Lightweight Visual Localization of Steel Surface Defects for Autonomous Inspection Robots Based on Improved YOLOv10n
Sensors · 30.03.2026 · 26 (7) · 2132
DOI: 10.3390/s26072132 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 30.03.2026. Verfasst von Jinwu Tong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Machine Vision and Deformation Monitoring Laboratory, Artificial Intelligence and Precision Medicine Research Laboratory, Engineering Training Center…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Basic and Applied Basic Research Foundation, Shenzhen Science and Technology Program, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
To address the challenges of steel surface defect detection—characterized by fine-grained textures, substantial scale variations, and complex background interference—conventional lightweight detectors often struggle to balance real-time navigation requirements with high-precision spatial localization on mobile inspection platforms. In this work, we propose KDM-YOLO, a lightweight visual localization and detection method built upon YOLOv10n, designed to provide an efficient perception engine for autonomous inspection robots. The proposed approach enhances the baseline through three key perspectives: feature extraction, context modeling, and multi-scale fusion. Specifically, KWConv is introduced to strengthen the representation of fine-grained texture and edge cues; C2f-DRB is employed to enlarge the effective receptive field and improve long-range dependency perception to reduce missed detections; and a multi-scale attention fusion (MSAF) module is inserted before the detection head to adaptively integrate spatial details with semantic context while suppressing redundant background responses. Ablation studies confirm that each module contributes to performance gains, and their combination yields the best overall results. Comparative experiments further demonstrate that KDM-YOLO significantly improves detection performance while retaining a compact model size and high inference speed. Compared with the YOLOv10n baseline, Precision, Recall and mAP@50 are increased to 91.0%, 93.9%, and 95.4%, respectively, with a parameter count of 3.29 M and an inference speed of 155.6 f/s. These results indicate that KDM-YOLO achieves an ideal balance between the accuracy and computational efficiency required for embedded navigation platforms, providing an effective solution for online autonomous inspection and real-time localization of steel surface defects.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Machine Vision and Deformation Monitoring Laboratory, Artificial Intelligence and Precision Medicine Research Laboratory, Engineering Training Center, School of Applied Technology, Nanjing Institute of Technology, Nanji…
- School of Automation, Northwestern Polytechnical University, Xi'an 710072, China.
- Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen 518057, China.
ORCID-Profile: Jinwu Tong, Bingbing Gao
Förderung
- Guangdong Basic and Applied Basic Research Foundation
- Shenzhen Science and Technology Program
- China Postdoctoral Science Foundation
- Shaanxi Postdoctoral Research Project
- Key Laboratory of Micro-Inertial Instrument and Advanced Navigation Technology
- Nanjing Institute of Technology Talent Introduction Scientific Research Start Fund Project
- Industry-University-Research Collaboration Project in Jiangsu Province
- Nanjing Health Science and Technology Development Major Project
Zitieren
APA
Tong, J., Zhang, X., Lu, X., Cao, H., Yao, L., & Gao, B. (2026). Lightweight Visual Localization of Steel Surface Defects for Autonomous Inspection Robots Based on Improved YOLOv10n. Sensors, 26(7), 2132. https://doi.org/10.3390/s26072132
Vancouver
Tong J, Zhang X, Lu X, Cao H, Yao L, Gao B. Lightweight Visual Localization of Steel Surface Defects for Autonomous Inspection Robots Based on Improved YOLOv10n. Sensors. 2026;26(7):2132. doi:10.3390/s26072132
BibTeX
@article{Tong2026,
author = {Tong, Jinwu and Zhang, Xin and Lu, Xinyun and Cao, Han and Yao, Lengtao and Gao, Bingbing},
title = {Lightweight Visual Localization of Steel Surface Defects for Autonomous Inspection Robots Based on Improved YOLOv10n},
journal = {Sensors},
year = {2026},
volume = {26},
number = {7},
pages = {2132},
doi = {10.3390/s26072132}
}
EUVIMED