NCC Feature Matching Optimized Algorithm Based on Constraint Fusion

In this paper, a binocular stereo vision three-dimensional (3D) reconstruction algorithm is proposed. In order to reduce the computation in feature extraction process, it begins with selecting candidate corner points, and then uses this as the center to establish the search area. Finally, scale invariant feature transform (SIFT) algorithm is used to extract corner points. In the process of stereo matching, the rough matching point pairs obtained from the Normal Cross Correlation (NCC) algorithm are applied to feature constraints to get the precise matching point pairs so that the final experiment realizes the 3D reconstruction of objects.