Frontiers in neurorobotics · 2026
NL-YOLOv5: a model with a larger receptive field and the ability to globally acquire features.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Li Zhiyu, Liu Jinhu, Zhuo Zhihao, Chen Lin, Zeng Xiao, Li Di, Zhou Yongfa, Huang Chunzhou
Аннотация
INTRODUCTION: 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.
METHODS: 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.
RESULTS: 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.
DISCUSSION: This work delivers a practical solution for high-precision landslide detection in remote sensing applications.
METHODS: 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.
RESULTS: 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.
DISCUSSION: This work delivers a practical solution for high-precision landslide detection in remote sensing applications.