Full
Outline
Windmills are important facilities that convert wind energy into electrical energy. This paper addresses the issues of missed detections and false detections in the process of identifying small-scale windmills in remote sensing images by constructing a new GF-2 windmill dataset. It proposes the YOLO-WM algorithm for the small target detection task of windmills, adding a tiny object detection layer based on the YOLOv8 object detection algorithm, and incorporates a BSAM dynamic attention mechanism module in the backbone section. It replaces the C2f module with the lightweight C2f_RepGhost module and finally utilizes the SAHI slicing algorithm in the prediction stage to complete the windmill target detection task. Experimental results show that the YOLO-WM algorithm can better retain shallow convolutional features while reducing algorithm complexity, allowing for more accurate capture of small-scale target information. This method compensates for the shortcomings of small object detection datasets, and it has been verified that the improved algorithm performs better in detecting small-scale windmills than other algorithms. This research provides valuable insights for the rational optimization and allocation of wind energy resources and the joint analysis of geographical elements.
114
32
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
