Real-time pixel-level fusion of colour and thermal (RGB-T) imagery via extrinsic optical alignment: Scope for automating building inspections’,

Shariq, Hasan; Hughes, B. R.

Abstract

Building inspections and energy surveys are performed to detect and diagnose building defects, however, existing inspection methods are highly labour intensive, time consuming, and not suitable for large-scale audits. This work presents a thermal-colour fusion technique using pre-capture optical alignment that eliminates the need for compute-intensive post-processing of data. The coinciding axes of dual cameras also prevent parallax errors, which helps expand its applications to near proximity or indoor thermal inspection as well. A prototype of this design was assembled and tested, which showed a pixel-level accurate alignment of thermal and colour camera imagery with minimal computation. The research and development in this paper provides scope and feasibility to automate building inspection techniques through drone-based low-powered embedded machine learning models and identify faults in real-time for large-scale surveys of building façades.

Citation

Shariq, H., & Hughes, B. R. (2021, September). Real-time pixel-level fusion of colour and thermal (RGB-T) imagery via extrinsic optical alignment: Scope for automating building inspections’,. Presented at International Conference on Evolving Cities (ICEC 2021), Southampton, UK

• Presentation Conference Type: Conference Paper (published)
• Conference Name: International Conference on Evolving Cities (ICEC 2021)
• Start Date: Sep 22, 2021
• End Date: Sep 24, 2021
• Acceptance Date: Aug 19, 2021
• Online Publication Date: Feb 15, 2022
• Publication Date: Feb 15, 2022
• Deposit Date: Nov 1, 2024
• Publicly Available Date: Aug 18, 2025
• Peer Reviewed: Peer Reviewed
• Book Title: Proceedings of the 2nd International Conference on Evolving Cities
• ISBN: 2754-5768
• DOI: https://doi.org/10.55066/proc-icec.2021.30
• Keywords: Building Inspection; Real-time Fault Detection; RGB-T Fusion
• Public URL: https://hull-repository.worktribe.com/output/4904708
• Publisher URL: https://publications.evolvingcities.org/proc-icec/article/view/30