Curb detection and tracking using 3D-LIDAR scanner

Abstract

This paper presents a novel road curb detection method using 3D-LIDAR scanner. To detect the curbs, the ground points are separated from the pointcloud first. Then the candidate curb points are selected using three spatial cues: the elevation difference, gradient value and normal orientation. Afterwards the false curb points caused by obstacles are removed using the short-term memory technique. Next the curbs are fitted using the parabola model. Finally, the particle filter is used to smooth the curb detection result. The proposed approach was evaluated on a dataset collected by an autonomous ground vehicle driving around the Ford Research campus and downtown Dearborn. Our curb detection results are accurate and robust despite variations introduced by moving vehicles and pedestrians, static obstacles, road curvature changes, etc.

An Algorithm for Automatic Road Asphalt Edge Delineation from Mobile Laser Scanner Data Using the Line Clouds Concept

“…For instance, some studies [6,24,31] focus on the extraction of road markings and, even though some of them report their performance in terms of completeness and correctness, these values are not comparable to the ones obtained in this study, as they do not try to detect the road edge. Several other studies present algorithms for automatic detection of curbs [15,22,23,25,32,34], and most of them assess completeness and correctness, but these refer to the length of the curbs detected. In contrast, Zhao et al [28], Smadja et al [29] and Guan et al [35] show methods for automatically identifying road points from MLS data, but their performance is not assessed.…”

Road Orthophoto/DTM Generation From Mobile Laser Scanning

“…• Precise mapping of road marks (Hervieu et al, 2015), road limits (McElhinney et al, 2010) or curbs (El-Halawany et al, 2011) (Zhao and Yuan, 2012) (Hervieu and Soheilian, 2013b),...…”

“…Laser Scanning (MLS), this extraction can be done based on elevation and gradient features (Zhao and Yuan, 2012), based on extracting large planes at a certain distance below the 3D trajectory of the laser scanner and analysing them (Pu et al, 2011) or with Robust Locally Weighted Regression (Nurunnabi et al, 2013).…”

A Hybrid Vision-Map Method for Urban Road Detection

“…Although 2D LIDARs can directly return this information, only select curb points can be detected using this sensor [13]. 3D LIDAR provides a dense point cloud and thus makes it possible to detect a larger extent of the curb [14]. LIDARs provide precise measurements, which is a very important feature to detect small curbs.…”