Data Augmentation and Fine Tuning of Convolutional Neural Network during Training for Person Re-Identification in Video Surveillance Systems

IF 1 Q4 OPTICS Optical Memory and Neural Networks Pub Date : 2023-12-22 DOI:10.3103/s1060992x23040124

S. Ye, R. Bohush, H. Chen, S. Ihnatsyeva, S. V. Ablameyko

{"title":"Data Augmentation and Fine Tuning of Convolutional Neural Network during Training for Person Re-Identification in Video Surveillance Systems","authors":"S. Ye, R. Bohush, H. Chen, S. Ihnatsyeva, S. V. Ablameyko","doi":"10.3103/s1060992x23040124","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>A new image set, augmentation method and fine in-learning adjustment of convolutional neural networks (CNN) are proposed to increase the accuracy of CNN-based person re-identification. Unlike other known sets, we have used many video frames from external and internal surveillance systems shot at all seasons of the year to make up our PolReID1077 set of person images. The PolReID1077-forming samples are subjected to the cyclic shift, chroma subsampling, and replacement of a fragment by a reduced copy of another sample to get a wider range of images. The learning set generating technique is used to train a CNN. The training is carried out in two stages. The first stage is pre-training using the augmented data. At the second stage the original images are used to carry out fine-tuning of CNN weight coefficients to reduce in-learning losses and increase re-identification efficiency. The approach doesn’t allow the CNN to remember learning sets and decreases the chances of overfitting. Different augmentation methods, data sets and learning techniques are used in the experiments.</p>","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"120 1","pages":""},"PeriodicalIF":1.0000,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optical Memory and Neural Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3103/s1060992x23040124","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"OPTICS","Score":null,"Total":0}

引用次数: 0

Abstract

A new image set, augmentation method and fine in-learning adjustment of convolutional neural networks (CNN) are proposed to increase the accuracy of CNN-based person re-identification. Unlike other known sets, we have used many video frames from external and internal surveillance systems shot at all seasons of the year to make up our PolReID1077 set of person images. The PolReID1077-forming samples are subjected to the cyclic shift, chroma subsampling, and replacement of a fragment by a reduced copy of another sample to get a wider range of images. The learning set generating technique is used to train a CNN. The training is carried out in two stages. The first stage is pre-training using the augmented data. At the second stage the original images are used to carry out fine-tuning of CNN weight coefficients to reduce in-learning losses and increase re-identification efficiency. The approach doesn’t allow the CNN to remember learning sets and decreases the chances of overfitting. Different augmentation methods, data sets and learning techniques are used in the experiments.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

用于视频监控系统中人员再识别的卷积神经网络在训练过程中的数据增强和微调

摘要我们提出了一种新的图像集、增强方法和卷积神经网络（CNN）的精细内学习调整，以提高基于 CNN 的人物再识别的准确性。与其他已知图像集不同的是，我们使用了许多来自外部和内部监控系统的一年四季拍摄的视频帧来组成我们的 PolReID1077 人物图像集。PolReID1077 形成的样本要经过循环移位、色度子采样，并用另一个样本的缩小副本替换一个片段，以获得范围更广的图像。学习集生成技术用于训练 CNN。训练分两个阶段进行。第一阶段是使用增强数据进行预训练。第二阶段使用原始图像对 CNN 权重系数进行微调，以减少学习中的损失，提高重新识别效率。这种方法不会让 CNN 记住学习集，降低了过度拟合的几率。实验中使用了不同的增强方法、数据集和学习技术。

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

Optical Memory and Neural Networks OPTICS-

CiteScore

1.50

自引率

11.10%

发文量

期刊介绍： The journal covers a wide range of issues in information optics such as optical memory, mechanisms for optical data recording and processing, photosensitive materials, optical, optoelectronic and holographic nanostructures, and many other related topics. Papers on memory systems using holographic and biological structures and concepts of brain operation are also included. The journal pays particular attention to research in the field of neural net systems that may lead to a new generation of computional technologies by endowing them with intelligence.