Full
Outline
To address the frequent accidents caused by uneven illumination, complex backgrounds, and human rule-breaking operations in underground coal mines, a personnel behavior recognition method based on the fusion and optimization of improved Retinex and YOLOv5 was proposed. Firstly, an improved multi-scale Retinex algorithm was employed to enhance underground images. Through multi-scale fusion and color restoration techniques, the interference of low illumination, coal dust, and water mist on the images was eliminated, thereby improving image clarity and color fidelity. Subsequently, the enhanced image data were input into YOLOv5 network to construct a target detection model based on the fusion and optimization of Retinex and YOLOv5, which was adapted to detection scenarios with dense equipment and complex backgrounds in underground mines. The experimental results show that the average accuracy of this method for recognizing helmet-wearing behavior and on-site operational violation postures of underground personnel reaches over 95% and 85%, respectively. This method can achieve the precise identification and judgment of rule-breaking behavior by underground personnel, providing technical support for intelligent safety supervision in coal mines.
49
15
| 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
