基于生成特征模块的水下不完全目标识别网络

IF 1.9 4区 计算机科学 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS International Journal of Distributed Sensor Networks Pub Date : 2023-01-12 DOI:10.1155/2023/5337454
Qi Shen, Jishen Jia, Lei Cai
{"title":"基于生成特征模块的水下不完全目标识别网络","authors":"Qi Shen, Jishen Jia, Lei Cai","doi":"10.1155/2023/5337454","DOIUrl":null,"url":null,"abstract":"A complex and changeable underwater archaeological environment leads to the lack of target features in the collected images, affecting the accuracy of target detection. Meanwhile, the difficulty in obtaining underwater archaeological images leads to less training data, resulting in poor generalization performance of the recognition algorithm. For these practical issues, we propose an underwater incomplete target recognition network via generating feature module (UITRNet). Specifically, for targets that lack features, features are generated by dual discriminators and generators to improve target detection accuracy. Then, multilayer features are fused to extract regions of interest. Finally, supervised contrastive learning is introduced into few-shot learning to improve the intraclass similarity and interclass distance of the target and enhance the generalization of the algorithm. The UIFI dataset is produced to verify the effectiveness of the algorithm in this paper. The experimental results show that the mean average precision (mAP) of our algorithm was improved by 0.86% and 1.29% under insufficient light and semiburied interference, respectively. The mAP for ship identification reached the highest level under all four sets of experiments.","PeriodicalId":50327,"journal":{"name":"International Journal of Distributed Sensor Networks","volume":" ","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Underwater Incomplete Target Recognition Network via Generating Feature Module\",\"authors\":\"Qi Shen, Jishen Jia, Lei Cai\",\"doi\":\"10.1155/2023/5337454\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A complex and changeable underwater archaeological environment leads to the lack of target features in the collected images, affecting the accuracy of target detection. Meanwhile, the difficulty in obtaining underwater archaeological images leads to less training data, resulting in poor generalization performance of the recognition algorithm. For these practical issues, we propose an underwater incomplete target recognition network via generating feature module (UITRNet). Specifically, for targets that lack features, features are generated by dual discriminators and generators to improve target detection accuracy. Then, multilayer features are fused to extract regions of interest. Finally, supervised contrastive learning is introduced into few-shot learning to improve the intraclass similarity and interclass distance of the target and enhance the generalization of the algorithm. The UIFI dataset is produced to verify the effectiveness of the algorithm in this paper. The experimental results show that the mean average precision (mAP) of our algorithm was improved by 0.86% and 1.29% under insufficient light and semiburied interference, respectively. The mAP for ship identification reached the highest level under all four sets of experiments.\",\"PeriodicalId\":50327,\"journal\":{\"name\":\"International Journal of Distributed Sensor Networks\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2023-01-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Distributed Sensor Networks\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1155/2023/5337454\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Distributed Sensor Networks","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1155/2023/5337454","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

复杂多变的水下考古环境导致采集到的图像缺乏目标特征,影响了目标检测的准确性。同时,水下考古图像的获取困难导致训练数据较少,导致识别算法的泛化性能较差。针对这些实际问题,我们提出了一种基于生成特征模块的水下不完全目标识别网络。具体来说,对于缺乏特征的目标,通过双鉴别器和生成器生成特征,以提高目标检测精度。然后,对多层特征进行融合以提取感兴趣的区域。最后,将监督对比学习引入到少镜头学习中,以提高目标的类内相似性和类间距离,增强算法的泛化能力。生成UIFI数据集以验证本文算法的有效性。实验结果表明,在弱光和半隐式干涉下,算法的平均精度分别提高了0.86%和1.29%。用于船舶识别的mAP在所有四组实验中都达到了最高水平。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Underwater Incomplete Target Recognition Network via Generating Feature Module
A complex and changeable underwater archaeological environment leads to the lack of target features in the collected images, affecting the accuracy of target detection. Meanwhile, the difficulty in obtaining underwater archaeological images leads to less training data, resulting in poor generalization performance of the recognition algorithm. For these practical issues, we propose an underwater incomplete target recognition network via generating feature module (UITRNet). Specifically, for targets that lack features, features are generated by dual discriminators and generators to improve target detection accuracy. Then, multilayer features are fused to extract regions of interest. Finally, supervised contrastive learning is introduced into few-shot learning to improve the intraclass similarity and interclass distance of the target and enhance the generalization of the algorithm. The UIFI dataset is produced to verify the effectiveness of the algorithm in this paper. The experimental results show that the mean average precision (mAP) of our algorithm was improved by 0.86% and 1.29% under insufficient light and semiburied interference, respectively. The mAP for ship identification reached the highest level under all four sets of experiments.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
6.50
自引率
4.30%
发文量
94
审稿时长
3.6 months
期刊介绍: International Journal of Distributed Sensor Networks (IJDSN) is a JCR ranked, peer-reviewed, open access journal that focuses on applied research and applications of sensor networks. The goal of this journal is to provide a forum for the publication of important research contributions in developing high performance computing solutions to problems arising from the complexities of these sensor network systems. Articles highlight advances in uses of sensor network systems for solving computational tasks in manufacturing, engineering and environmental systems.
期刊最新文献
An Intrusion Detection Model Based on Feature Selection and Improved One-Dimensional Convolutional Neural Network Convex Combination for Wireless Localization Using Biased RSS Measurements Research on Visual SLAM Navigation Techniques for Dynamic Environments Improved Private Data Protection Scheme for Blockchain Smart Contracts Parameter Identification of Frame Structures by considering Shear Deformation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1