Pre-processing Techniques for Grid Stereo Images in the 3D Surface Data Acquisition System

摘要

A novel surface restoral system based on passive stereo vision principle and active raster projection is introduced in this paper. The key techniques of image pre-processing methods used in this system are described in detail. Especially, the Local Weighted Image Smoothness (LWIS) and the Selective Image Enhancement (SIE) techniques proposed here are discussed to help the three dimensional data acquisition from the grid stereo images in the surface restoral system. The experiment results prove the efficiency of these image processing methods.