Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor

For people re-identification in distributed video surveillance systems, it is important to have an algorithm that ensures efficiency when a person is blocked by other people or objects. Therefore, for this task, an algorithm has been developed that involves the compound descriptor formation, which i...

Full description

Saved in:
Bibliographic Details
Main Authors: S. A. Ihnatsyeva, R. P. Bohush
Format: Article
Language:English
Published: Belarusian National Technical University 2024-05-01
Series:Системный анализ и прикладная информатика
Subjects:
Online Access:https://sapi.bntu.by/jour/article/view/654
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832557283783999488
author S. A. Ihnatsyeva
R. P. Bohush
author_facet S. A. Ihnatsyeva
R. P. Bohush
author_sort S. A. Ihnatsyeva
collection DOAJ
description For people re-identification in distributed video surveillance systems, it is important to have an algorithm that ensures efficiency when a person is blocked by other people or objects. Therefore, for this task, an algorithm has been developed that involves the compound descriptor formation, which includes a global features vector of a person’s image and three local ones for its upper, middle and down parts. The regions of interest selection is carried out based on the detecting key points results in the image of the human body. If a person's image part is occluded by other people or objects, then it is classified as invisible. The hidden part person image is not used in the formation of the local feature. To obtain it, the average value of the k-nearest neighbors such features of a person’s image is calculated. The experiments performed indicate an increase in re-identification accuracy for the Market-1501, DukeMTMC-ReID, MSMT17 and PolReID1077 datasets.
format Article
id doaj-art-1573e318033146a1b7ccb5cade850805
institution Kabale University
issn 2309-4923
2414-0481
language English
publishDate 2024-05-01
publisher Belarusian National Technical University
record_format Article
series Системный анализ и прикладная информатика
spelling doaj-art-1573e318033146a1b7ccb5cade8508052025-02-03T05:16:55ZengBelarusian National Technical UniversityСистемный анализ и прикладная информатика2309-49232414-04812024-05-0101121710.21122/2309-4923-2024-1-12-17480Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptorS. A. Ihnatsyeva0R. P. Bohush1Euphrosyne Polotskaya State University of PolotskEuphrosyne Polotskaya State University of PolotskFor people re-identification in distributed video surveillance systems, it is important to have an algorithm that ensures efficiency when a person is blocked by other people or objects. Therefore, for this task, an algorithm has been developed that involves the compound descriptor formation, which includes a global features vector of a person’s image and three local ones for its upper, middle and down parts. The regions of interest selection is carried out based on the detecting key points results in the image of the human body. If a person's image part is occluded by other people or objects, then it is classified as invisible. The hidden part person image is not used in the formation of the local feature. To obtain it, the average value of the k-nearest neighbors such features of a person’s image is calculated. The experiments performed indicate an increase in re-identification accuracy for the Market-1501, DukeMTMC-ReID, MSMT17 and PolReID1077 datasets.https://sapi.bntu.by/jour/article/view/654machine learningconvolutional neural networksfeature vectorpolreid1077data augmentation
spellingShingle S. A. Ihnatsyeva
R. P. Bohush
Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
Системный анализ и прикладная информатика
machine learning
convolutional neural networks
feature vector
polreid1077
data augmentation
title Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
title_full Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
title_fullStr Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
title_full_unstemmed Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
title_short Person re-identification algorithm by image from video surveilance sistem using a neural network compound descriptor
title_sort person re identification algorithm by image from video surveilance sistem using a neural network compound descriptor
topic machine learning
convolutional neural networks
feature vector
polreid1077
data augmentation
url https://sapi.bntu.by/jour/article/view/654
work_keys_str_mv AT saihnatsyeva personreidentificationalgorithmbyimagefromvideosurveilancesistemusinganeuralnetworkcompounddescriptor
AT rpbohush personreidentificationalgorithmbyimagefromvideosurveilancesistemusinganeuralnetworkcompounddescriptor