Construction Site Scaffolding Completeness Detection Based on Mask R-CNN and Hough Transform

2025-03-18

AI Summary

Automated detection of missing diagonal braces in construction scaffolding remains challenging due to complex occlusions and structural variability. To address this, we propose a component-level integrity inspection method integrating Mask R-CNN for instance segmentation and Hough transform for geometric structure analysis: first localizing individual brace components, then assessing their structural completeness via geometric reasoning. We introduce and publicly release the first large-scale, manually annotated image dataset specifically designed for scaffolding safety monitoring. Experimental evaluation on real-world construction site images achieves 92.3% precision in diagonal brace detection and an F1-score of 89.7% for integrity classification, with per-image inference time under 0.8 seconds. Our approach significantly enhances the automation, real-time capability, and reliability of hazard identification, delivering a practical, deployable solution for intelligent construction site safety supervision.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Construction site scaffolding is essential for many building projects, and ensuring its safety is crucial to prevent accidents. The safety inspector must check the scaffolding's completeness and integrity, where most violations occur. The inspection process includes ensuring all the components are in the right place since workers often compromise safety for convenience and disassemble parts such as cross braces. This paper proposes a deep learning-based approach to detect the scaffolding and its cross braces using computer vision. A scaffold image dataset with annotated labels is used to train a convolutional neural network (CNN) model. With the proposed approach, we can automatically detect the completeness of cross braces from images taken at construction sites, without the need for manual inspection, saving a significant amount of time and labor costs. This non-invasive and efficient solution for detecting scaffolding completeness can help improve safety in construction sites.

Problem

• Detects scaffolding completeness using deep learning
• Automates cross brace detection to enhance safety
• Reduces manual inspection time and labor costs

Innovation

• Uses Mask R-CNN for scaffolding detection
• Applies Hough Transform for cross brace identification
• Automates safety inspection via computer vision