中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
AiOENet: All-in-One Low-Visibility Enhancement to Improve Visual Perception for Intelligent Marine Vehicles Under Severe Weather Conditions

文献类型：期刊论文

作者Liu, Ryan Wen1,2; Lu, Yuxu3; Guo, Yu1,2; Ren, Wenqi4; Zhu, Fenghua5; Lv, Yisheng5
刊名IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
出版日期2024-02-01
卷号9期号:2页码:3811-3826
关键词Meteorology Imaging Navigation Marine vehicles Feature extraction Visual perception Snow Deep neural network intelligent marine vehicles low-visibility enhancement severe weather visual perception
ISSN号2379-8858
DOI10.1109/TIV.2023.3347952
通讯作者Lu, Yuxu(yuxulouis.lu@connect.polyu.hk) ; Zhu, Fenghua(fenghua.zhu@ia.ac.cn)
英文摘要Benefiting from the higher performance-cost ratio and installation convenience, the visible-light imaging camera has become one of the most widely-used onboard sensors for safe vehicle navigation. However, the captured images inevitably suffer from color distortion, contrast reduction, or loss of fine details under severe weather conditions (such as haze, low-lightness, rain, and snow). The quality-degraded visual information will lead to limited perceptual accuracy and range, resulting in the increased navigation risk for intelligent marine vehicles. To suppress the influences of severe imaging conditions on navigation safety, this work proposes an all-in-one low-visibility enhancement network (termed AiOENet) to improve the visual perception for marine surface vehicles under different weather scenarios. Specifically, our AiOENet mainly consists of a VGG16-driven scene discriminator, an encoder, parameter-shared Transformer blocks, and a decoder. The scene discriminator is exploited to classify four degradation types of low-visibility images. According to the classification results, the low-visibility images are fed into the corresponding encoders for coarse feature extraction. The multiple Transformer blocks are then employed to separate and extract the smaller-scale features. The latent normal-visibility images are finally generated through the corresponding decoders. Therefore, our AiOENet has the capacity of flexibly and adaptively restoring diverse low-visibility images using a uniform encoder-decoder network architecture. Compared with the state-of-the-art imaging methods, the AiOENet achieves comparable or even superior enhancement results in terms of both quantitative and qualitative evaluations. In addition, our method can contribute to more accurate and stable object detection with improved visual perception in maritime low-visibility scenes.
WOS关键词OBJECT DETECTION ; NETWORK ; REAL
资助项目Hainan Provincial Joint Project of Sanya Yazhou Bay Science and Technology City
WOS研究方向Computer Science ; Engineering ; Transportation
语种英语
WOS记录号WOS:001215322100073
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Hainan Provincial Joint Project of Sanya Yazhou Bay Science and Technology City
源URL[http://ir.ia.ac.cn/handle/173211/59091]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Lu, Yuxu; Zhu, Fenghua
作者单位1.Wuhan Univ Technol, Sch Nav, Wuhan 430063, Peoples R China
2.State Key Lab Maritime Technol & Safety, Wuhan 430063, Peoples R China
3.Hong Kong Polytech Univ, Dept Logist & Maritime Studies, Hong Kong, Peoples R China
4.Sun Yat sen Univ Shenzhen, Sch Cyber Sci & Technol, Shenzhen 518107, Peoples R China
5.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Ryan Wen,Lu, Yuxu,Guo, Yu,et al. AiOENet: All-in-One Low-Visibility Enhancement to Improve Visual Perception for Intelligent Marine Vehicles Under Severe Weather Conditions[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(2):3811-3826.
APA Liu, Ryan Wen,Lu, Yuxu,Guo, Yu,Ren, Wenqi,Zhu, Fenghua,&Lv, Yisheng.(2024).AiOENet: All-in-One Low-Visibility Enhancement to Improve Visual Perception for Intelligent Marine Vehicles Under Severe Weather Conditions.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(2),3811-3826.
MLA Liu, Ryan Wen,et al."AiOENet: All-in-One Low-Visibility Enhancement to Improve Visual Perception for Intelligent Marine Vehicles Under Severe Weather Conditions".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.2(2024):3811-3826.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。