The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B1-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2020, 65–71, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B1-2020-65-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2020, 65–71, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B1-2020-65-2020

  06 Aug 2020

06 Aug 2020

A BOUNDARY-ENHANCED SUPERVOXEL METHOD FOR EXTRACTION OF ROAD EDGES IN MLS POINT CLOUDS

Z. Sha1, Y. Chen1, W. Li1, C. Wang1, A. Nurunnabi2, and J. Li1,3 Z. Sha et al.
  • 1Fujian Key Laboratory of Sensing and Computing for Smart Cities, School of Informatics Xiamen University, Xiamen, Fujian 361005, China
  • 2Faculty of Science, Technology and Communication, University of Luxembourg, Belval Campus, 2 avenue de l'Université, L-4365 Esch-sur-Alzette, Luxembourg
  • 3Departments of Geography and Environmental Management and Systems Design Engineering, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada

Keywords: mobile laser scanning, point cloud, road edge, detection, supervoxel

Abstract. Road extraction plays a significant role in production of high definition maps (HD maps). This paper presents a novel boundary-enhanced supervoxel segmentation method for extracting road edge contours from MLS point clouds. The proposed method first leverages normal feature judgment to obtain 3D point clouds global geometric information, then clusters points according to an existing method with global geometric information to enhance the boundaries. Finally, it utilizes the neighbor spatial distance metric to extract the contours and drop out existing outliers. The proposed method is tested on two datasets acquired by a RIEGL VMX-450 MLS system that contain the major point cloud scenes with different types of road boundaries. The experimental results demonstrate that the proposed method provides a promising solution for extracting contours efficiently and completely. Results show that the precision values are 1.5 times higher and approximately equal than the other two existing methods when the recall value is 0 for both tested two road datasets.