基于卷积神经网络和增强的两阶段训练改进人再识别

IF 3.4 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Informatics Pub Date : 2023-03-29 DOI:10.37661/1816-0301-2023-20-1-40-54
S. Ihnatsyeva, R. Bohush
{"title":"基于卷积神经网络和增强的两阶段训练改进人再识别","authors":"S. Ihnatsyeva, R. Bohush","doi":"10.37661/1816-0301-2023-20-1-40-54","DOIUrl":null,"url":null,"abstract":"Objectives. The main goal is to improve person re-identification accuracy in distributed video surveillance systems.Methods. Machine learning methods are applied.Result. A technology for two-stage training of convolutional neural networks (CNN) is presented, characterized by the use of image augmentation for the preliminary stage and fine tuning of weight coefficients based on the original images set for training. At the first stage, training is carried out on augmented data, at the second stage, fine tuning of the CNN is performed on the original images, which allows minimizing the losses and increasing model efficiency. The use of different data at different training stages does not allow the CNN to remember training examples, thereby preventing overfitting.Proposed method as expanding the training sample differs as it combines an image pixels cyclic shift, color  exclusion and fragment replacement with a reduced copy of another image. This augmentation method allows to get a wide variety of training data, which increases the CNN robustness to occlusions, illumination, low image resolution, dependence on the location of features.Conclusion. The use of two-stage learning technology and the proposed data augmentation method made it possible to increase the person re-identification accuracy for different CNNs and datasets: in the Rank1 metric  by 4–21 %; in the mAP by 10–31 %; in the mINP by 39–60 %. ","PeriodicalId":37100,"journal":{"name":"Informatics","volume":" ","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving person re-identification based on two-stage training of convolutional neural networks and augmentation\",\"authors\":\"S. Ihnatsyeva, R. Bohush\",\"doi\":\"10.37661/1816-0301-2023-20-1-40-54\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Objectives. The main goal is to improve person re-identification accuracy in distributed video surveillance systems.Methods. Machine learning methods are applied.Result. A technology for two-stage training of convolutional neural networks (CNN) is presented, characterized by the use of image augmentation for the preliminary stage and fine tuning of weight coefficients based on the original images set for training. At the first stage, training is carried out on augmented data, at the second stage, fine tuning of the CNN is performed on the original images, which allows minimizing the losses and increasing model efficiency. The use of different data at different training stages does not allow the CNN to remember training examples, thereby preventing overfitting.Proposed method as expanding the training sample differs as it combines an image pixels cyclic shift, color  exclusion and fragment replacement with a reduced copy of another image. This augmentation method allows to get a wide variety of training data, which increases the CNN robustness to occlusions, illumination, low image resolution, dependence on the location of features.Conclusion. The use of two-stage learning technology and the proposed data augmentation method made it possible to increase the person re-identification accuracy for different CNNs and datasets: in the Rank1 metric  by 4–21 %; in the mAP by 10–31 %; in the mINP by 39–60 %. \",\"PeriodicalId\":37100,\"journal\":{\"name\":\"Informatics\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2023-03-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Informatics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.37661/1816-0301-2023-20-1-40-54\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37661/1816-0301-2023-20-1-40-54","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

目标。主要目的是提高分布式视频监控系统中人员再识别的准确性。机器学习方法的应用。提出了一种卷积神经网络(CNN)的两阶段训练技术,其特点是在初始阶段使用图像增强,并在原始图像集的基础上微调权重系数。第一阶段在增强数据上进行训练,第二阶段在原始图像上对CNN进行微调,使损失最小化,提高模型效率。在不同的训练阶段使用不同的数据,不允许CNN记住训练样例,从而防止过拟合。所提出的扩展训练样本的方法的不同之处在于它结合了图像像素的循环移位、颜色排除和片段替换与另一图像的简化副本。这种增强方法可以获得多种多样的训练数据,增强了CNN对遮挡、光照、低图像分辨率、对特征位置依赖性等的鲁棒性。使用两阶段学习技术和提出的数据增强方法可以提高不同cnn和数据集的人员再识别精度:在Rank1度量中提高4 - 21%;在mAP中下降10 - 31%;在mINP中占39% - 60%。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Improving person re-identification based on two-stage training of convolutional neural networks and augmentation
Objectives. The main goal is to improve person re-identification accuracy in distributed video surveillance systems.Methods. Machine learning methods are applied.Result. A technology for two-stage training of convolutional neural networks (CNN) is presented, characterized by the use of image augmentation for the preliminary stage and fine tuning of weight coefficients based on the original images set for training. At the first stage, training is carried out on augmented data, at the second stage, fine tuning of the CNN is performed on the original images, which allows minimizing the losses and increasing model efficiency. The use of different data at different training stages does not allow the CNN to remember training examples, thereby preventing overfitting.Proposed method as expanding the training sample differs as it combines an image pixels cyclic shift, color  exclusion and fragment replacement with a reduced copy of another image. This augmentation method allows to get a wide variety of training data, which increases the CNN robustness to occlusions, illumination, low image resolution, dependence on the location of features.Conclusion. The use of two-stage learning technology and the proposed data augmentation method made it possible to increase the person re-identification accuracy for different CNNs and datasets: in the Rank1 metric  by 4–21 %; in the mAP by 10–31 %; in the mINP by 39–60 %. 
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
Informatics
Informatics Social Sciences-Communication
CiteScore
6.60
自引率
6.50%
发文量
88
审稿时长
6 weeks
期刊最新文献
Simulation of discrete control systems with parallelism of behavior Formal description model and conditions for detecting linked coupling faults of the memory devices A model of homographs automatic identification for the Belarusian language Ontological analysis in the problems of container applications threat modelling Closed Gordon – Newell network with single-line poles and exponentially limited request waiting time
×
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