Cargando…

Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network

This paper presents an extended model for a pedestrian attribute recognition network utilizing skeleton data as a soft attention model to extract a local feature corresponding to a specific attribute. This technique helped keep valuable information surrounding the target area and handle the variatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Sooksatra, Sorn, Rujikietgumjorn, Sitapa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8709013/
https://www.ncbi.nlm.nih.gov/pubmed/34940731
http://dx.doi.org/10.3390/jimaging7120264
_version_ 1784622829111607296
author Sooksatra, Sorn
Rujikietgumjorn, Sitapa
author_facet Sooksatra, Sorn
Rujikietgumjorn, Sitapa
author_sort Sooksatra, Sorn
collection PubMed
description This paper presents an extended model for a pedestrian attribute recognition network utilizing skeleton data as a soft attention model to extract a local feature corresponding to a specific attribute. This technique helped keep valuable information surrounding the target area and handle the variation of human posture. The attention masks were designed to focus on the partial and the whole-body regions. This research utilized an augmented layer for data augmentation inside the network to reduce over-fitting errors. Our network was evaluated in two datasets (RAP and PETA) with various backbone networks (ResNet-50, Inception V3, and Inception-ResNet V2). The experimental result shows that our network improves overall classification performance with a mean accuracy of about 2–3% in the same backbone network, especially local attributes and various human postures.
format Online
Article
Text
id pubmed-8709013
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87090132021-12-25 Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network Sooksatra, Sorn Rujikietgumjorn, Sitapa J Imaging Article This paper presents an extended model for a pedestrian attribute recognition network utilizing skeleton data as a soft attention model to extract a local feature corresponding to a specific attribute. This technique helped keep valuable information surrounding the target area and handle the variation of human posture. The attention masks were designed to focus on the partial and the whole-body regions. This research utilized an augmented layer for data augmentation inside the network to reduce over-fitting errors. Our network was evaluated in two datasets (RAP and PETA) with various backbone networks (ResNet-50, Inception V3, and Inception-ResNet V2). The experimental result shows that our network improves overall classification performance with a mean accuracy of about 2–3% in the same backbone network, especially local attributes and various human postures. MDPI 2021-12-04 /pmc/articles/PMC8709013/ /pubmed/34940731 http://dx.doi.org/10.3390/jimaging7120264 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sooksatra, Sorn
Rujikietgumjorn, Sitapa
Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title_full Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title_fullStr Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title_full_unstemmed Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title_short Skeleton-Based Attention Mask for Pedestrian Attribute Recognition Network
title_sort skeleton-based attention mask for pedestrian attribute recognition network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8709013/
https://www.ncbi.nlm.nih.gov/pubmed/34940731
http://dx.doi.org/10.3390/jimaging7120264
work_keys_str_mv AT sooksatrasorn skeletonbasedattentionmaskforpedestrianattributerecognitionnetwork
AT rujikietgumjornsitapa skeletonbasedattentionmaskforpedestrianattributerecognitionnetwork