ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 27–34, 2021
https://doi.org/10.5194/isprs-annals-V-2-2021-27-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 27–34, 2021
https://doi.org/10.5194/isprs-annals-V-2-2021-27-2021

  17 Jun 2021

17 Jun 2021

FAST WEAKLY SUPERVISED DETECTION OF RAILWAY-RELATED INFRASTRUCTURES IN LIDAR ACQUISITIONS

S. A. Guinard, J.-P. Riant, J.-C. Michelin, and S. Costa D’Aguiar S. A. Guinard et al.
  • SNCF Réseau / Directions Techniques Réseau / DGII TTD MATRICE, 9 Avenue François Mitterand, 93210 Saint-Denis, France

Keywords: Railway, Classification, Segmentation, Random Forest, LiDAR

Abstract. Railroad environments are peculiar, as they combine dense urban areas, along with rural parts. They also display a very specific spatial organization. In order to monitor a railway network a at country scale, LiDAR sensors can be equipped on a running train, performing a full acquisition of the network. Then most processing steps are manually done. In this paper, we propose to improve performances and production flow by creating a classification of the acquired data. However, there exists no public benchmark, and little work on LiDAR data classification in railroad environments. Thus, we propose a weakly supervised method for the pointwise classification of such data. We show that our method can be improved by using the l0-cut pursuit algorithm and regularize the noisy pointwise classification on the produced segmentation. As production is envisaged in our context, we designed our implementation such that it is computationally efficient. We evaluate our results against a manual classification, and show that our method can reach a FScore of 0.96 with just a few samples of each class.