ORIGINAL RESEARCH article
Front. Remote Sens.
Sec. Image Analysis and Classification
NL-YOLOv5: A model with a larger receptive field and the ability to globally acquire features
Provisionally accepted
- Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau, Zhuhai, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Landslide disasters cause severe casualties and economic losses, demanding rapid and accurate detection from high-resolution remote sensing imagery. Traditional methods struggle with insufficient landslide samples and low detection accuracy. To address this, we propose a dual solution: (1) DCGAN-based data augmentation generating 3,429 synthetic landslide samples from Google Earth imagery, significantly improving model generalization; (2) an NL-YOLOv5 model integrating non-local attention (NLA) and an improved LK-SPP module (based on large-kernel convolution concepts) to enhance global information capture. The NL-YOLOv5 model achieves 80% detection accuracy (a 5% improvement over baseline), with 7% higher precision, 2% higher recall, and 5% higher F1-score, while maintaining real-time speed at 69 f/s. This work delivers a practical solution for high-precision landslide detection in remote sensing applications.
Keywords: DCGAN, deep learning, landslide, NL-YOLOv5, object detection
Received: 11 Dec 2025; Accepted: 30 Jan 2026.
Copyright: © 2026 Li, Liu, Zhuo, Chen, Zeng, Li, Zhou and Huang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Zhiyu Li
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.