Full
Outline
To address the degradation of object detection caused by reduced contrast and blurred textures in foggy images, this paper proposes Fog-RT-DETR based on the Real-Time Detection Transformer (RT-DETR). The method integrates an Asymptotic Feature Pyramid Network (AFPN) for multi-scale feature fusion, a Variance-Enhanced Convolutional Block Attention Module (VE-CBAM) for local low-texture perception, and a Feature Degradation Enhancement Module (FDEM) for spatially weighted feature enhancement. Experiments on a foggy-weather dataset constructed from DAWN and ACDC show that Fog-RT-DETR achieves 81.45% mAP@0.5 and 58.78% mAP@0.5∶0.95, improving over the baseline by 2.12 and 3.89 percentage points, respectively. Recall increases by 0.49 percentage points. Ablation experiments show that combining all three modules yields the best detection results in the reported experiments. Channel compression experiments further demonstrate a trade-off between detection accuracy and computational cost.
89
17
| 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
