摘要:
在移动测量系统获取的街道序列影像中,建筑物立面占有相当大的比例,而通常建筑物立面含有大量的规则重复纹理.利用特征匹配的方法对此类影像进行匹配时,容易造成大量的误匹配,严重影响后期的影像定向以及三维重建.针对此问题,提出了一种利用相位相关算法辅助KLT(Kanade- Lucas-Tomasi)对角点进行跟踪,从而实现特征匹配的算法.首先,在整体上利用相位相关将待匹配的影像对进行粗配准;然后,使用KLT算法从影像中提取局部角点特征并进行跟踪匹配.实验结果表明,该算法对建筑物密集的街道序列影像匹配的正确率比单纯利用特征匹配方法有较大提高,且匹配的特征角点分布也比较均匀,能够有效解决街道序列影像中重复纹理区域的特征匹配问题.
Abstract:
Building facade is the main content of street images captured by mobile measurement system and contains a lot of regular repeating textures. Applying feature matching algorithm to such images may cause a lot of false matches,which seriously affect the later image orientation and three-dimensional reconstruction. To solve this problem,this paper proposes a phase correlation supported KLT (Kanade-Lucas-Tomasi)feature track-matching algorithm. Firstly, phase correlation algorithm was applied from global to local scale to get crude registration. Then the KLT algorithm was used to track the corners at each matched area. The experimental results show that,when match between building dense street images,the algorithm proposed have a greater increase than pure feature matching algorithm in correct matching rate, and the distribution of features is relatively uniform, which can effectively solve the feature matching problem of street images with regular repeating textures.
下载: