红外与可见光图像自相似性特征的描述与匹配

Description and matching of self-similarities for IR and visual images

针对红外与可见光图像匹配的难题,提出了一种基于自相似性的异源图像点特征匹配算法。首先对红外与可见光图像进行小邻域平方和计算;再通过构造高斯金字塔,运用FAST-9进行角点检测,使得检测的特征点具有尺度属性;然后,统计特征点邻域的特征信息以确定特征点的主方向;再求取在相应尺度下特征点邻域的相关平面,对相关平面进行区域划分,提取每个区域相关平面的极值以构造100维的自相似性描述子,并对描述子进行归一化处理;而后,剔除不良特征描述子;最后采用最近邻匹配算法进行特征匹配。实验结果表明,提出的算法能够实现红外与可见光图像在视角、旋转、尺度变换下的有效匹配;在保证运算速度的前提下,提出的算法较SIFT算法在正确匹配率方面有明显提高。

A point matching algorithm based on self-similarities is proposed to solve the difficulty of IR and visible im- ages matching. Firstly,sums of square in small neighborhoods are calculated. Secondly,by introducing Gaussian scale space, feature points are extracted by FAST-9 corner detector which has scale-invariance. And the main orientation for each point is assigned according to the neighborhood information. Thirdly, correlation surfaces with corresponding scale are chosen for region. Extreme value of each correlation surface is extracted to construct a normalized descriptor with 100 dimensions. Finally ,the nearest neighbor algorithm is used to match control points after eliminating non-informa- tive descriptors. Experimental results indicate that the proposed method is robust to changes in rotation change, affine change and scale change. Meanwhile, it gets a higher correct ratio than SIFT.