基于张量投票的摄像机自标定方法研究  

Study of camera self-calibration method based on tensor voting

作　　者：王君竹[1] 陈丽芳[1] 刘渊[1] WANG Junzhu;CHEN Lifang,;LIU Yuan(School of Digital Media, Jiangnan University, Wuxi, Jiangsu 214122, China)

机构地区：[1]江南大学数字媒体学院,江苏无锡214122

出　　处：《计算机工程与应用》2016年第15期190-197,共8页Computer Engineering and Applications

基　　金：江苏省自然科学基金青年基金(No.BK20130161);无锡市科技支撑计划(社会发展)(No.CSE01N1206)

摘　　要：针对传统的基于Kruppa方程摄像机自标定算法的欠鲁棒性,首次提出将鲁棒的张量投票算法用于摄像机自标定方法中。利用基于尺度不变的SIFT算法查找并匹配出每对图像的特征点,其中待匹配图像由摄像机对同一场景从三个不同角度位置拍摄,对图像张量投票后按棒张量特征值降序排序,由此筛选得到具有鲁棒性边缘特征的前八对特征点,利用八点算法求解相应的基础矩阵和极点,根据Kruppa方程和三维重建(SFM)算法求得摄像机参数矩阵。实验结果证明,该方法具有较高标定精度,并通过加入高斯噪声的仿真实验证明该算法是一种鲁棒的摄像机自标定方法。In order to improve robustness of the traditional camera self-calibration algorithm based on Kruppa equations,the new method of camera self-calibration based on tensor voting is first proposed. The SIFT algorithm, based on scaleinvariant property, is adopted to extract and match the feature points of each image, which are taken from three differentangles to the same scene. The first eight feature points with robustness are figured out with tensor voting and sorting.Then the fundamental matrix and the pole points are calculated by 8 points’algorithm, and finally the parameter matricesof camera can be obtained by the Kruppa equations and the Structure From Motion(SFM)algorithm. Compared with otheralgorithms through the comparative experiments, this method is proven to be more accurate, meanwhile, it can be regardedas a new robust camera self-calibration algorithm by the simulation experiments with Gaussian noise.

关 键 词：摄像机自标定 Kruppa 方程 尺度不变特征变换(SIFT) 张量投票 基础矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]