Binocular speckle structured light three-dimensional reconstruction method and system

Abstract

The invention relates to a binocular speckle structured light three-dimensional reconstruction method and system. The method comprises the steps that a speckle image is acquired; building a binocularstructured light vision system, and calibrating to obtain internal parameters and external parameters of the left and right cameras; projecting the speckle image to the surface of the measured objectthrough projection equipment, and shooting through a left camera and a right camera to obtain a left image and a right image; epipolar correction is performed on the left and right images; performingimage matching on the left image and the right image by adopting an improved SGM algorithm based on the speckle image to obtain a parallax image; and based on the internal parameters and the externalparameters of the left and right cameras and the parallax image recovery depth information, obtaining three-dimensional data of the surface of the measured object, and obtaining a final image. According to the method, the speckle distribution constraint window is preset to control the density degree of pseudo-random speckle distribution, the speckle pattern with high identification degree and richtextures is generated, and the new parallax calculation cost function is established, so that the image matching precision is effectively improved, and the accurate three-dimensional dynamic reconstruction method is realized.

Description

technical field [0001] The invention relates to the field of three-dimensional reconstruction, in particular to a method and system for three-dimensional reconstruction of binocular speckle structured light. Background technique [0002] The existing structured light 3D reconstruction technology mainly adopts coding methods, which are divided into time coding method and spatial coding method. The former continuously projects coded images onto the object surface and codes according to the time sequence of the projected images, which has high measurement accuracy. , The advantage of high measurement resolution, but its measurement speed is slow, so it is suitable for three-dimensional information acquisition of static targets and scenes; the latter only needs to project a coding pattern, and its coding information consists of spatial coding features or their different combinations The process of encoding and decoding can be completed in a single image, so the measurement speed...

AI Technical Summary

Problems solved by technology

However, the traditional SGM algorithm (semi-global matching method, SGM) has a local plane assumption, and trapezoidal phenomena will appear when reconstructing inclined surfaces, resulting in low reconstruction accuracy. The present invention proposes an improved SGM algorithm. By establishing a new parallax Calculate the cost function to improve the problem that the traditional SGM algorithm cannot effectively deal with the inclined surface, so as to realize the accurate three-dimensional dynamic reconstruction method

Images