Full
Outline
Aiming at the problem that the existing machine vision methods cannot effectively detect foreign objects due to the special shape and unobvious characteristics of foreign objects on coal mine conveyor belts, an improved YOLOv11 model was proposed. Firstly, the C3k2-LDC feature extraction module was constructed using linear deformable convolution, so that the model has the ability to extract features of irregular shaped foreign objects. Then, the edge enhancement module was introduced, and the multi-scale feature fusion strategy was adopted to effectively strengthen the edge information of the weak feature foreign object. Finally, a loss function optimization scheme based on WIoU was proposed to reduce the impact of low-quality data samples on training. The effectiveness and robustness of the improved YOLOv11 model were verified by ablation test, comparative test, thermal map and visual analysis. The results show that the mAP50 of the improved YOLOv11 model is 90.2%, which is 4.0, 9.1, 7.4 and 5.7 percentage points higher than that of RT-DETR, EfficientDet-D2, YOLOv8n and YOLOv11s models, respectively. In terms of lightweight, the floating-point calculation amount and parameter amount of the improved YOLOv11 model are 6.8×109 and 2.6×106 respectively, and the detection speed is 127 frames/s, which can realize the real-time foreign object detection task on the basis of ensuring the detection accuracy. Compared with the original model, the improved model pays more attention to the characteristics of complex foreign objects and has good robustness. The research results can provide technical support for mine safety management.
75
39
| 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
