NM Group researching machine learning for extracting complex powerline features from lidar


NM Group, a provider of asset management, survey and mapping solutions for the power sector, is exploring the use of machine learning and deep learning approaches to improve automatic feature extraction from lidar data.

The R&D project will be undertaken as part of an ongoing relationship with Durham University, with a research associate working in NM Group for a year. That associate will complete academic research and, “crucially,” apply it in the industry-specific context of lidar data use for electrical networks.

“Automatic feature extraction has been around for a while,” explained senior client manager for NM Group Tim Hustwayte. The technology is currently capable of extracting information like the location of infrastructure, vegetation, buildings, and powerline assets. However, Hustwayte continunes, “we still have not seen an example that provides the quality and accuracy that we need to produce our service. Therefore, this project will be about leveraging the latest academic research to help deliver something new and practical.”

In an official statement, NM Group says that the research is intended to develop feature identification with high enough accuracy to “reliably identify complex powerline features in sufficient detail.”


About Author

SPAR 3D Editor Sean Higgins produces SPAR 3D's weekly newsletters for 3D-scanning professionals, and spar3d.com. Sean has previously worked as a technical writer, a researcher, a freelance technology writer, and an editor for various arts publications. He has degrees from Hampshire College in Amherst, Massachusetts and the University of Aberdeen in Scotland, where he studied the history of sound-recording technologies. Sean is a native of Maine and lives in Portland.

Leave A Reply

© Diversified Communications. All rights reserved.