Cargando…

GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System

Infrared cameras allow non-invasive and 24 h continuous monitoring. Thus, they are widely used in automatic pig monitoring, which is essential to maintain the profitability and sustainability of intensive pig farms. However, in practice, impurities such as insect secretions continuously pollute came...

Descripción completa

Detalles Bibliográficos
Autores principales: Bo, Zhao, Atif, Othmane, Lee, Jonguk, Park, Daihee, Chung, Yongwha
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9143193/
https://www.ncbi.nlm.nih.gov/pubmed/35632328
http://dx.doi.org/10.3390/s22103917
_version_ 1784715745258635264
author Bo, Zhao
Atif, Othmane
Lee, Jonguk
Park, Daihee
Chung, Yongwha
author_facet Bo, Zhao
Atif, Othmane
Lee, Jonguk
Park, Daihee
Chung, Yongwha
author_sort Bo, Zhao
collection PubMed
description Infrared cameras allow non-invasive and 24 h continuous monitoring. Thus, they are widely used in automatic pig monitoring, which is essential to maintain the profitability and sustainability of intensive pig farms. However, in practice, impurities such as insect secretions continuously pollute camera lenses. This causes problems with IR reflections, which can seriously affect pig detection performance. In this study, we propose a noise-robust, real-time pig detection system that can improve accuracy in pig farms where infrared cameras suffer from the IR reflection problem. The system consists of a data collector to collect infrared images, a preprocessor to transform noisy images into clean images, and a detector to detect pigs. The preprocessor embeds a multi-scale spatial attention module in U-net and generative adversarial network (GAN) models, enabling the model to pay more attention to the noisy area. The GAN model was trained on paired sets of clean data and data with simulated noise. It can operate in a real-time and end-to-end manner. Experimental results show that the proposed preprocessor was able to significantly improve the average precision of pig detection from 0.766 to 0.906, with an additional execution time of only 4.8 ms on a PC environment.
format Online
Article
Text
id pubmed-9143193
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91431932022-05-29 GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System Bo, Zhao Atif, Othmane Lee, Jonguk Park, Daihee Chung, Yongwha Sensors (Basel) Article Infrared cameras allow non-invasive and 24 h continuous monitoring. Thus, they are widely used in automatic pig monitoring, which is essential to maintain the profitability and sustainability of intensive pig farms. However, in practice, impurities such as insect secretions continuously pollute camera lenses. This causes problems with IR reflections, which can seriously affect pig detection performance. In this study, we propose a noise-robust, real-time pig detection system that can improve accuracy in pig farms where infrared cameras suffer from the IR reflection problem. The system consists of a data collector to collect infrared images, a preprocessor to transform noisy images into clean images, and a detector to detect pigs. The preprocessor embeds a multi-scale spatial attention module in U-net and generative adversarial network (GAN) models, enabling the model to pay more attention to the noisy area. The GAN model was trained on paired sets of clean data and data with simulated noise. It can operate in a real-time and end-to-end manner. Experimental results show that the proposed preprocessor was able to significantly improve the average precision of pig detection from 0.766 to 0.906, with an additional execution time of only 4.8 ms on a PC environment. MDPI 2022-05-22 /pmc/articles/PMC9143193/ /pubmed/35632328 http://dx.doi.org/10.3390/s22103917 Text en © 2022 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
Bo, Zhao
Atif, Othmane
Lee, Jonguk
Park, Daihee
Chung, Yongwha
GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title_full GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title_fullStr GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title_full_unstemmed GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title_short GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System
title_sort gan-based video denoising with attention mechanism for field-applicable pig detection system
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9143193/
https://www.ncbi.nlm.nih.gov/pubmed/35632328
http://dx.doi.org/10.3390/s22103917
work_keys_str_mv AT bozhao ganbasedvideodenoisingwithattentionmechanismforfieldapplicablepigdetectionsystem
AT atifothmane ganbasedvideodenoisingwithattentionmechanismforfieldapplicablepigdetectionsystem
AT leejonguk ganbasedvideodenoisingwithattentionmechanismforfieldapplicablepigdetectionsystem
AT parkdaihee ganbasedvideodenoisingwithattentionmechanismforfieldapplicablepigdetectionsystem
AT chungyongwha ganbasedvideodenoisingwithattentionmechanismforfieldapplicablepigdetectionsystem