Remote detection method for surface diseases of water conveyance tunnels based on biomimetic visual attention mechanism

Abstract This paper presents a remote disease detection method for water conveyance tunnels based on a biomimetic visual attention mechanism. To address the challenges posed by uneven disease distribution and complex background textures, the proposed method integrates local distinctiveness features and global rarity features. First, an enhanced distance-weighted fast point feature histogram (DWFPFH) descriptor is developed to improve the representation of subtle local geometric variations. Based on the enhanced descriptor, local distinctiveness is quantified using a Chi-square statistical measure. Second, global structural rarity is extracted by analyzing the spatial distribution of distinctive points. Finally, local distinctiveness and global rarity are integrated through an optimization-based fusion strategy to generate the final saliency map for disease detection. Quantitative experiments on simulated tunnel point-cloud models demonstrate that the proposed framework achieves improved detection performance compared with existing point-cloud saliency methods. Experiments on real small-scale tunnel acoustic point clouds further verify its practical applicability for detecting various types of surface diseases under different underwater inspection conditions. This study provides a promising tool for enhancing the reliability and efficiency of disease detection in water conveyance tunnels.

Authors

Institutions

Publication Details

Journal
Engineering Research Express
Published
2026-11-17
DOI
https://doi.org/10.1088/2631-8695/aec371
Primary Topic
Infrastructure Maintenance and Monitoring
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Remote detection method for surface diseases of water conveyance tunnels based on biomimetic visual attention mechanism

许海燕 Xu Haiyan, Jisong Wang, Xuewu Zhang, Xiaoshun Chen
2 links
Engineering Research Express
Infrastructure Maintenance and Monitoring
article

Remote detection method for surface diseases of water conveyance tunnels based on biomimetic visual attention mechanism

许海燕 Xu Haiyan, Jisong Wang, Xuewu Zhang, Xiaoshun Chen
article en

Abstract

Abstract This paper presents a remote disease detection method for water conveyance tunnels based on a biomimetic visual attention mechanism. To address the challenges posed by uneven disease distribution and complex background textures, the proposed method integrates local distinctiveness features and global rarity features. First, an enhanced distance-weighted fast point feature histogram (DWFPFH) descriptor is developed to improve the representation of subtle local geometric variations. Based on the enhanced descriptor, local distinctiveness is quantified using a Chi-square statistical measure. Second, global structural rarity is extracted by analyzing the spatial distribution of distinctive points. Finally, local distinctiveness and global rarity are integrated through an optimization-based fusion strategy to generate the final saliency map for disease detection. Quantitative experiments on simulated tunnel point-cloud models demonstrate that the proposed framework achieves improved detection performance compared with existing point-cloud saliency methods. Experiments on real small-scale tunnel acoustic point clouds further verify its practical applicability for detecting various types of surface diseases under different underwater inspection conditions. This study provides a promising tool for enhancing the reliability and efficiency of disease detection in water conveyance tunnels.

Engineering Research Express
Hohai University (CN), Huaiyin Normal University (CN)
Government of Jiangsu Province
Industry, innovation and infrastructure
Infrastructure Maintenance and Monitoring
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon