Recent advancements in deep learning techniques make automated object/feature extraction from Lidar point clouds possible. In this session we’ll be exploring the usage of two novel deep learning techniques with ArcGIS for both Feature Detection & Segmentation. Using PointCNN, we show how we have replaced 50,000 man hours by automating the detection of utility poles and lines for a big area. Using PointNet, we’ll also be demonstrating how we can automate rail asset extraction. Both examples demonstrate data preprocessing, training data generation, and visualization.

————————————————————————————————————————–
Follow us on Social Media!
Twitter: https://twitter.com/Esri
Facebook: https://facebook.com/EsriGIS
LinkedIn: https://www.linkedin.com/company/esri
Instagram: https://www.instagram.com/esrigram

The Science of Where: http://www.esri.com

source