Home // ENERGY 2022, The Twelfth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies // View article

GIS Deep Learning for Power Assets' Detection and Identification

Authors:
Vivian Sultan
Jose Ramirez
Jordan Peabody
Madison Bautista

Keywords: LiDAR; deep learning; point cloud; ArcGIS Pro; point classification.

Abstract:
In this study, ArcGIS Pro 2.8 identified power poles and towers from Light Detection And Ranging (LiDAR) point-cloud data. In previous research, machine learning has identified objects from such data. We sought to demonstrate a deep-learning model developed by the Environmental Systems Research Institute and a group based in Australia and whether deep learning is a viable solution for identifying power assets in three California areas. The deep-learning model was deployed in ArcGIS Pro using the Classify Point Cloud Using Trained Model geoprocessing tool. The model successfully identified some power poles in both rural and urban areas. A better training dataset might improve on this limited success, suggesting that deep learning can successfully classify point clouds. Those interested in using LiDAR point clouds with deep learning to classify power poles and towers should produce training data using accurately labeled data that accurately represents the objects of interest to ensure optimal results with a new model.

Pages: 1 to 5

Copyright: Copyright (c) IARIA, 2022

Publication date: May 22, 2022

Published in: conference

ISSN: 2308-412X

ISBN: 978-1-61208-967-6

Location: Venice, Italy

Dates: from May 22, 2022 to May 26, 2022