GIFF-AlgaeDet: An effective and lightweight deep learning method based on Global Information and Feature Fusion for microalgae detection

IF 4.6 2区 生物学 Q1 BIOTECHNOLOGY & APPLIED MICROBIOLOGY
Yanjuan Wang , Zhenquan Liu , Jiayue Liu , Yuhang Shi , Wenjing Ren , Xiaohong Yan , Jiangpeng Fan , Fengqi Li
{"title":"GIFF-AlgaeDet: An effective and lightweight deep learning method based on Global Information and Feature Fusion for microalgae detection","authors":"Yanjuan Wang ,&nbsp;Zhenquan Liu ,&nbsp;Jiayue Liu ,&nbsp;Yuhang Shi ,&nbsp;Wenjing Ren ,&nbsp;Xiaohong Yan ,&nbsp;Jiangpeng Fan ,&nbsp;Fengqi Li","doi":"10.1016/j.algal.2024.103815","DOIUrl":null,"url":null,"abstract":"<div><div>The identification and detection of microalgae are essential prerequisites for the development and utilization of microalgal resources. Traditional methods for the identification and detection of microalgae face the challenges of poor accuracy and time-consuming labor. Here is a method for microalgae identification and detection proposed in this paper, which utilizes Global Information and Feature Fusion (GIFF).</div><div>Initially, to address the issue of low accuracy, the Coordinate Attention Group Shuffle Convolution (CAGS) is incorporated into the method to enhance the feature extraction capability. Furthermore, to address the issue of time-consuming labor, two small object detection heads for microalgae detection have been designed to effectively improve the training and detection speed. Additionally, the SCYLLA-IoU (SIoU) algorithm is employed to address the issue of unstable model convergence. To assess the efficacy of the method employed in this study, a dataset was intentionally created for the purpose of detecting microalgae. The experimental results indicate that, under the same experimental conditions, the proposed method has achieved significant improvements in terms of average precision, mAP@50, and mAP@95. Compared to the original method, it has increased by 3.1 %, 2 %, and 9.8 %, respectively. Moreover, this algorithm obtains a great improvement in detection speed and lightness, with a 29 % reduction in parameters and a single image detection time of 0.0219 s, which is significantly less than baseline. Location of the dataset and code: <span><span><em>https://github.com/DjtuResearch/Microalgae_detection</em></span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7855,"journal":{"name":"Algal Research-Biomass Biofuels and Bioproducts","volume":"84 ","pages":"Article 103815"},"PeriodicalIF":4.6000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Algal Research-Biomass Biofuels and Bioproducts","FirstCategoryId":"99","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2211926424004272","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The identification and detection of microalgae are essential prerequisites for the development and utilization of microalgal resources. Traditional methods for the identification and detection of microalgae face the challenges of poor accuracy and time-consuming labor. Here is a method for microalgae identification and detection proposed in this paper, which utilizes Global Information and Feature Fusion (GIFF).
Initially, to address the issue of low accuracy, the Coordinate Attention Group Shuffle Convolution (CAGS) is incorporated into the method to enhance the feature extraction capability. Furthermore, to address the issue of time-consuming labor, two small object detection heads for microalgae detection have been designed to effectively improve the training and detection speed. Additionally, the SCYLLA-IoU (SIoU) algorithm is employed to address the issue of unstable model convergence. To assess the efficacy of the method employed in this study, a dataset was intentionally created for the purpose of detecting microalgae. The experimental results indicate that, under the same experimental conditions, the proposed method has achieved significant improvements in terms of average precision, mAP@50, and mAP@95. Compared to the original method, it has increased by 3.1 %, 2 %, and 9.8 %, respectively. Moreover, this algorithm obtains a great improvement in detection speed and lightness, with a 29 % reduction in parameters and a single image detection time of 0.0219 s, which is significantly less than baseline. Location of the dataset and code: https://github.com/DjtuResearch/Microalgae_detection.

Abstract Image

求助全文
约1分钟内获得全文 求助全文
来源期刊
Algal Research-Biomass Biofuels and Bioproducts
Algal Research-Biomass Biofuels and Bioproducts BIOTECHNOLOGY & APPLIED MICROBIOLOGY-
CiteScore
9.40
自引率
7.80%
发文量
332
期刊介绍: Algal Research is an international phycology journal covering all areas of emerging technologies in algae biology, biomass production, cultivation, harvesting, extraction, bioproducts, biorefinery, engineering, and econometrics. Algae is defined to include cyanobacteria, microalgae, and protists and symbionts of interest in biotechnology. The journal publishes original research and reviews for the following scope: algal biology, including but not exclusive to: phylogeny, biodiversity, molecular traits, metabolic regulation, and genetic engineering, algal cultivation, e.g. phototrophic systems, heterotrophic systems, and mixotrophic systems, algal harvesting and extraction systems, biotechnology to convert algal biomass and components into biofuels and bioproducts, e.g., nutraceuticals, pharmaceuticals, animal feed, plastics, etc. algal products and their economic assessment
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信