Automation in Construction Quality Control: Integrating Unmanned Aerial Vehicle (UAV), CNNs, and Photogrammetry for Structural Element Detection and Measurement Precision

DOI

10.2991/978-94-6463-884-4_22How to use a DOI?

Keywords

Convolutional Neural Networks (CNNs); Unmanned Aerial Vehicle (UAV); Construction Quality Control; Photogrammetry; Structural Element Detection; Automation in Construction

Abstract

Traditional construction auditing and quality control systems rely on manual processes, including paper-based documentation and physical inspections. The conventional approach generates delays and inaccuracies during construction. For instance, manual inspections frequently fail to detect critical defects, and nonconformance reports typically require several days for processing, resulting in delayed corrective actions. Studies have shown that up to 30% of the project time is lost because of poor documentation and error-prone processes, which results in higher rework rates and non-compliance with design specifications. This study presents a novel approach to overseeing construction activities. An Unmanned Aerial Vehicle (UAV) is equipped to capture imagery data at specific stages of construction, ensuring optimal camera angles, altitudes, and image overlaps for extensive data collection. Deep learning models, particularly convolutional neural networks (CNNs), are implemented using PyTorch to automatically detect structural components, such as beams, columns, and slabs. Following the identification, a database was utilized to store and track the quantity of these identified elements at specific stages of construction. Photogrammetry was subsequently applied to precisely measure the identified structural elements. The system identifies construction elements and validates their structural dimensions. Automating this process significantly reduces reliance on manual inspections, thereby enabling the detection of deviations from the design specifications. The integration of PyTorch facilitates recursive learning, allowing the model to improve over time as it processes more data, thereby increasing its accuracy in subsequent audits. This enables stakeholders to view real-time data and to ensure transparency. Notably, this framework aligns with the fundamental project management principle of ensuring timely delivery, budget control, and adherence to the project requirements.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Alinda Bhattacharjee
AU  - Estiak Ahmed
AU  - Md Jewel Rana
PY  - 2025
DA  - 2025/11/18
TI  - Automation in Construction Quality Control: Integrating Unmanned Aerial Vehicle (UAV), CNNs, and Photogrammetry for Structural Element Detection and Measurement Precision
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 181
EP  - 189
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_22
DO  - 10.2991/978-94-6463-884-4_22
ID  - Bhattacharjee2025
ER  -