光学学报, 2014, 34 (2): 0215003, 网络出版: 2014-01-23
水下环境中基于曲线约束的SIFT特征匹配算法研究
Research on Scale Invariant Feature Transform Feature Matching Based on Underwater Curve Constraint
机器视觉 曲线约束 尺度不变特征变换 水下特征匹配 machine vision curve constraint scale invariant feature transform underwater feature matching
摘要
针对水下双目图像匹配时不再满足空气中极线约束条件以及尺度不变特征变换(SIFT)特征匹配算法处理水下图像误匹配率较高等问题,提出一种基于曲线约束的水下特征匹配算法。对双目摄像机进行标定获取相关参数,再获取参考图和待匹配图;利用SIFT算法对两幅图像进行匹配,同时利用由参考图提取的特征点推导出其在待匹配图上对应的曲线,将该曲线作为约束条件判定待匹配图上对应特征点是否在曲线上,从而剔除误匹配点,以达到提高精度的目的。实验结果表明,该算法优于SIFT算法,可以有效地剔除误匹配点,比SIFT算法匹配精度提高约12%,解决了SIFT算法在水下双目立体匹配中误匹配率高的问题。
Abstract
In the light of underwater binocular image matching cannot satisfy the epipolar constraint of air, and the mismatching rate of underwater image processed by the scale invariant feature transform (SIFT) algorithm is high, we put forward an underwater feature matching algorithm based on curve constraint. Binocular camera should be calibrated, and some relevant parameters are obtained, as well as the reference image and the image to be matched; the SIFT feature matching algorithm can help to match two images, at the same time, the feature points can be extracted from the reference image to deduce the corresponding curve on the image to be matched. The curve is used as a constraint to determine whether the corresponding feature is on it, thus mismatching points will be excluded to achieve a higher accuracy. The test results show that this algorithm is superior to SIFT algorithm and can help to exclude mismatching points effectively. The matching accuracy can increase by about 12%. The problem of SIFT algorithm′s high rate of mismatching for underwater binocular stereo matching is solved.
张强, 郝凯, 李海滨. 水下环境中基于曲线约束的SIFT特征匹配算法研究[J]. 光学学报, 2014, 34(2): 0215003. Zhang Qiang, Hao Kai, Li Haibin. Research on Scale Invariant Feature Transform Feature Matching Based on Underwater Curve Constraint[J]. Acta Optica Sinica, 2014, 34(2): 0215003.