{"title":"Self-Supervised Marine Organism Detection From Underwater Images","authors":"Jiahua Li;Wentao Yang;Shishi Qiao;Zhaorui Gu;Bing Zheng;Haiyong Zheng","doi":"10.1109/JOE.2024.3455565","DOIUrl":null,"url":null,"abstract":"In recent years, in light of the significant progress in deep learning on general object detection, research on marine organism detection has become increasingly popular. However, manual annotation of marine organism images usually requires specialized expertise, resulting in a scarcity of labeled data for research purposes. In addition, the complex and dynamic marine environment leads to varying degrees of light absorption and scattering, causing severe degradation issues in the collected images. These factors hinder the acquisition of high-quality representations for subsequent detection objectives. To overcome the reliance on annotated marine data sets and derive high-quality representations from extensive unlabeled and degraded data, we propose a self-supervised marine organism detection (SMOD) framework. To the best of the authors' knowledge, it is the first time that self-supervised learning has been introduced into the task of marine organism object detection. Specifically, in order to improve the quality of learned image representation from degraded data, a set of underwater augmentation strategies to improve the perceptional quality of underwater images is designed. To further address the challenging issue posed by numerous marine objects and diverse backgrounds, an underwater attention module is elaborately devised such that the model prioritizes objects over backgrounds during representation learning. Experimental results on URPC2021 data set show that our SMOD achieves competitive performance in the marine organism object detection task.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 1","pages":"120-135"},"PeriodicalIF":3.8000,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Journal of Oceanic Engineering","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10716005/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
Abstract
In recent years, in light of the significant progress in deep learning on general object detection, research on marine organism detection has become increasingly popular. However, manual annotation of marine organism images usually requires specialized expertise, resulting in a scarcity of labeled data for research purposes. In addition, the complex and dynamic marine environment leads to varying degrees of light absorption and scattering, causing severe degradation issues in the collected images. These factors hinder the acquisition of high-quality representations for subsequent detection objectives. To overcome the reliance on annotated marine data sets and derive high-quality representations from extensive unlabeled and degraded data, we propose a self-supervised marine organism detection (SMOD) framework. To the best of the authors' knowledge, it is the first time that self-supervised learning has been introduced into the task of marine organism object detection. Specifically, in order to improve the quality of learned image representation from degraded data, a set of underwater augmentation strategies to improve the perceptional quality of underwater images is designed. To further address the challenging issue posed by numerous marine objects and diverse backgrounds, an underwater attention module is elaborately devised such that the model prioritizes objects over backgrounds during representation learning. Experimental results on URPC2021 data set show that our SMOD achieves competitive performance in the marine organism object detection task.
期刊介绍:
The IEEE Journal of Oceanic Engineering (ISSN 0364-9059) is the online-only quarterly publication of the IEEE Oceanic Engineering Society (IEEE OES). The scope of the Journal is the field of interest of the IEEE OES, which encompasses all aspects of science, engineering, and technology that address research, development, and operations pertaining to all bodies of water. This includes the creation of new capabilities and technologies from concept design through prototypes, testing, and operational systems to sense, explore, understand, develop, use, and responsibly manage natural resources.