Dr. Shabnam Jabari, Associate Professor, P.Eng | ASIL

ASIL Researchers to Present at ISPRS Congress 2026 in Toronto

Thu, 11 Jun 2026 00:00:00 +0000

Three researchers from the Advanced Spatial Intelligence Lab will present at the in Toronto, contributing to session IvS3B — Advancing Digital Twins for Urban Environments: Approaches to Mapping, Monitoring, and Management.

The session takes place Monday, July 6, 2026 from 1:30 PM to 3:00 PM in room 716A.

ASIL Presentations

1:45 PM – 2:00 PM

A Comprehensive Evaluation of the Spatial Accuracy of Building Gaussian Splatting Samuel McNally, Shabnam Jabari, Heather McGrath, Mark Masry

2:00 PM – 2:15 PM

Towards Roof Material Identification by Fusing Aerial and Street View Imagery Faezeh SoleimaniVostikolaei, SeyedPooya Soofbaf, Travis Moore, Shabnam Jabari

2:15 PM – 2:30 PM

Evaluating Comparative Performance of 2D and 3D Feature Detection Models for Digital Twinning Colin Richardson, Shabnam Jabari, Liam Delong, Darian Crouse, Travis Moore, Derek Lichti

Session Information

The IvS3B session focuses on emerging approaches to building, maintaining, and applying urban digital twins. ASIL’s three contributions span spatial accuracy assessment of novel 3D representations (Gaussian splatting), multimodal classification of building materials, and benchmarking of feature-detection models for twinning workflows.

The full preliminary program for the congress is available at .

LoD2 Building Reconstruction with Geospatial AI

Wed, 04 Mar 2026 00:00:00 +0000

ASIL develops AI-assisted methods for LoD2 building reconstruction using orthophotos, point clouds, and mobile mapping imagery.

Focus

Extract roof components using graph-based and deep learning approaches
Detect facade elements under occlusion, complex viewpoints, and varying image conditions
Generate robust building models for large urban areas

Research Outputs

Recent work includes journal and conference publications on multimodal segmentation, feature fusion, and reconstruction quality assessment.

Urban Digital Twin Platform

Wed, 04 Mar 2026 00:00:00 +0000

This project develops scalable workflows for generating and updating urban digital twins from mobile mapping, airborne LiDAR, and optical imagery.

Objectives

Build LoD2-ready city models for planning and engineering use
Improve camera-LiDAR registration and quality control
Support downstream climate, hazard, and infrastructure analytics

Methods

Multimodal segmentation and feature extraction
Geometry-aware registration pipelines
Quality assessment using field and reference datasets

Impact

Outputs support municipal planning, emergency preparation, and data-driven infrastructure management.

Urban Heat and Flood Projection Analytics

Wed, 04 Mar 2026 00:00:00 +0000

This research combines geospatial modeling, remote sensing, and AI to project urban heat and flood behavior under development and climate-change scenarios.

Focus

Project urban heat island patterns and identify high-risk hotspots
Map flood susceptibility and assess potential impacts on built environments
Support scenario-based planning for municipalities and public agencies

Application

The framework supports resilience planning, emergency preparedness, and data-driven infrastructure upgrades.