A Lightweight Underwater Object Detection Model: FL-YOLOV3-TINY

Cong Tan, Dandan Chen, Haijie Huang, Qiuling Yang, Xiangdang Huang
{"title":"A Lightweight Underwater Object Detection Model: FL-YOLOV3-TINY","authors":"Cong Tan, Dandan Chen, Haijie Huang, Qiuling Yang, Xiangdang Huang","doi":"10.1109/iemcon53756.2021.9623066","DOIUrl":null,"url":null,"abstract":"Due to the variety of underwater object species and small object, the traditional object detection model is difficult to adapt to underwater object detection in accuracy and real-time. In this paper, a lightweight detection model FL-YOLOV3-TINY is proposed, which improves the detection accuracy and real-time performance while shrinking the model size. In FL-YOLOV3-TINY, first, the model reduces the number of parameters by introducing deep separable convolutional module to replace traditional convolutional feature extraction module. Secondly, in order to improve the detection ability of small objects and obtain more delicate image features, FL-YOLOV3-TINY adds the feature size to the three-scale to improve the detection performance. Finally, the CIoU loss regression function is introduced to make the prediction box closer to the actual box. Experiments show that compared with other lightweight models YOLOV3-MobilenetV1 and YOLOV3-Tiny, FL-YOLOV3-TINY has better mAP performance (13.7% and 10.9% increase, respectively) and better real-time perfurmance(6% and 29% increase in FPS, respectively). Meanwhile, the model size is reduced by 43% compared to YOLOV3-Tiny.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iemcon53756.2021.9623066","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Due to the variety of underwater object species and small object, the traditional object detection model is difficult to adapt to underwater object detection in accuracy and real-time. In this paper, a lightweight detection model FL-YOLOV3-TINY is proposed, which improves the detection accuracy and real-time performance while shrinking the model size. In FL-YOLOV3-TINY, first, the model reduces the number of parameters by introducing deep separable convolutional module to replace traditional convolutional feature extraction module. Secondly, in order to improve the detection ability of small objects and obtain more delicate image features, FL-YOLOV3-TINY adds the feature size to the three-scale to improve the detection performance. Finally, the CIoU loss regression function is introduced to make the prediction box closer to the actual box. Experiments show that compared with other lightweight models YOLOV3-MobilenetV1 and YOLOV3-Tiny, FL-YOLOV3-TINY has better mAP performance (13.7% and 10.9% increase, respectively) and better real-time perfurmance(6% and 29% increase in FPS, respectively). Meanwhile, the model size is reduced by 43% compared to YOLOV3-Tiny.
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
一种轻型水下目标检测模型:FL-YOLOV3-TINY
由于水下目标种类繁多,目标体积小,传统的目标检测模型在精度和实时性上难以适应水下目标的检测。本文提出了一种轻量级的检测模型FL-YOLOV3-TINY,在缩小模型尺寸的同时提高了检测精度和实时性。在FL-YOLOV3-TINY中,首先,模型通过引入深度可分离卷积模块来取代传统的卷积特征提取模块,减少了参数的数量;其次,为了提高小物体的检测能力,获得更细腻的图像特征,FL-YOLOV3-TINY在三尺度中加入特征尺寸,提高检测性能。最后,引入CIoU损失回归函数,使预测框更接近实际框。实验表明,与其他轻量化模型YOLOV3-MobilenetV1和YOLOV3-Tiny相比,FL-YOLOV3-TINY具有更好的mAP性能(分别提高13.7%和10.9%)和更好的实时性(FPS分别提高6%和29%)。同时,与YOLOV3-Tiny相比,模型尺寸缩小43%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Maximization of the User Association of a Low-Power Tier Deploying Biased User Association Scheme in 5G Multi-Tier Heterogeneous Network A Deep Reinforcement Learning: Location-based Resource Allocation for Congested C-V2X Scenario A Deep Learning Approach to Predict Chronic Kidney Disease in Human Evaluation of a bio-socially inspired secure DSA scheme using testbed-calibrated hybrid simulations Siamese Network based Pulse and Signal Attribute Identification
×
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