基于SVR的宽基线图像匹配方法

Wide baseline image matching using support vector regression

针对宽基线图像匹配处理中的误匹配问题,使用支持向量回归(support vector regression,SVR)方法来解决宽基线图像匹配,采用了一种改进的拓扑过滤器新算法来剔除误匹配。改进拓扑过滤机制匹配大量SIFT(scale-in-variant feature transform)特征,剔除一些误匹配项获得高正确率的初始匹配,实现使用高正确率的初始匹配来构建SVR;同时,基于构建SVR关系给出的预测值附件搜索新的匹配。在宽基线条件下对室内和室外的环境图像进行测试实验,结果表明,该算法能够自动获取大量正确匹配。

Wide baseline matching is solved by using support vector regression（SVR）.High correct ratio initial matches are used to train SVR relationships,obtained by matching large-scale SIFT features and discarding some mismatches by the improved topological filtering scheme.And new matches are searched near the prediction given by trained SVR relationships.Both indoor and outdoor environments image pairs under wide baseline condition are tested,and experiment results show that the algorithm automatically gain large numbers of accurate point correspondences.