Volume XLII-4/W18
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 1001–1007, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-1001-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 1001–1007, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-1001-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  19 Oct 2019

19 Oct 2019

UTILITY POLES EXTRACTION FROM MOBILE LIDAR DATA IN URBAN AREA BASED ON DENSITY INFORMATION

D. Shokri1, H. Rastiveis1, A. Shams2, and W. A. Sarasua3 D. Shokri et al.
  • 1Department of Photogrammetry and Remote Sensing, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
  • 2Advanced Highway Maintenance & Construction Technology (AHMCT) Research Centre, University of California, Davis, CA, USA
  • 3Glenn Department of Civil Engineering, Clemson University, Clemson, SC, USA

Keywords: Utility Poles, Mobile Terrestrial Laser Scanner, Point Clouds, Density Information, Hough Transform, LiDAR

Abstract. Utility poles located along roads play a key role in road safety and planning as well as communications and electricity distribution. In this regard, new sensing technologies such as Mobile Terrestrial Laser Scanner (MTLS) could be an efficient method to detect utility poles and other planimetric objects along roads. However, due to the vast amount of data collected by MTLS in the form of a point cloud, automated techniques are required to extract objects from this data. This study proposes a novel method for automatic extraction of utility poles from the MTLS point clouds. The proposed algorithm is composed of three consecutive steps of pre-processing, cable area detection, and poles extraction. The point cloud is first pre-processed and then candidate areas for utility poles are specified based on Hough Transform (HT). Utility poles are extracted by applying horizontal and vertical density information to these areas. The performance of the method was evaluated on a sample point cloud and 98% accuracy was achieved in extracting utility poles using the proposed method.