Integrating text parsing and object detection for automated monitoring of finishing works in construction projects

다국어 초록 (Multilingual Abstract)

Construction process monitoring traditionally relies on manual inspections and document cross-referencing, leading to inefficiencies in project management. Despite advances enabling computer vision-based monitoring and automated document analysis, integrating these technologies remains challenging, particularly in connecting field data with work documentation. This paper proposes an automated monitoring system integrating computer vision-based field data with text-based work instructions. The system employs YOLOv5 object detection models to analyze construction site images and architectural drawings, while utilizing text parsing techniques to extract information from work instructions. Validation using thirty apartment units demonstrated effectiveness in monitoring finishing works, particularly masonry and tiling applications. Results showed consistent performance in establishing automated connections between work instructions, drawings, and site conditions, reducing manual verification requirements while maintaining high accuracy. The successful implementation in finishing works demonstrates potential scalability for broader construction applications with varying complexity levels.

목차 (Table of Contents)

• Ⅰ. Introduction 1
• 1.1 Introduction 1
• 1.2 Research background and literature review 5
• 1.2.1 Object Detection Applications in Construction Monitoring 5
• 1.2.2 Text analysis methods for construction documentation 8
• Ⅱ. Methodology 10
• 2.1 System overview 10
• 2.2 Preparation phase 13
• 2.2.1 Dataset generation 13
• 2.2.2 Wall detection and labeling in architectural drawings 14
• 2.2.3 Aligning work instructions with drawings 15
• 2.3 Operation phase 17
• 2.3.1 Construction site data collection using UGV 17
• 2.3.2 Object detection in construction site images 19
• 2.3.3 Extracting work instruction information through text parsing 20
• 2.3.4 Integration framework 21
• Ⅲ. Results 24
• 3.1 Results 24
• 3.1.1 Object detection performance 25
• 3.1.2 The result of text parsing in a work instruction 31
• 3.1.3 Integrated monitoring system results 32
• Ⅳ. Discussion 35
• 4.1 Technical contributions and system effectiveness 35
• 4.2 Theoretical implications and knowledge contributions 38
• 4.3 Limitations and future research 39
• Ⅴ. Conclusions 40
• 5.1 Conclusion 40
• References 42
• 국문 초록 53