For rapid and automatic recognition of blast fragmentation in the Husab Mine in Namibia of Africa, a dynamic recognition model was proposed for blast fragmentation in open-pit mines. By acquiring stereo images through a binocular camera and constructing a depth map, in combination with an improved YOLOv8 instance segmentation model, the classification of gravel and fragmentation analysis were realized. Moreover, transfer learning, ROI extraction, and shadow data augmentation technologies were all adopted to optimize the model, enhancing its recognition accuracy in complex environments. The model training results show that the optimized model can achieve a precision of 0.375, a recall of 0.600, and an accuracy of 0.300. This model exhibits strong robustness in extremely complex scenes of open-pit mines, and is capable of successfully detecting most effective rock blocks from high-noise and high-interference backgrounds. Field measurement data indicate that the model can operate stably in environments with high dust and dynamic lighting, achieving a recognition accuracy of 85% for effective rocks on site, and the error of the fragmentation distribution curve is controlled within 8%. This model provides reliable technical support for the efficient evaluation and intelligent detection of blasting effects in the Husab Mine.
| 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 |