Line Segment Based Man-Made Object Recognition Using Invariance

Abstract

The traditional three-dimensional object recognition method based on hypothesise and test need to solve the coordinate transformation matrix from scene to model through a group of non-linear equations. Therefore, it has a very high complexity. This paper presents a man-made object recognition method based on the geometry feature of line segments characteristics, and disperses the overall coordinate transformation calculation in every local plane homography calculation, reduces the complexity of the solution. First we prematch the feature points using geometric invariants, then assume and solve the plane homography matrix between scenes to model. After that we match the line segments on the homography plane, and by this we verify the assumption. Experiments proved that this method can rapidly and accurately identify man-made objects which contain coplanar line segment features.