Work

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

Year: 2026
Type: article
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.
Language: English
Open Access status: bronze
OpenAlex ID: W7235767543
FWCI:
Cites: 26
Cited by:
Related to: 10