Image-based dust quantification: a novel approach using texture and color features
Environmental Pollution · 2025-06 · 375 · 126309
DOI: 10.1016/j.envpol.2025.126309 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Pollution, 2025-06. Verfasst von Jiangjiang Yin und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Resources and Safety Engineering, Central South University, Changsha, Hunan, 410083, China. Hauptthemen laut MEDLINE: Dust, Environmental Monitoring, Air Pollutants. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Hunan Provincial Innovation Foundation for Postgraduate, Fundamental Research Funds for Central Universities of the Central South University, Science and Technology Program of Hunan Province.
Abstract (Originalsprache)
Airborne dust pollution, particularly in the mining environment, poses significant environmental and health risks due to its fine particulate matter. Traditional monitoring methods, while widely used, face limitations in real-time detection and spatial accuracy. In this study, an image-based methodology is presented for quantifying dust concentration, integrating texture and color features to enhance detection precision. Using a self-designed experimental setup replicating underground mining conditions, the high-resolution images of dust dispersion are acquired under controlled conditions and extract feature parameters, including Entropy in texture and Standard Deviation in color features, across multiple color models. The approach demonstrates a strong correlation between image features and dust concentration, achieving an R2 of 0.90 with expanded measurement ranges. A comparative analysis against existing laser-based and vision-based techniques highlights the method accuracy and computational efficiency, suggesting its potential for real-time, high-precision dust monitoring. This work establishes a foundation for advanced image-based dust quantification, with applications extending to diverse industrial monitoring scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Resources and Safety Engineering, Central South University, Changsha, Hunan, 410083, China.
- School of Resources and Safety Engineering, Central South University, Changsha, Hunan, 410083, China. Electronic address: sf.wang@csu.edu.cn.
Förderung
- Hunan Provincial Innovation Foundation for Postgraduate
- Fundamental Research Funds for Central Universities of the Central South University
- Science and Technology Program of Hunan Province
- National Natural Science Foundation of China
Zitieren
APA
Yin, J., Wang, S., Shi, L., Lei, J., & Zhou, Z. (2025). Image-based dust quantification: a novel approach using texture and color features. Environmental Pollution, 375, 126309. https://doi.org/10.1016/j.envpol.2025.126309
Vancouver
Yin J, Wang S, Shi L, Lei J, Zhou Z. Image-based dust quantification: a novel approach using texture and color features. Environmental Pollution. 2025;375:126309. doi:10.1016/j.envpol.2025.126309
BibTeX
@article{Yin2025,
author = {Yin, Jiangjiang and Wang, Shaofeng and Shi, Liwei and Lei, Jiangyang and Zhou, Zilong},
title = {Image-based dust quantification: a novel approach using texture and color features},
journal = {Environmental Pollution},
year = {2025},
volume = {375},
pages = {126309},
doi = {10.1016/j.envpol.2025.126309}
}
EUVIMED