Detection of Road Objects and Road Signs from 3D Mobile Mapping System

Abstract

As the number of practical applications of point clouds from a mobile mapping system (MMS) increases, the use of modeled data from MMS has also increased in many fields. However, the data-modeling process is costly. Therefore, in order to make the modeling process efficient, a method of recognizing road objects is needed. Conventional methods cannot recognize objects that include various shapes such as walls and guardrails, or objects that are close to others. High-definition and highly accurate road maps are necessary for the realization of automated driving, and road signs are among the most important element in the road map. Therefore, a technique is necessary which can acquire information about all kinds of road signs automatically and efficiently. We propose a method for recognizing road objects by focusing on smaller local areas of the object by using a support vector machine. Our method can robustly identify pole-like objects at 96.6% accuracy and walls at 99.0% accuracy. Due to the continuous technical advancement of Mobile Mapping System (MMS), it has become possible to acquire large number of images and 3d point cloud efficiently with highly precise position information. In this paper, we present an automatic road sign detection and recognition approach utilizing both images and 3D point cloud acquired by MMS.