一种快速的空间变换模型计算方法  

Fast Calculation Method of Space Transform Model

作　　者：路晓静[1] 黄向生[1] 

机构地区：[1]中国科学院自动化研究所,北京100090

出　　处：《计算机科学》2014年第3期279-281,292,共4页Computer Science

基　　金：基于超多视角成像的三维重建关键技术研究(61175034)资助

摘　　要：提出一种基于Sobel算子特征点检测的快速空间变换模型计算方法。利用Sobel算子对边缘的敏感特性生成Sobel描述器,进行特征点的描述和匹配,并运用PROSAC算法快速消除误匹配,从而计算出空间变换模型。实验结果表明,算法采用简单的Sobel算子组合成描述器,快速提取出了图像中的特征点,并且根据相似性描述器准确地进行了特征点匹配,提高了空间变换模型的计算速度,为增强现实和图像拼接等视觉领域应用提供了前提[1,2]。A novel fast spatial transformation model calculation approach,based on Sobel operator feature point detection,was proposed.The Sobel descriptor is constructed by taking advantages of the sensitive characteristics of Sobel operator on edge.The features are extracted and matched.Then the wrong matching points are eliminated by PROSAC algorithm,and the spatial transformation model between two images is calculated.The experimental results demonstrate that the simple structure Sobel descriptor can extract the feature points with high speed and match the feature points between two images exactly,thus improve the calculation speed,provide a method for augmented reality and image mosaic etc.

关 键 词：SOBEL算子 描述器 特征点 特征点匹配 PROSAC 增强现实 图像拼接 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]