Hole Filled 3D Map Using Mobile Robots in the Urban Environment

Abstract

3D mapping and expression of the environment are very important with various applications in many different fields. Among the various sensors (vision sensor, infrared sensor, and LiDAR (Light Detection and Ranging) sensor), we used the LiDAR sensor in this paper because its accuracy is good and easy to handle. There exist holes in the result of 3D reconstruction. When these holes are filled, improved results of localization, and path planning are expected. We propose a contour based sampling algorithm to fill holes. It uses the information from regions near the holes for the prediction, and the results confirm that the filled regions look similar to the real environment.