PDF
Full
Outline
Stereo vision wave measurement technology has become one of the most promising methods for monitoring wave fields at present. However, traditional feature extraction and matching methods rely on feature point extraction, therefore cannot meet the requirements of rate and accuracy in practical applications, thereby affecting the effect of 3D reconstruction. This paper introduces the LoFTR (Local Feature Transformer) algorithm. Taking the wave images captured by the binocular vision wave measurement system installed on a certain fixed offshore wind turbine as the image set, an efficient wave feature extraction and matching technology based on artificial intelligence algorithms and 3D wave field dense reconstruction technology is constructed. The algorithm has been verified under various lighting environments. The results show that the LoFTR algorithm can extract an average of 4300 pairs of matching points per frame for wave images under normal lighting, while taking 0.9 s per frame. The matching effect is significantly better than that of traditional methods. Moreover, for images with unclear textures in the night environment, the algorithm can still stably match more than 2000 pairs of matching points, achieving dense reconstruction of the 3D wave field and providing core technical support for the intelligent monitoring of ocean waves.
PDF
171
74
| 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
