One-class anomaly detection through color-to-thermal AI for building envelope inspection

TL;DR

This paper introduces a label-free AI method that predicts thermal distributions from color images to detect anomalies in building envelopes, aiding inspections without prior thermal labels.

Contribution

It presents a novel one-class classification approach using AI-driven thermal prediction from color images for building envelope inspection.

Findings

Successfully detected thermal bridges in outdoor conditions.

Can be integrated with mobile platforms for large-scale inspections.

Operates without labeled thermal data.

Abstract

We present a label-free method for detecting anomalies during thermographic inspection of building envelopes. It is based on the AI-driven prediction of thermal distributions from color images. Effectively the method performs as a one-class classifier of the thermal image regions with high mismatch between the predicted and actual thermal distributions. The algorithm can learn to identify certain features as normal or anomalous by selecting the target sample used for training. We demonstrated this principle by training the algorithm with data collected at different outdoors temperature, which lead to the detection of thermal bridges. The method can be implemented to assist human professionals during routine building inspections or combined with mobile platforms for automating examination of large areas.