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. 深海科学与工程研究所
  3. 中国科学院深海科学与工程研究所
  4. 深海工程技术部
  5. 深海信息技术研究室
Vision-based underwater target real-time detection for autonomous underwater vehicle subsea exploration

文献类型：期刊论文

作者Xu, Gaofei5; Zhou, Daoxian2,3,4; Yuan, Libiao2,3,4; Guo, Wei5; Huang, Zepeng1; Zhang, Yinlong2,3,4
刊名FRONTIERS IN MARINE SCIENCE
出版日期2023-05-24
卷号10页码:12
关键词autonomous underwater vehicle subsea exploration real-time target detection lightweight convolutional neural network underwater image enhancement
DOI10.3389/fmars.2023.1112310
通讯作者Guo, Wei(guow@idsse.ac.cn) ; Zhang, Yinlong(zhangyinlong@sia.cn)
英文摘要Autonomous underwater vehicles (AUVs) equipped with online visual inspection systems can detect underwater targets during underwater operations, which is of great significance to subsea exploration. However, the undersea scene has some instinctive challenging problems, such as poor lighting conditions, sediment burial, and marine biofouling mimicry, which makes it difficult for traditional target detection algorithms to achieve online, reliable, and accurate detection of underwater targets. To solve the above issues, this paper proposes a real-time object detection algorithm for underwater targets based on a lightweight convolutional neural network model. To improve the imaging quality of underwater images, contrast limited adaptive histogram equalization with the fused multicolor space (FCLAHE) model is designed to enhance the image quality of underwater targets. Afterwards, a spindle-shaped backbone network is designed. The inverted residual block and group convolutions are used to extract depth features to ensure the target detection accuracy on one hand and to reduce the model parameter volume on the other hand under complex scenarios. Through extensive experiments, the precision, recall, and mAP of the proposed algorithm reached 91.2%, 90.1%, and 88.3%, respectively. It is also noticeable that the proposed method has been integrated into the embedded GPU platform and deployed in the AUV system in the practical scenarios. The average computational time is 0.053s, which satisfies the requirements of real-time object detection.
资助项目National Key Research and Development Program of China[2020YFC1521704] ; National Natural Science Foundation of China[62273332] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences[2023386]
WOS研究方向Environmental Sciences & Ecology ; Marine & Freshwater Biology
语种英语
出版者FRONTIERS MEDIA SA
WOS记录号WOS:001002778400001
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
源URL[http://ir.idsse.ac.cn/handle/183446/10492]  
专题深海工程技术部_深海信息技术研究室
通讯作者Guo, Wei; Zhang, Yinlong
作者单位1.Natl Ctr Archaeol, Underwater Archaeol Dept, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Robot & Intelligent Mfg, Shenyang, Peoples R China
3.Chinese Acad Sci, Key Lab Networked Control Syst, Shenyang, Peoples R China
4.Chinese Acad Sci, Shenyang Inst Automat, State Key Lab Robot, Shenyang, Peoples R China
5.Chinese Acad Sci, Inst Deep Sea Sci & Engn, Sanya, Peoples R China
推荐引用方式
GB/T 7714		 Xu, Gaofei,Zhou, Daoxian,Yuan, Libiao,et al. Vision-based underwater target real-time detection for autonomous underwater vehicle subsea exploration[J]. FRONTIERS IN MARINE SCIENCE,2023,10:12.
APA Xu, Gaofei,Zhou, Daoxian,Yuan, Libiao,Guo, Wei,Huang, Zepeng,&Zhang, Yinlong.(2023).Vision-based underwater target real-time detection for autonomous underwater vehicle subsea exploration.FRONTIERS IN MARINE SCIENCE,10,12.
MLA Xu, Gaofei,et al."Vision-based underwater target real-time detection for autonomous underwater vehicle subsea exploration".FRONTIERS IN MARINE SCIENCE 10(2023):12.

入库方式： OAI收割

来源：深海科学与工程研究所

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。