CENTRALE LYON - Post-doctorant en vision et apprentissage : Détection automatique de défauts thermiques dans des prises de vues intérieures de façades pour l’aide au diagnostic de qualité des bâtiments
Core
Develop AI and computer vision models to automatically detect thermal defects in interior facade images for building quality diagnosis.
Role type
Post-doctoral researcher (computer vision and machine learning)
Builds
Automated diagnostic proof of concept for building envelope quality
Domain
Construction / Energy efficiency / Computer Vision
Deliverable
production ML models
Required skills
Computer Vision, Machine Learning, Deep Learning, Python, PyTorch
Preferred skills
Frugal learning, Multimodal data fusion, Semantic segmentation, Anomaly detection
Technologies
PyTorch, Python, BIM, Digital Twin
Responsibilities
Define measurement protocols and conduct robotized IR+RGB campaigns; Align spatially IR and RGB images; Develop multimodal fusion methods; Build semantic segmentation models to filter perturbations; Implement thermal anomaly detection and defect classification; Generate structured diagnostics and validate against expert analysis.