基于模糊逻辑的多尺度小基高比立体匹配方法

Multiscale stereo matching method for small baseline based on fuzzy logic

针对小基高比立体匹配中的辐射差异和深度精度问题,提出一种小基高比立体匹配方法。该方法首先通过小波变换对立体图像构建多尺度空间,然后利用HSL色彩模式下的模糊逻辑相似性测度函数和十字支撑臂自适应窗口技术获取初始匹配成本,再依据"胜者全取"策略计算整数级视差,最后以整数级视差为基础利用基于迭代相位相关法的亚像素匹配方法计算亚像素级视差图。研究结果表明:该立体匹配算法克服了小基高比匹配中的辐射差异问题,同时获得了高精度亚像素级视差,其亚像素精度高于1/20个像素。

A stereo matching method for small baseline was proposed to solve radiometric variations and depth accuracy in small baseline stereovision. Firstly, the multiscale space was constructed using wavelet transform. The raw matching cost was calculated by fuzzy logic based similarity function and cross based window. Then the ＂winner takes all＂ strategy was used to compute integral disparities. Finally, the sub-pixel stereo matching method based on iterative phase correlation was employed to obtain sub-pixel disparities on the basis of integral disparities. The results show that the proposed stereo matching method overcomes the radiometric variations problem and achieves the dense disparity map with sub-pixel precision higher than 1/20.