KEYWORD |
ELECTRONIC DESIGN AUTOMATION - EDA
Machine Learning Techniques for Automating 3D BIM Modeling of Tunnels
keywords 3D MODELLING, BIM, LIDAR, OBJECTS DETECTION, RECOGNITION, MACHINE LEARNING
Reference persons ANNA OSELLO, EDOARDO PATTI
External reference persons Nicola Rimella (nicola.rimella@polito.it)
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, EDA Group, ELECTRONIC DESIGN AUTOMATION - EDA, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description In recent years, there has been a growing interest in the research of methods and tools that support inspection and maintenance interventions on civil infrastructures (e.g., tunnels). With the aging of these infrastructures, it becomes crucial to develop efficient methods and processes that assist technicians in maintenance management.
Taking Italian tunnels as a case study, starting from point clouds describing the geometry of the tunnels, acquired, for example, through lidar, the goal is to implement a classification algorithm capable of recognizing the different categories of objects within road tunnels. The objective is to test various Machine Learning algorithms, validating their robustness and accuracy, and then automatically create a parametric and virtual 3D Building Information Modeling (BIM) model of the tunnel itself. The outcome will be an artificial intelligence capable of utilizing scalable and reliable point cloud classification and segmentation methods, adapting processes to different point cloud configurations and infrastructure geometries.
Required skills python
Deadline 24/10/2024
PROPONI LA TUA CANDIDATURA