A CNN-Based Methodology for Cow Heat ...
Type de document :
Article dans une revue scientifique: Article original
Titre :
A CNN-Based Methodology for Cow Heat Analysis from Endoscopic Images
Auteur(s) :
He, Ruiwen [Auteur]
JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Benhabiles, Halim [Auteur]
JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Moulla Windal, Feryal [Auteur]
JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Even, Gaël [Auteur]
Gènes Diffusion [Douai]
Audebert, Christophe [Auteur]
Gènes Diffusion [Douai]
Decherf, Agathe [Auteur]
Collard, Dominique [Auteur]
JUNIA [JUNIA]
Laboratory for Integrated Micro Mechatronics Systems [LIMMS]
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Benhabiles, Halim [Auteur]

JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Moulla Windal, Feryal [Auteur]
JUNIA [JUNIA]
Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Even, Gaël [Auteur]
Gènes Diffusion [Douai]
Audebert, Christophe [Auteur]
Gènes Diffusion [Douai]
Decherf, Agathe [Auteur]
Collard, Dominique [Auteur]
JUNIA [JUNIA]
Laboratory for Integrated Micro Mechatronics Systems [LIMMS]
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Titre de la revue :
Applied Intelligence
Pagination :
pp 8372–8385
Éditeur :
Springer Verlag
Date de publication :
2022-06
ISSN :
0924-669X
Mot(s)-clé(s) en anglais :
Deep learning
Endoscopic image
Android CNN optimization
Cow heat
Artificial insemination
Endoscopic image
Android CNN optimization
Cow heat
Artificial insemination
Discipline(s) HAL :
Sciences de l'ingénieur [physics]
Résumé en anglais : [en]
In cattle farming, the artificial insemination technique is a biotechnology that brings to farmers a wide range of benefits namely health security, genetic gain and economic costs. The main condition for the success of ...
Lire la suite >In cattle farming, the artificial insemination technique is a biotechnology that brings to farmers a wide range of benefits namely health security, genetic gain and economic costs. The main condition for the success of artificial insemination within cattle is the heat (or estrus) detection. In this context, several cow heat detection systems have been recently proposed in the literature to assist the farmer in this task. Nevertheless, they are mainly based on the analysis of the physical behavior of the cow which may be affected by several factors related to its health and its environment. In this paper, we present a new vision system for cow heat detection which is based on the analysis of the genital tract of the cow. The main core of our system is a CNN model that has been designed and tailored for analyzing endoscopic images collected using an innovative insemination technology named Eye breed. The conducted experiments on two datasets namely our own dataset and a public dataset show the high accuracy of our CNN model (more than 97% for both datasets) outperforming 19 methods from the state of the art. Moreover, we propose an optimized version of our model for an Android deployment by exploiting several techniques namely quantization, GPU acceleration and video downsampling. The conducted tests on a smart-phone shows that our heat detection system has a response time of a few seconds.Lire moins >
Lire la suite >In cattle farming, the artificial insemination technique is a biotechnology that brings to farmers a wide range of benefits namely health security, genetic gain and economic costs. The main condition for the success of artificial insemination within cattle is the heat (or estrus) detection. In this context, several cow heat detection systems have been recently proposed in the literature to assist the farmer in this task. Nevertheless, they are mainly based on the analysis of the physical behavior of the cow which may be affected by several factors related to its health and its environment. In this paper, we present a new vision system for cow heat detection which is based on the analysis of the genital tract of the cow. The main core of our system is a CNN model that has been designed and tailored for analyzing endoscopic images collected using an innovative insemination technology named Eye breed. The conducted experiments on two datasets namely our own dataset and a public dataset show the high accuracy of our CNN model (more than 97% for both datasets) outperforming 19 methods from the state of the art. Moreover, we propose an optimized version of our model for an Android deployment by exploiting several techniques namely quantization, GPU acceleration and video downsampling. The conducted tests on a smart-phone shows that our heat detection system has a response time of a few seconds.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Source :