Digital Twin for Civil Engineering Design Workflow

McElhanney provides Engineering and Surveying services across Canada. They want to leverage the AI feature extraction work conducted in 2021 – 22 (Mitacs Accelerate IT23104) whereby the University of Alberta interns helped to extract physical municipal assets (fire hydrants, street lights, manholes, curbs, etc.) from detailed terrestrial laser scanning (TLS) data, i.e., LiDAR point-clouds. This work led McElhanney to be able to run Machine Learning based algorithms on LiDAR captured point-cloud scenes to identify and extract asset features for use in civil engineering design workflows. While this work achieved substantial progress with publications, we want to go beyond the labour-intensive feature extraction and begin to associate engineering attributes to those features so that they can be accurately represented in a digital twin, which will be used for a more efficient object annotation framework for professional surveying purposes. To achieve this attribution, we propose to deploy the use of AR/VR technology on the premise that the immersive experience can expedite and enhance attribute annotations and scene understanding.

Faculty Supervisor:

Irene Cheng

Student:

Partner:

McElhanney

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

University of Alberta

Program: