The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 237–244, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-237-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 237–244, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-237-2022
 
30 May 2022
30 May 2022

STORM DRAIN DETECTION AND LOCALISATION ON MOBILE LIDAR DATA USING A PRE-TRAINED RANDLA-NET SEMANTIC SEGMENTATION NETWORK

L. Mattheuwsen, M. Bassier, and M. Vergauwen L. Mattheuwsen et al.
  • Dept. of Civil Engineering, Geomatics KU Leuven - Faculty of Engineering Technology, Ghent, Belgium

Keywords: storm drain, detection, localisation, semantic segmentation, RandLa-Net, point cloud

Abstract. As the expansion of cities and urban areas results in the construction of more impermeable road surfaces, a well designed urban drainage system becomes of greater importance. However, the accurate and up-to-date mapping of storm drains necessary to create accurate drainage models is often lacking. In recent years, mapping of the road infrastructure is increasingly carried out by highly efficient mobile mapping systems but which lack automatic interpretation of the massive amount data. In this paper we present a fully automatic storm drain detection method to extract and locate storm drain inlets in mobile mapping lidar data. The point cloud is first segmented by a pre-trained RandLa-Net model, which although untrained to segment storm drains, is able the segment storm drain clusters in the hardscape class. The results from this class are further processed by enforcing different requirements to only extract and locate storm drain clusters. Our approach is evaluated on a large testing dataset with 171 storm drains and achieves 81.9%, 95.2% and 88.1% for recall, precision and F1-score respectively. The majority of the false positive and false negative detections are due to incorrect point cloud segmentation of the RandLa-Net. In terms of localisation, our approach achieves an RMSE of 5.5 cm on the centre location while the dimensions of the bounding box are on average 23% off compared to the ground truth.