基于YOLOv4模型的小型车辆检测轻量级深度神经网络

Q4 Engineering

IEIE Transactions on Smart Processing and Computing Pub Date : 2023-10-31 DOI:10.5573/ieiespc.2023.12.5.369

Mingi Kim, Heegwang Kim, Chanyeong Park, Joonki Paik

{"title":"基于YOLOv4模型的小型车辆检测轻量级深度神经网络","authors":"Mingi Kim, Heegwang Kim, Chanyeong Park, Joonki Paik","doi":"10.5573/ieiespc.2023.12.5.369","DOIUrl":null,"url":null,"abstract":"In this paper, we present a light-weight deep neural network based on an efficiently scaled YOLOv4 model for detecting small objects in drone images. Since drone-captured images mainly contain small objects, we modified the YOLOv4 model by eliminating the head layer responsible for detecting large objects. This modification significantly reduced the model","PeriodicalId":37326,"journal":{"name":"IEIE Transactions on Smart Processing and Computing","volume":"16 2","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Light-weight Deep Neural Network for Small Vehicle Detection using Model-scale YOLOv4\",\"authors\":\"Mingi Kim, Heegwang Kim, Chanyeong Park, Joonki Paik\",\"doi\":\"10.5573/ieiespc.2023.12.5.369\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present a light-weight deep neural network based on an efficiently scaled YOLOv4 model for detecting small objects in drone images. Since drone-captured images mainly contain small objects, we modified the YOLOv4 model by eliminating the head layer responsible for detecting large objects. This modification significantly reduced the model\",\"PeriodicalId\":37326,\"journal\":{\"name\":\"IEIE Transactions on Smart Processing and Computing\",\"volume\":\"16 2\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-10-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEIE Transactions on Smart Processing and Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5573/ieiespc.2023.12.5.369\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEIE Transactions on Smart Processing and Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5573/ieiespc.2023.12.5.369","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

摘要

在本文中，我们提出了一种基于高效缩放YOLOv4模型的轻型深度神经网络，用于检测无人机图像中的小物体。由于无人机捕获的图像主要包含小物体，我们对YOLOv4模型进行了修改，去掉了负责检测大物体的头部层。这一修改大大缩小了模型

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Light-weight Deep Neural Network for Small Vehicle Detection using Model-scale YOLOv4

In this paper, we present a light-weight deep neural network based on an efficiently scaled YOLOv4 model for detecting small objects in drone images. Since drone-captured images mainly contain small objects, we modified the YOLOv4 model by eliminating the head layer responsible for detecting large objects. This modification significantly reduced the model

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

IEIE Transactions on Smart Processing and Computing Engineering-Electrical and Electronic Engineering

CiteScore

1.00

自引率

0.00%

发文量

期刊介绍： IEIE Transactions on Smart Processing & Computing (IEIE SPC) is a regular academic journal published by the IEIE (Institute of Electronics and Information Engineers). This journal is published bimonthly (the end of February, April, June, August, October, and December). The topics of the new journal include smart signal processing, smart wireless communications, and smart computing. Since all electronic devices have become human brain-like, signal processing, wireless communications, and computing are required to be smarter than traditional systems. Additionally, electronic computing devices have become smaller, and more mobile. Thus, we call for papers sharing the results of the state-of-art research in various fields of interest. In order to quickly disseminate new technologies and ideas for the smart signal processing, wireless communications, and computing, we publish our journal online only. Our most important aim is to publish the accepted papers quickly after receiving the manuscript. Our journal consists of regular and special issue papers. The papers are strictly peer-reviewed. Both theoretical and practical contributions are encouraged for our Transactions.