【摘要】 通过引入Rank变换,提出了一种基于新的匹配基元的双目立体匹配算法,该算法首先是将灰度图像转换为Rank图像,在此基础上进行匹配,并结合汉明码距离约束条件,减少误匹配率,最后得出视差图。通过对比实验,表明采用这种新的匹配基元进行匹配,与直接采用灰度特征作为匹配基元的算法相比,该方法有更好的抗噪性和匹配准确性。更多还原

【Abstract】 New stereo matching approach based on matching primitives from rank transform was proposed. The image was rank transformed from gray-level. Area-matching was processed. After incorrect rate is decreased by Hamming distance constraint, disparity map will be done. The experiment result indicates that the proposed algorithm is the more precise matching and invariance to certain types of image noise than the ones based on intensity.更多还原