都有许多染色体。然后,引入匹配约束条件,形成目标函数,利用遗传算法搜索全局最优解。另外,还采用了由粗到精的层次策略来减少匹配模糊性和搜索时间。最后,分别用合成图像和真实图像对这种方法进行了验证。

This paper presents an approach to address the stereo correspondence problem using genetic algorithms (GAs) so as to obtain a dense disparity map. Among a wide variety of optimization methods, GAs are proven to be potentially effective one for the global optimization problems with large search space. With this idea, each disparity map is viewed as an individual and the disparity values are encoded as chromosomes, so each individual contains lots of chromosomes in the approach. Then, several matching constraints are formulated into an objective function, and GAs are used to search for the global optimal solution. Furthermore, the coarse- to-fine strategy is embedded in the approach so as to reduce the matching ambiguity and the time cost. At the end of this paper, experimental results on synthetic and real images are shown to illustrate the performance of the work.