To read this content please select one of the options below:

Machine learning using synthetic images for detecting dust emissions on construction sites

Ruoxin Xiong (Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA)
Pingbo Tang (Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA)

Smart and Sustainable Built Environment

ISSN: 2046-6099

Article publication date: 13 July 2021

Issue publication date: 10 November 2021

502

Abstract

Purpose

Automated dust monitoring in workplaces helps provide timely alerts to over-exposed workers and effective mitigation measures for proactive dust control. However, the cluttered nature of construction sites poses a practical challenge to obtain enough high-quality images in the real world. The study aims to establish a framework that overcomes the challenges of lacking sufficient imagery data (“data-hungry problem”) for training computer vision algorithms to monitor construction dust.

Design/methodology/approach

This study develops a synthetic image generation method that incorporates virtual environments of construction dust for producing training samples. Three state-of-the-art object detection algorithms, including Faster-RCNN, you only look once (YOLO) and single shot detection (SSD), are trained using solely synthetic images. Finally, this research provides a comparative analysis of object detection algorithms for real-world dust monitoring regarding the accuracy and computational efficiency.

Findings

This study creates a construction dust emission (CDE) dataset consisting of 3,860 synthetic dust images as the training dataset and 1,015 real-world images as the testing dataset. The YOLO-v3 model achieves the best performance with a 0.93 F1 score and 31.44 fps among all three object detection models. The experimental results indicate that training dust detection algorithms with only synthetic images can achieve acceptable performance on real-world images.

Originality/value

This study provides insights into two questions: (1) how synthetic images could help train dust detection models to overcome data-hungry problems and (2) how well state-of-the-art deep learning algorithms can detect nonrigid construction dust.

Keywords

Acknowledgements

This paper is a substantially extended and enhanced version of the paper presented at the 20th International Conference on Construction Applications of Virtual Reality (CONVR 2020). The authors would like to acknowledge the editorial contributions of Professor Nashwan Dawood and Dr. Farzad Rahimian of Teesside University in the publication of this paper. The authors also gratefully acknowledge Mr. Bo Zhang for assisting in data preparation and collection. The research was supported by funds from NASA University Leadership Initiative program (Contract No. NNX17AJ86A, Project Officer: Dr. Anupa Bajwa, Program coordinator: Koushik Datta, Principal Investigator: Dr. Yongming Liu, Co-PI: Dr. Pingbo Tang), the US National Science Foundation (NSF) under Grant No. 1454654, the US National Science Foundation (NSF) Convergence under Grant No. 1937115 and College of Engineering Dean’s Fellowship of the Carnegie Mellon University (CMU). Any opinions, findings, conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of NASA, NSF and CMU.

Citation

Xiong, R. and Tang, P. (2021), "Machine learning using synthetic images for detecting dust emissions on construction sites", Smart and Sustainable Built Environment, Vol. 10 No. 3, pp. 487-503. https://doi.org/10.1108/SASBE-04-2021-0066

Publisher

:

Emerald Publishing Limited

Copyright © 2021, Emerald Publishing Limited

Related articles