3D A method of improving the quality of 3D images acquired from RGB-depth camera

摘要

A method for improving the quality of a 3D image obtained from a depth image camera, wherein the quality is improved by processing a 3D image obtained through a texture depth (RGB-Depth) camera on a multi-view camera system, the method comprising: (a) multi-view acquiring a depth image and a texture image; (b) generating a binary image based on the brightness value of the texture image, and generating a mask image from the generated binary image; (c) filtering by applying the mask image to the texture image; (d) performing primary correction by adding an alpha channel to the filtered texture image; (e) filtering the depth image with the mask image; (f) correcting the filtered depth image by applying time-average filtering; (g) secondarily correcting the firstly corrected texture image using the histogram; (h) generating point cloud data from the corrected multi-view depth image and correcting it by removing surface noise; and (i) constructing a curved surface from the corrected point cloud data. Through the above method, a more accurate 3D image may be obtained by improving noise in the depth image, illumination and boundary noise between adjacent color images, noise in point cloud data, noise in surface data, and the like.