A Line Segments Matching Method Based on Epipolar-line Constraint and Line Segment Features

Line segments are ordinary in industrial scene, accurate line segments matching is a key step for many applications, such as 3-D reconstruction. A matching method based on epipolar-line constraint and line segment features is proposed. Firstly, the points on line segments between image pairs are matched by epipolar-line constraint. Secondly, geometric descriptor and gray value descriptor are used to describe the line segment features, then the two descriptors are combined into a feature vector, and Euclidean distance between vectors is used to achieve fine match. Experiment results show that the proposed method is accurate and fast.