Deep Learning for Detecting Building Defects Using Convolutional Neural Networks

TL;DR

This paper explores using convolutional neural networks to automate the detection and localization of building defects from images, aiming to improve efficiency and safety over traditional manual inspections.

Contribution

It evaluates the effectiveness of pre-trained CNN models, including VGG-16, ResNet-50, and Inception, with class activation mapping for defect detection and localization.

Findings

The CNN models accurately detect building defects.

VGG-16 outperforms other models in localization accuracy.

The approach can be scaled for real-time mobile and drone applications.

Abstract

Clients are increasingly looking for fast and effective means to quickly and frequently survey and communicate the condition of their buildings so that essential repairs and maintenance work can be done in a proactive and timely manner before it becomes too dangerous and expensive. Traditional methods for this type of work commonly comprise of engaging building surveyors to undertake a condition assessment which involves a lengthy site inspection to produce a systematic recording of the physical condition of the building elements, including cost estimates of immediate and projected long-term costs of renewal, repair and maintenance of the building. Current asset condition assessment procedures are extensively time consuming, laborious, and expensive and pose health and safety threats to surveyors, particularly at height and roof levels which are difficult to access. This paper aims at evaluating the application of convolutional neural networks (CNN) towards an automated detection and localisation of key building defects, e.g., mould, deterioration, and stain, from images. The proposed model is based on pre-trained CNN classifier of VGG-16 (later compaired with ResNet-50, and Inception models), with class activation mapping (CAM) for object localisation. The challenges and limitations of the model in real-life applications have been identified. The proposed model has proven to be robust and able to accurately detect and localise building defects. The approach is being developed with the potential to scale-up and further advance to support automated detection of defects and deterioration of buildings in real-time using mobile devices and drones.