A Fast 3D Reconstruction Method Based on Curve Segment of Binocular Vision

Aiming at the problem of low efficiency of the 3D reconstruction, a fast method based on piecewise quadratic curve is proposed. Firstly, a multi-line structured light binocular vision measurement system is used to obtain the two-dimensional image. Through the two-dimensional image, the center line and feature points of the laser strip are quickly acquired. Then, the acquired feature points are used as the given data points of curve interpolation, and NURBS curves are used to interpolate the feature lines of the image. According to the perspective invariance principle of plane curve, the zero curvature point and cusp point on the curve are detected and used as segmentation points. Using the segmentation results, a number of points on each NURBS curve segment are taken to fit as the quadratic curve. Finally, by constructing the right and left space straight taper surfaces, the three-dimensional reconstruction of the feature lines is completed by the method of surface intersection. Taking the black shoe sole as the experimental object, the results show that the method proposed in this paper can quickly complete the three-dimensional reconstruction of the inner and outer feature lines of the shoe sole, which can provide the basis and guarantee for the follow-up shoe sole process monitoring and quality inspection.