3D Reconstruction of Weak Texture Surface Based On Binocular Vision

With the rapid development of computer science and image processing technology, 3D reconstruction and measurement of surface based on computer vision have become a research trends. However, for the weak texture surface, it is difficult to extract enough key points through general corner detection algorithms. Based on the principle of binocular stereo vision, this paper proposes a method of pasting circular markers to research 3D reconstruction of weak texture surface. This method can rich the surface's texture information used to feature extraction, so it can efficiently extract more key points. The results show that this proposed method is feasible and greatly improve 3D reconstruction of weak texture surface.