Three-Dimensional Reconstruction of Shoe Soles via Binocular Vision Based on Improved Matching Cost

Abstract

Aiming at the problem that the toe cap and upper part of the sole of a shoe easily appear missing when using binocular vision to reconstruct the shoe sole in the industrial production process, an improved matching cost calculation method is proposed to reconstruct shoe soles in three dimensions. Firstly, a binocular vision platform is built, and Zhang’s calibration method is used to obtain the calibration parameters. Secondly, the method of fusing Census and BT costs is used to calculate the matching cost of the image, so that the matching cost calculation result is more accurate. On this basis, 4-path aggregation is performed on the obtained cost, and the optimal matching cost is selected in combination with the WTA algorithm. Finally, left–right consistency detection and median filtering are used to optimize the disparity map and combine the camera calibration parameters to reconstruct the shoe sole in three dimensions. The experimental results show that the average mismatch rate of the four images on the Middlebury website in this method is about 6.57%, the reconstructed sole point cloud contour information is complete, and there is no material missing at the toe and heel.