The estimation of broiler respiration rate based on the semantic segmentation and video amplification

Respiratory rate is an indicator of a broilers’ stress and health status, thus, it is essential to detect respiratory rate contactless and stress-freely. This study proposed an estimation method of broiler respiratory rate by deep learning and machine vision. Experiments were performed at New Hope (...

Full description

Bibliographic Details
Main Authors: Jintao Wang, Longshen Liu, Mingzhou Lu, Cedric Okinda, Daniela Lovarelli, Marcella Guarino, Mingxia Shen
Format: Article
Language:English
Published: Frontiers Media S.A. 2022-12-01
Series:Frontiers in Physics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2022.1047077/full
_version_ 1797979818998890496
author Jintao Wang
Jintao Wang
Longshen Liu
Mingzhou Lu
Cedric Okinda
Cedric Okinda
Daniela Lovarelli
Marcella Guarino
Mingxia Shen
author_facet Jintao Wang
Jintao Wang
Longshen Liu
Mingzhou Lu
Cedric Okinda
Cedric Okinda
Daniela Lovarelli
Marcella Guarino
Mingxia Shen
author_sort Jintao Wang
collection DOAJ
description Respiratory rate is an indicator of a broilers’ stress and health status, thus, it is essential to detect respiratory rate contactless and stress-freely. This study proposed an estimation method of broiler respiratory rate by deep learning and machine vision. Experiments were performed at New Hope (Shandong Province, P. R. China) and Wen’s group (Guangdong Province, P. R. China), and a total of 300 min of video data were collected. By separating video frames, a data set of 3,000 images was made, and two semantic segmentation models were trained. The single-channel Euler video magnification algorithm was used to amplify the belly fluctuation of the broiler, which saved 55% operation time compared with the traditional Eulerian video magnification algorithm. The contour features significantly related to respiration were used to obtain the signals that could estimate broilers’ respiratory rate. Detrending and band-pass filtering eliminated the influence of broiler posture conversion and motion on the signal. The mean absolute error, root mean square error, average accuracy of the proposed respiratory rate estimation technique for broilers were 3.72%, 16.92%, and 92.19%, respectively.
first_indexed 2024-04-11T05:45:55Z
format Article
id doaj.art-939689e5f90041d69def3bcddccba446
institution Directory Open Access Journal
issn 2296-424X
language English
last_indexed 2024-04-11T05:45:55Z
publishDate 2022-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physics
spelling doaj.art-939689e5f90041d69def3bcddccba4462022-12-22T04:42:15ZengFrontiers Media S.A.Frontiers in Physics2296-424X2022-12-011010.3389/fphy.2022.10470771047077The estimation of broiler respiration rate based on the semantic segmentation and video amplificationJintao Wang0Jintao Wang1Longshen Liu2Mingzhou Lu3Cedric Okinda4Cedric Okinda5Daniela Lovarelli6Marcella Guarino7Mingxia Shen8School of Mechanical and Power Engineering, Henan Polytechnic University, Jiaozuo, Henan, ChinaLaboratory of Modern Facility Agriculture Technology and Equipment Engineering of Jiangsu Province, College of Engineering, Nanjing Agricultural University, Nanjing, Jiangsu, ChinaLaboratory of Modern Facility Agriculture Technology and Equipment Engineering of Jiangsu Province, College of Engineering, Nanjing Agricultural University, Nanjing, Jiangsu, ChinaLaboratory of Modern Facility Agriculture Technology and Equipment Engineering of Jiangsu Province, College of Engineering, Nanjing Agricultural University, Nanjing, Jiangsu, ChinaLaboratory of Modern Facility Agriculture Technology and Equipment Engineering of Jiangsu Province, College of Engineering, Nanjing Agricultural University, Nanjing, Jiangsu, ChinaDepartment of Electrical and Communications Engineering, School of Engineering and Built Environment, Masinde Muliro University of Science and Technology, Kakamega, KenyaDepartment of Science and Environmental Policy, University of Milan, Milan, ItalyDepartment of Science and Environmental Policy, University of Milan, Milan, ItalyLaboratory of Modern Facility Agriculture Technology and Equipment Engineering of Jiangsu Province, College of Engineering, Nanjing Agricultural University, Nanjing, Jiangsu, ChinaRespiratory rate is an indicator of a broilers’ stress and health status, thus, it is essential to detect respiratory rate contactless and stress-freely. This study proposed an estimation method of broiler respiratory rate by deep learning and machine vision. Experiments were performed at New Hope (Shandong Province, P. R. China) and Wen’s group (Guangdong Province, P. R. China), and a total of 300 min of video data were collected. By separating video frames, a data set of 3,000 images was made, and two semantic segmentation models were trained. The single-channel Euler video magnification algorithm was used to amplify the belly fluctuation of the broiler, which saved 55% operation time compared with the traditional Eulerian video magnification algorithm. The contour features significantly related to respiration were used to obtain the signals that could estimate broilers’ respiratory rate. Detrending and band-pass filtering eliminated the influence of broiler posture conversion and motion on the signal. The mean absolute error, root mean square error, average accuracy of the proposed respiratory rate estimation technique for broilers were 3.72%, 16.92%, and 92.19%, respectively.https://www.frontiersin.org/articles/10.3389/fphy.2022.1047077/fullbroilerrespiration ratecomputer visionsemantic segmentationEuler video magnification
spellingShingle Jintao Wang
Jintao Wang
Longshen Liu
Mingzhou Lu
Cedric Okinda
Cedric Okinda
Daniela Lovarelli
Marcella Guarino
Mingxia Shen
The estimation of broiler respiration rate based on the semantic segmentation and video amplification
Frontiers in Physics
broiler
respiration rate
computer vision
semantic segmentation
Euler video magnification
title The estimation of broiler respiration rate based on the semantic segmentation and video amplification
title_full The estimation of broiler respiration rate based on the semantic segmentation and video amplification
title_fullStr The estimation of broiler respiration rate based on the semantic segmentation and video amplification
title_full_unstemmed The estimation of broiler respiration rate based on the semantic segmentation and video amplification
title_short The estimation of broiler respiration rate based on the semantic segmentation and video amplification
title_sort estimation of broiler respiration rate based on the semantic segmentation and video amplification
topic broiler
respiration rate
computer vision
semantic segmentation
Euler video magnification
url https://www.frontiersin.org/articles/10.3389/fphy.2022.1047077/full
work_keys_str_mv AT jintaowang theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT jintaowang theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT longshenliu theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT mingzhoulu theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT cedricokinda theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT cedricokinda theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT danielalovarelli theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT marcellaguarino theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT mingxiashen theestimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT jintaowang estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT jintaowang estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT longshenliu estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT mingzhoulu estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT cedricokinda estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT cedricokinda estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT danielalovarelli estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT marcellaguarino estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification
AT mingxiashen estimationofbroilerrespirationratebasedonthesemanticsegmentationandvideoamplification