Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction

2025-03-05

AI Summary

To address the reliance on manual inspection and poor compatibility with digital management in drywall progress tracking and quality control during construction, this paper proposes an end-to-end automated drywall image analysis framework. The method integrates an enhanced Mask R-CNN for instance segmentation, camera geometric modeling, robust perspective distortion estimation and correction, and a clustering-driven wall-segment parsing algorithm—enabling precise component identification, sub-millimeter spatial localization, and quantitative assessment of wall surface integrity. Key contributions include: (1) domain-specific data augmentation and architectural refinements that significantly improve segmentation accuracy; and (2) the first fully automated pipeline mapping raw images to spatial relationships and quantified construction metrics—achieving <3% progress deviation and 92.4% defect recall. Comprehensive evaluation on real-world construction sites demonstrates superior performance over state-of-the-art approaches.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Digitalization in the construction industry has become essential, enabling centralized, easy access to all relevant information of a building. Automated systems can facilitate the timely and resource-efficient documentation of changes, which is crucial for key processes such as progress tracking and quality control. This paper presents a method for image-based automated drywall analysis enabling construction progress and quality assessment through on-site camera systems. Our proposed solution integrates a deep learning-based instance segmentation model to detect and classify various drywall elements with an analysis module to cluster individual wall segments, estimate camera perspective distortions, and apply the corresponding corrections. This system extracts valuable information from images, enabling more accurate progress tracking and quality assessment on construction sites. Our main contributions include a fully automated pipeline for drywall analysis, improving instance segmentation accuracy through architecture modifications and targeted data augmentation, and a novel algorithm to extract important information from the segmentation results. Our modified model, enhanced with data augmentation, achieves significantly higher accuracy compared to other architectures, offering more detailed and precise information than existing approaches. Combined with the proposed drywall analysis steps, it enables the reliable automation of construction progress and quality assessment.

Problem

• Automated drywall analysis for construction progress tracking.
• Deep learning-based instance segmentation for quality control.
• Image-based system to correct camera perspective distortions.

Innovation

• Deep learning-based instance segmentation model
• Camera perspective distortion correction algorithm
• Enhanced accuracy through data augmentation