Cargando…
A multi-branch separable convolution neural network for pedestrian attribute recognition
Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds t...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7078519/ https://www.ncbi.nlm.nih.gov/pubmed/32195393 http://dx.doi.org/10.1016/j.heliyon.2020.e03563 |
_version_ | 1783507636854980608 |
---|---|
author | Junejo, Imran N. Ahmed, Naveed |
author_facet | Junejo, Imran N. Ahmed, Naveed |
author_sort | Junejo, Imran N. |
collection | PubMed |
description | Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses depthwise separable convolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art. |
format | Online Article Text |
id | pubmed-7078519 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-70785192020-03-19 A multi-branch separable convolution neural network for pedestrian attribute recognition Junejo, Imran N. Ahmed, Naveed Heliyon Article Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses depthwise separable convolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art. Elsevier 2020-03-17 /pmc/articles/PMC7078519/ /pubmed/32195393 http://dx.doi.org/10.1016/j.heliyon.2020.e03563 Text en © 2020 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Article Junejo, Imran N. Ahmed, Naveed A multi-branch separable convolution neural network for pedestrian attribute recognition |
title | A multi-branch separable convolution neural network for pedestrian attribute recognition |
title_full | A multi-branch separable convolution neural network for pedestrian attribute recognition |
title_fullStr | A multi-branch separable convolution neural network for pedestrian attribute recognition |
title_full_unstemmed | A multi-branch separable convolution neural network for pedestrian attribute recognition |
title_short | A multi-branch separable convolution neural network for pedestrian attribute recognition |
title_sort | multi-branch separable convolution neural network for pedestrian attribute recognition |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7078519/ https://www.ncbi.nlm.nih.gov/pubmed/32195393 http://dx.doi.org/10.1016/j.heliyon.2020.e03563 |
work_keys_str_mv | AT junejoimrann amultibranchseparableconvolutionneuralnetworkforpedestrianattributerecognition AT ahmednaveed amultibranchseparableconvolutionneuralnetworkforpedestrianattributerecognition AT junejoimrann multibranchseparableconvolutionneuralnetworkforpedestrianattributerecognition AT ahmednaveed multibranchseparableconvolutionneuralnetworkforpedestrianattributerecognition |