摘要
提出了一种基于局部仿射不变量特征的宽基线影像匹配算法。该算法以影像特征点为定位点,使用分层变尺度窗口内的几何和亮度仿射不变量特征实现立体匹配。由于使用局部特征,在较大窗口范围内构造尺度、旋转不变特征,以及将大窗口划分为较小的子区域,因此,该算法具有较高的匹配可靠性、较高的效率和匹配精度。
A novel algorithm based on local arlene invariants was proposed for searching correspondences between images in the most general case. Image point features were used as anchor points and the local space-variant regions around the anchor point were used as local window region to generate geometric and brightness arlene invariants for image matching. The method is efficient because only the local image features are used in the process, The matching results are reliable and robust because its feature matching region is relatively large, and the shape of local window region was transformed according to possible projective deformation. In addition, overlapped sub-regions were used in local feature extraction to reduce partially occluding problems.
出处
《计算机应用》
CSCD
北大核心
2006年第5期1001-1003,1014,共4页
journal of Computer Applications
基金
国家973规划资助项目(2004CB719400)
国家863计划资助项目(2004AA115120)
国家自然科学基金资助项目(60173062)
作者简介
王宇宙（1964-），男，山东博兴人．高级工程师，博士，主要研究方向：计算机视觉、图像处理；（wangyuzhou@pku．edu．cn）
汪国平（1964-），男，浙江嵊州人，教授，博士生导师，主要研究方向：人机交互与虚拟现实、计算机图形学与计算几何．
