MS-PANet: Multi-Scale Spatial Pyramid Attention for Effective Drainage Pipeline Image Dehazing
Journal of Imaging · 27.04.2026 · 12 (5) · 189
DOI: 10.3390/jimaging12050189 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 27.04.2026. Verfasst von Ce Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, China University of Mining and Technology-Beijing, Beijing 100083, China. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Beijing Nova Program of Science and Technology.
Abstract (Originalsprache)
Urban drainage pipelines are crucial for flood control, drainage, and environmental quality. However, fog within pipelines degrades image quality, hindering the identification of damage features such as cracks and leaks. Existing dehazing algorithms struggle with the unique challenges presented by drainage pipelines, such as their cylindrical structure, non-uniform lighting, and multi-scale particulate interference, leading to inadequate feature extraction and weak cross-channel dependency modeling. To address these issues, we propose a novel drainage pipeline image dehazing network based on a pyramid attention mechanism. Specifically, our proposed method incorporates a custom-designed multi-scale spatial pyramid attention (MSPA) module, which combines hierarchical pyramid convolution and spatial pyramid recalibration modules. This enables the dynamic adjustment of multi-scale feature weights and the effective modeling of cross-channel long-range dependencies. Extensive experiments demonstrate that our network achieves superior dehazing performance across diverse underground environments, particularly in synthetic foggy dataset under real pipeline conditions, outperforming state-of-the-art dehazing algorithms. This proposed approach provides a reliable solution for high-precision visual inspection in complex pipeline scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence, China University of Mining and Technology-Beijing, Beijing 100083, China.
- Key Laboratory of Safety Detection and Evaluation of Urban Roads and Underground Space, Ministry of Emergency Management, Beijing 100083, China.
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China.
- School of Geosciences and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China.
ORCID-Profile: Ce Li
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Beijing Nova Program of Science and Technology
- CUMTB Postgraduate Education and Teaching Reform Project
- the National Key Technology R&D Program
- National Key Technology R&D Program
Zitieren
APA
Li, C., Duan, X., Jiang, Z., Ding, Y., Li, Q., Tang, Z., & Yang, F. (2026). MS-PANet: Multi-Scale Spatial Pyramid Attention for Effective Drainage Pipeline Image Dehazing. Journal of Imaging, 12(5), 189. https://doi.org/10.3390/jimaging12050189
Vancouver
Li C, Duan X, Jiang Z, Ding Y, Li Q, Tang Z, et al. MS-PANet: Multi-Scale Spatial Pyramid Attention for Effective Drainage Pipeline Image Dehazing. Journal of Imaging. 2026;12(5):189. doi:10.3390/jimaging12050189
BibTeX
@article{Li2026,
author = {Li, Ce and Duan, Xinyi and Jiang, Zhongbo and Ding, Yijing and Li, Quanzhi and Tang, Zhengyan and Yang, Feng},
title = {MS-PANet: Multi-Scale Spatial Pyramid Attention for Effective Drainage Pipeline Image Dehazing},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {5},
pages = {189},
doi = {10.3390/jimaging12050189}
}
EUVIMED