Full
Outline
Underground mine drill bit detection is a critical link to ensure the safety of underground mine operations, but existing deep learning-based detection models have shortcomings in feature extraction capability and detection efficiency. To improve detection performance, a drill bit detection model named YOLOv8-WGB based on the improved YOLOv8n was proposed. Firstly, the traditional CIoU loss function was replaced with the WIoU loss function, which enhanced the focus on key features. Secondly, the global attention mechanism (GAM) was introduced, which enhanced the global information interaction capability of the YOLOv8 backbone network, reduced information loss, and amplified global dimensional features. Finally, the BiFPN structure was added, which assigned different weights to feature maps of different scales when fusing them, so as to achieve optimal feature fusion. The test results show that YOLOv8-WGB improves precision, recall, and mAP@0.5 by 7.1%, 11.1%, and 8.3% respectively compared with YOLOv8n, and its inference speed is 173 frames/s faster than that of YOLOv8s, exhibiting higher detection speed. On the basis of maintaining the model complexity and inference speed advantages of YOLOv8n, the proposed model has significantly superior detection accuracy to YOLOv8s. It effectively balances detection accuracy and speed, and exhibits excellent performance in the underground mine drill bit detection task.
78
34
| 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
