摘要：This paper proposes a method for line matching based on invariance of feature points. Firstly, feature points are roughly matched by Normalized Cross Correlation (NNC) and Average of Square Difference (ASD). Additionally, feature points obtained from the two views are grouped into matched point pairs. Finally, curve segments between matched point pairs are matched by dynamic programming algorithm with edge potential functions (EPF) taken as the measure. The proposed method makes full use of feature points, the relationship between feature points and the curve, and space information of the gray image.
