Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection

Peng, Zhangjun; Li, Li; Chang, Chuanhao; Wan, Mingfei; Zheng, Guoqiang; Yue, Zhiming; Zhou, Shuai; Liu, Zhigui

doi:10.3390/s26030923

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection

by

Zhangjun Peng

^1,2

,

Li Li

²,

Chuanhao Chang

²,

Mingfei Wan

¹,

Guoqiang Zheng

²,

Zhiming Yue

²,

Shuai Zhou

¹ and

Zhigui Liu

^1,*

¹

School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, China

²

School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, China

^*

Author to whom correspondence should be addressed.

Sensors 2026, 26(3), 923; https://doi.org/10.3390/s26030923 (registering DOI)

Submission received: 21 December 2025 / Revised: 29 January 2026 / Accepted: 30 January 2026 / Published: 31 January 2026

(This article belongs to the Section Fault Diagnosis & Sensors)

Download Versions Notes

Abstract

Surface defects in hydraulic concrete structures exhibit extreme topological heterogeneity. and are frequently obscured by unstructured environmental noise. Conventional detection models, constrained by fixed-grid convolutions, often fail to effectively capture these irregular geometries or suppress background artifacts. To address these challenges, this study proposes the Adaptive Local–Global Synergistic Perception Network (ALGSP-Net). First, to overcome geometric constraints, the Defect-aware Receptive Field Aggregation and Adaptive Dynamic Receptive Field modules are introduced. Instead of rigid sampling, this design adaptively modulates the receptive field to align with defect morphologies, ensuring the precise encapsulation of slender cracks and interlaced spalling. Second, a dual-stream gating fusion strategy is employed to mitigate semantic ambiguity. This mechanism leverages global context to calibrate local feature responses, effectively filtering background interference while enhancing cross-scale alignment. Experimental results on the self-constructed SDD-HCS dataset demonstrate that the method achieves an average Precision of 77.46% and an mAP50 of 72.78% across six defect categories. Comparative analysis confirms that ALGSP-Net outperforms state-of-the-art benchmarks in both accuracy and robustness, providing a reliable solution for the intelligent maintenance of hydraulic infrastructure.

Keywords: hydraulic concrete; defect detection; structural health monitoring; multi-scale perception; gated feature fusion

Share and Cite

MDPI and ACS Style

Peng, Z.; Li, L.; Chang, C.; Wan, M.; Zheng, G.; Yue, Z.; Zhou, S.; Liu, Z. Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection. Sensors 2026, 26, 923. https://doi.org/10.3390/s26030923

AMA Style

Peng Z, Li L, Chang C, Wan M, Zheng G, Yue Z, Zhou S, Liu Z. Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection. Sensors. 2026; 26(3):923. https://doi.org/10.3390/s26030923

Chicago/Turabian Style

Peng, Zhangjun, Li Li, Chuanhao Chang, Mingfei Wan, Guoqiang Zheng, Zhiming Yue, Shuai Zhou, and Zhigui Liu. 2026. "Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection" Sensors 26, no. 3: 923. https://doi.org/10.3390/s26030923

APA Style

Peng, Z., Li, L., Chang, C., Wan, M., Zheng, G., Yue, Z., Zhou, S., & Liu, Z. (2026). Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection. Sensors, 26(3), 923. https://doi.org/10.3390/s26030923

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Adaptive Local–Global Synergistic Perception Network for Hydraulic Concrete Surface Defect Detection

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI