Segmentation Framework for Heat Loss Identification in Thermal Images: Empowering Scottish Retrofitting and Thermographic Survey Companies

TL;DR

This paper introduces a deep learning segmentation framework using Mask RCNN to automatically identify heat loss sources in thermal images, aiming to assist Scottish retrofitting efforts and reduce manual analysis.

Contribution

It presents a novel application of Mask RCNN with transfer learning for thermal image segmentation in energy efficiency assessments.

Findings

Achieved a 77.2% mean average precision in segmenting heat loss sources.

Validated the framework with 1800 annotated thermal images from real-world data.

Demonstrated potential to automate and improve accuracy in thermal image analysis.

Abstract

Retrofitting and thermographic survey (TS) companies in Scotland collaborate with social housing providers to tackle fuel poverty. They employ ground-level infrared (IR) camera-based-TSs (GIRTSs) for collecting thermal images to identi-fy the heat loss sources resulting from poor insulation. However, this identifica-tion process is labor-intensive and time-consuming, necessitating extensive data processing. To automate this, an AI-driven approach is necessary. Therefore, this study proposes a deep learning (DL)-based segmentation framework using the Mask Region Proposal Convolutional Neural Network (Mask RCNN) to validate its applicability to these thermal images. The objective of the framework is to au-tomatically identify, and crop heat loss sources caused by weak insulation, while also eliminating obstructive objects present in those images. By doing so, it min-imizes labor-intensive tasks and provides an automated, consistent, and reliable solution. To validate the proposed framework, approximately 2500 thermal imag-es were collected in collaboration with industrial TS partner. Then, 1800 repre-sentative images were carefully selected with the assistance of experts and anno-tated to highlight the target objects (TO) to form the final dataset. Subsequently, a transfer learning strategy was employed to train the dataset, progressively aug-menting the training data volume and fine-tuning the pre-trained baseline Mask RCNN. As a result, the final fine-tuned model achieved a mean average precision (mAP) score of 77.2% for segmenting the TO, demonstrating the significant po-tential of proposed framework in accurately quantifying energy loss in Scottish homes.