Multi-photo evidence fusion and VLM benchmarking for automated form filling - BC-1039

Genre de projet: Recherche
Discipline(s) souhaitée(s): Génie - civil, Génie, Informatique, Sciences mathématiques, Mathématiques
Entreprise: Anonymous
Durée du projet: 4 à 6 mois
Date souhaitée de début: 11/02/2026
Langue exigée: Anglais
Emplacement(s): Richmond / Vancouver, BC, Canada
Nombre de postes: 1
Niveau de scolarité désiré: MaîtriseDoctorat
Ouvert aux candidatures de personnes inscrites à un établissement à l’extérieur du Canada: No

Au sujet de l’entreprise: 

The partner organization (ANONYMOUS) is an established Canadian electrical utility consulting firm based in British Columbia, with a team of approximately 95 professionals. The company provides engineering services to major Canadian utilities across transmission, distribution, substation, and telecommunications infrastructure. A significant part of its practice is distribution pole replacement design: assessing end-of-life wood poles and producing the engineering design required to replace them safely and to standard. The company is investing in an applied AI/R&D program that uses computer vision and machine learning to automate the interpretation of field photographs of utility poles, so that engineering design information currently extracted manually can be pre-filled automatically with calibrated confidence scores and clear flags for designer review. Interns joining this program work with a real production dataset of field imagery and design records, alongside the company's internal ML, platform, and engineering teams, with a direct path from research results to deployment in a production design workflow.

Veuillez décrire le projet.: 

What is the project about / main goal: This project explores whether field photos can provide useful distance estimates for pole-replacement planning — anchor lead to pole, stake to existing pole, and stake to proposed new pole location — where manual measurements are currently required, with confidence scoring and a "manual measurement required" fallback for unreliable cases.
Main tasks to be performed by the candidate:
• Detect and localize existing pole base, anchors, guy wires, survey stakes, proposed pole markers, and curb/sidewalk/road reference features
• Evaluate monocular depth estimation, geometric calibration from known dimensions, and multi-photo triangulation where metadata is available
• Develop confidence rules separating usable estimates from cases requiring manual survey input
• Validate image-derived estimates against measured ground-truth distances from field records; stretch: estimate direction and offset of the proposed new pole location
Methodology/techniques to be used: Geometry-aware computer vision and photogrammetry; targets: median absolute distance error ≤ 0.5 m for clear cases, ≥ 80% of unreliable cases correctly flagged for manual review.

Expertise ou compétences exigées: 

Photogrammetry; monocular depth estimation; geometry-aware computer vision; practical ML systems.
Optional: assets
Production dataset of utility-pole field imagery with linked engineering design records; internal labeling platform and labeling pipeline; existing trained baseline models to build on; cloud GPU compute; day-to-day co-supervision by the company's internal ML and platform team.