Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment

Heat stress stands out as one of the main elements linked to concerns related to animal thermal comfort. This research aims to develop a sequential methodology for the extraction of automatic characteristics from thermal images and the classification of heat stress in pigs by means of machine learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Maria de Fátima Araújo Alves, Héliton Pandorfi, Rodrigo Gabriel Ferreira Soares, Gledson Luiz Pontes de Almeida, Taize Calvacante Santana, Marcos Vinícius da Silva
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:AgriEngineering
Subjects:
Online Access:https://www.mdpi.com/2624-7402/6/3/183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258480753016832
author Maria de Fátima Araújo Alves
Héliton Pandorfi
Rodrigo Gabriel Ferreira Soares
Gledson Luiz Pontes de Almeida
Taize Calvacante Santana
Marcos Vinícius da Silva
author_facet Maria de Fátima Araújo Alves
Héliton Pandorfi
Rodrigo Gabriel Ferreira Soares
Gledson Luiz Pontes de Almeida
Taize Calvacante Santana
Marcos Vinícius da Silva
author_sort Maria de Fátima Araújo Alves
collection DOAJ
description Heat stress stands out as one of the main elements linked to concerns related to animal thermal comfort. This research aims to develop a sequential methodology for the extraction of automatic characteristics from thermal images and the classification of heat stress in pigs by means of machine learning. Infrared images were obtained from 18 pigs housed in air-conditioned and non-air-conditioned pens. The image analysis consisted of its pre-processing, followed by color segmentation to isolate the region of interest and later the extraction of the animal’s surface temperatures, from a developed algorithm and later the recognition of the comfort pattern through machine learning. The results indicated that the automated color segmentation method was able to identify the region of interest with an average accuracy of 88% and the temperature extraction differed from the Therma Cam program by 0.82 °C. Using a Vector Support Machine (SVM), the research achieved an accuracy rate of 80% in the automatic classification of pigs in comfort and thermal discomfort, with an accuracy of 91%, indicating that the proposal has the potential to monitor and evaluate the thermal comfort of pigs effectively.
format Article
id doaj-art-a80d080ab0dd4a52938de589b7fee64f
institution OA Journals
issn 2624-7402
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series AgriEngineering
spelling doaj-art-a80d080ab0dd4a52938de589b7fee64f2025-08-20T01:56:09ZengMDPI AGAgriEngineering2624-74022024-09-01633203322610.3390/agriengineering6030183Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing EnvironmentMaria de Fátima Araújo Alves0Héliton Pandorfi1Rodrigo Gabriel Ferreira Soares2Gledson Luiz Pontes de Almeida3Taize Calvacante Santana4Marcos Vinícius da Silva5Department of Agricultural Engineering, Federal Rural University of Pernambuco, Recife 52171-900, PE, BrazilDepartment of Agricultural Engineering, Federal Rural University of Pernambuco, Recife 52171-900, PE, BrazilDepartment of Statistics and Computer Science, Federal Rural University of Pernambuco, Recife 52171-900, PE, BrazilDepartment of Agricultural Engineering, Federal Rural University of Pernambuco, Recife 52171-900, PE, BrazilDepartment of Agricultural Engineering, Federal Rural University of Pernambuco, Recife 52171-900, PE, BrazilPrograma de Pós-Graduação em Ciências Florestais, Universidade Federal de Campina Grande, Av. Universitária, s/n, Santa Cecília, Patos 58708-110, PB, BrazilHeat stress stands out as one of the main elements linked to concerns related to animal thermal comfort. This research aims to develop a sequential methodology for the extraction of automatic characteristics from thermal images and the classification of heat stress in pigs by means of machine learning. Infrared images were obtained from 18 pigs housed in air-conditioned and non-air-conditioned pens. The image analysis consisted of its pre-processing, followed by color segmentation to isolate the region of interest and later the extraction of the animal’s surface temperatures, from a developed algorithm and later the recognition of the comfort pattern through machine learning. The results indicated that the automated color segmentation method was able to identify the region of interest with an average accuracy of 88% and the temperature extraction differed from the Therma Cam program by 0.82 °C. Using a Vector Support Machine (SVM), the research achieved an accuracy rate of 80% in the automatic classification of pigs in comfort and thermal discomfort, with an accuracy of 91%, indicating that the proposal has the potential to monitor and evaluate the thermal comfort of pigs effectively.https://www.mdpi.com/2624-7402/6/3/183machine learninganimal welfarethermal monitoringinfrared thermography
spellingShingle Maria de Fátima Araújo Alves
Héliton Pandorfi
Rodrigo Gabriel Ferreira Soares
Gledson Luiz Pontes de Almeida
Taize Calvacante Santana
Marcos Vinícius da Silva
Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
AgriEngineering
machine learning
animal welfare
thermal monitoring
infrared thermography
title Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
title_full Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
title_fullStr Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
title_full_unstemmed Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
title_short Computational Techniques for Analysis of Thermal Images of Pigs and Characterization of Heat Stress in the Rearing Environment
title_sort computational techniques for analysis of thermal images of pigs and characterization of heat stress in the rearing environment
topic machine learning
animal welfare
thermal monitoring
infrared thermography
url https://www.mdpi.com/2624-7402/6/3/183
work_keys_str_mv AT mariadefatimaaraujoalves computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment
AT helitonpandorfi computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment
AT rodrigogabrielferreirasoares computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment
AT gledsonluizpontesdealmeida computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment
AT taizecalvacantesantana computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment
AT marcosviniciusdasilva computationaltechniquesforanalysisofthermalimagesofpigsandcharacterizationofheatstressintherearingenvironment