Cover Image

Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification

Human re-identification is to match a pair of humans appearing in different cameras with non-overlapping views. However, in order to achieve this task, we need to overcome several challenges such as variations in lighting, viewpoint, pose and colour. In this paper, we propose a new approach for pers...

Full description

Saved in:
Bibliographic Details
Main Authors: Low, K. B., Sheikh, U. U.
Format: Conference or Workshop Item
Published: Institute of Electrical and Electronics Engineers Inc. 2016
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://eprints.utm.my/id/eprint/73463/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964817632&doi=10.1109%2fICDIM.2015.7381875&partnerID=40&md5=6571936f40c48b02b047f16f616982cf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.73463
record_format eprints
spelling my.utm.734632017-11-23T04:17:45Z http://eprints.utm.my/id/eprint/73463/ Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification Low, K. B. Sheikh, U. U. TK Electrical engineering. Electronics Nuclear engineering Human re-identification is to match a pair of humans appearing in different cameras with non-overlapping views. However, in order to achieve this task, we need to overcome several challenges such as variations in lighting, viewpoint, pose and colour. In this paper, we propose a new approach for person re-identification in multi-camera networks by using a hierarchical structure with a Siamese Convolution Neural Network (SCNN). A set of human pairs is projected into the same feature subspace through a nonlinear transformation that is learned by using a convolution neural network. The learning process minimizes the loss function, which ensures that the similarity distance between positive pairs is less than lower threshold and the similarity distance between negative pairs is higher than upper threshold. Our experiment is achieved by using a small scale of dataset due to the computation time. Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset is used in our experiment, since it is widely employed in this field. Initial results suggest that the proposed SCNN structure has good performance in people re-identification. Institute of Electrical and Electronics Engineers Inc. 2016 Conference or Workshop Item PeerReviewed Low, K. B. and Sheikh, U. U. (2016) Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification. In: 10th International Conference on Digital Information Management, ICDIM 2015, 21-23 Oct 2015, South Korea. https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964817632&doi=10.1109%2fICDIM.2015.7381875&partnerID=40&md5=6571936f40c48b02b047f16f616982cf
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic TK Electrical engineering. Electronics Nuclear engineering
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Low, K. B.
Sheikh, U. U.
Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
description Human re-identification is to match a pair of humans appearing in different cameras with non-overlapping views. However, in order to achieve this task, we need to overcome several challenges such as variations in lighting, viewpoint, pose and colour. In this paper, we propose a new approach for person re-identification in multi-camera networks by using a hierarchical structure with a Siamese Convolution Neural Network (SCNN). A set of human pairs is projected into the same feature subspace through a nonlinear transformation that is learned by using a convolution neural network. The learning process minimizes the loss function, which ensures that the similarity distance between positive pairs is less than lower threshold and the similarity distance between negative pairs is higher than upper threshold. Our experiment is achieved by using a small scale of dataset due to the computation time. Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset is used in our experiment, since it is widely employed in this field. Initial results suggest that the proposed SCNN structure has good performance in people re-identification.
format Conference or Workshop Item
author Low, K. B.
Sheikh, U. U.
author_facet Low, K. B.
Sheikh, U. U.
author_sort Low, K. B.
title Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
title_short Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
title_full Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
title_fullStr Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
title_full_unstemmed Learning hierarchical representation using Siamese Convolution Neural Network for human re-identification
title_sort learning hierarchical representation using siamese convolution neural network for human re-identification
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2016
url http://eprints.utm.my/id/eprint/73463/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964817632&doi=10.1109%2fICDIM.2015.7381875&partnerID=40&md5=6571936f40c48b02b047f16f616982cf
_version_ 1643656667459485696
score 13.211869

Similar Items