稳定估计F矩阵的双对极点约束算法  

A Robust Biepipole Constraint Algorithm for Estimating Fundamental Matrix

作　　者：陈泽志[1] 吴成柯[1] 

机构地区：[1]西安电子科技大学综合业务网国家重点实验室,西安710071

出　　处：《计算机学报》2000年第11期1140-1145,共6页Chinese Journal of Computers

基　　金：国家自然科学基金!(6 9972 0 39);香港研究基金委员会!(RGC)

摘　　要：从基础矩阵参数的几何意义出发 ,给出了新的估计基础矩阵的约束条件 ,使无约束规划的目标函数由原来的 4元 8次降为 4元 6次 ,并用求解非线性方程的方法求出了双对极点位置 ,实现了 F阵的稳定估计 ,有效地避免了传统的用非线性最小二乘法求解所存在的不足 .实验结果表明 ,文中所提供的方法彻底克服了原双对极点约束方法运算速度慢、存在大量伪解和对极点的不稳定现象 ,实用性较强 .A new geometrical constraint, based on the geometrical analyzing of synthetic method, is developed to estimate fundamental matrix (F-matrix). A nonlinear equation of degree 8 in 4 unknowns for unconstraint optimizing objective function is reduced to a nonlinear equation of degree 6 in 4 unknowns by utilizing the constraint. Two epipoles can be obtained by solving the nonlinear equation. Compared to the traditional Least-Square method, the method is more robust. Experiments show that using the algorithm much more improvement in the speed of calculation can be obtained. Furthermore, problems raised by using two-epipole constrained algorithm, such as existing of pseudo-solution and poor stability of epipoles, can be completely eliminated. Hence, better practicability has bee n achieved.

关 键 词：F矩阵 真实图像 图像匹配 双对极点约束算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]