PDF
Full
Outline
Accurately acquiring the spatial distribution of open−pit mines is vital for "green mine" development and dynamic geological monitoring. To overcome the inherent challenges of dataset scarcity, drastic intra− and inter−class differences, and complex topological structures in this field, we propose a segmentation framework integrating hybrid semantic prompting and topological awareness. We constructed a specific dataset named Mine Semantic Segmentation (MSS). MSS contains 7,622 finely annotated images of open−pit mines. Based on MSS, we propose an instance segmentation method called Mine Segment Anything Model (Mine−SAM). Mine−SAM employs a dual−encoder structure. It also utilizes multi−scale feature aggregation techniques. The model couples global context from foundation models with local fine−grained features from expert models. Mine−SAM achieved an Average Precision box (PA,box) of 64.4%. The Average Precision mask (PA,mask) score reached 65.2%. In addition, we developed a semantic segmentation method named SemMSeg. This method combines graph convolutional networks (GCN) with pixel−level contrastive learning. The GCN captures spatial dependencies among mining elements. It also enforces structural constraints within the model. SemMSeg achieved an Intersection over Union (IoU) of 73.38%. The precision of the method reached 85.03%. These techniques provide a technical path for automatic mine monitoring. The findings contribute to the intelligent interpretation of remote sensing imagery.
PDF
150
75
| 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
010-62199257
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
