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: / esri
Facebook: / esrigis
LinkedIn: / esri
Instagram: / esrigram
The Science of Where: www.esri.com
6 апр 2020
