Encoded Deep Features for Visual Place Recognition

A. Hafez, Saed Alqaraleh, Ammar Tello
{"title":"Encoded Deep Features for Visual Place Recognition","authors":"A. Hafez, Saed Alqaraleh, Ammar Tello","doi":"10.1109/SIU49456.2020.9302266","DOIUrl":null,"url":null,"abstract":"In this work, a new VPR approach that uses the features extracted from a Convolutional Neural Network (CNN) architecture that will be encoded by the Fisher Vector (FV) is introduced. As the main aim of this work is to develop a robust approach that can meet real-life challenges, the deep features are encoded with FV, which as shown in the experiments section, can lead to getting more robust features. Our approach was evaluated using two classifiers, Dynamic Time Warping (DTW) and Support Vector Machine (SVM) in particular. Using both classifiers, the FV-based encoded features have outperformed the non-encoded features.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 28th Signal Processing and Communications Applications Conference (SIU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIU49456.2020.9302266","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

In this work, a new VPR approach that uses the features extracted from a Convolutional Neural Network (CNN) architecture that will be encoded by the Fisher Vector (FV) is introduced. As the main aim of this work is to develop a robust approach that can meet real-life challenges, the deep features are encoded with FV, which as shown in the experiments section, can lead to getting more robust features. Our approach was evaluated using two classifiers, Dynamic Time Warping (DTW) and Support Vector Machine (SVM) in particular. Using both classifiers, the FV-based encoded features have outperformed the non-encoded features.
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
用于视觉位置识别的编码深度特征
在这项工作中,介绍了一种新的VPR方法,该方法使用从卷积神经网络(CNN)架构中提取的特征,该特征将由Fisher向量(FV)编码。由于这项工作的主要目的是开发一种能够满足现实挑战的鲁棒方法,因此使用FV编码深度特征,如实验部分所示,可以获得更鲁棒的特征。我们的方法使用两个分类器进行评估,特别是动态时间翘曲(DTW)和支持向量机(SVM)。使用这两种分类器,基于fv的编码特征优于非编码特征。
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
Skin Lesion Classification With Deep CNN Ensembles Design of a New System for Upper Extremity Movement Ability Assessment Stock Market Prediction with Stacked Autoencoder Based Feature Reduction Segmentation networks reinforced with attribute profiles for large scale land-cover map production Encoded Deep Features for Visual Place Recognition
×
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