Leveraging the potential of convolutional neural networks in poultry farming: a 5-year overview

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12410%2F25%3A43909783" target="_blank" >RIV/60076658:12410/25:43909783 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/60076658:12220/25:43909783

Výsledek na webu

<a href="https://www.tandfonline.com/doi/full/10.1080/00439339.2024.2440102" target="_blank" >https://www.tandfonline.com/doi/full/10.1080/00439339.2024.2440102</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1080/00439339.2024.2440102" target="_blank" >10.1080/00439339.2024.2440102</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Leveraging the potential of convolutional neural networks in poultry farming: a 5-year overview

Popis výsledku v původním jazyce

Modern animal farming is increasingly adopting Artificial Intelligence (AI) technologies, with Convolutional Neural Networks (CNN), a critical component of computer vision (CV) and deep learning playing a pivotal role in enhancing productivity, sustainability, and animal welfare. In poultry farming, a cornerstone of global agriculture that contributes significantly to the world&apos;s meat and egg supply, Convolutional Neural Networks have emerged as powerful tools in poultry management and health monitoring due to their proficiency in image and video analysis. Ensuring poultry health is essential for food safety, economic efficiency, and animal welfare. This study provides a comprehensive review of recent advancements and applications of CNN-based models in poultry health monitoring, covering disease detection, behaviour classification, and overall poultry management. We analysed 54 selected articles, categorising them into disease detection and classification, behaviour monitoring, and poultry detection, localisation, and tracking. The results highlight the high accuracy and efficiency of CNN models in early disease detection, identifying specific diseases, and monitoring behavioural changes, key factors for timely intervention and improved poultry welfare. Prominent models such as YOLO, Faster R-CNN, and ResNet are frequently used, showcasing their robustness across various tasks. The analysis indicates a global research effort, with significant contributions from countries like China and the USA. Despite notable progress, challenges remain, including the limited diversity of datasets, the need for non-invasive methods to monitor critical health indicators like body temperature and weight, and the integration of CNN with other AI-driven technologies. Overcoming these challenges through continued research and innovation is vital for advancing poultry health management and ensuring higher standards of productivity, sustainability, and welfare in the industry.

Název v anglickém jazyce

Leveraging the potential of convolutional neural networks in poultry farming: a 5-year overview

Popis výsledku anglicky

Modern animal farming is increasingly adopting Artificial Intelligence (AI) technologies, with Convolutional Neural Networks (CNN), a critical component of computer vision (CV) and deep learning playing a pivotal role in enhancing productivity, sustainability, and animal welfare. In poultry farming, a cornerstone of global agriculture that contributes significantly to the world&apos;s meat and egg supply, Convolutional Neural Networks have emerged as powerful tools in poultry management and health monitoring due to their proficiency in image and video analysis. Ensuring poultry health is essential for food safety, economic efficiency, and animal welfare. This study provides a comprehensive review of recent advancements and applications of CNN-based models in poultry health monitoring, covering disease detection, behaviour classification, and overall poultry management. We analysed 54 selected articles, categorising them into disease detection and classification, behaviour monitoring, and poultry detection, localisation, and tracking. The results highlight the high accuracy and efficiency of CNN models in early disease detection, identifying specific diseases, and monitoring behavioural changes, key factors for timely intervention and improved poultry welfare. Prominent models such as YOLO, Faster R-CNN, and ResNet are frequently used, showcasing their robustness across various tasks. The analysis indicates a global research effort, with significant contributions from countries like China and the USA. Despite notable progress, challenges remain, including the limited diversity of datasets, the need for non-invasive methods to monitor critical health indicators like body temperature and weight, and the integration of CNN with other AI-driven technologies. Overcoming these challenges through continued research and innovation is vital for advancing poultry health management and ensuring higher standards of productivity, sustainability, and welfare in the industry.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40201 - Animal and dairy science; (Animal biotechnology to be 4.4)

Projekt

<a href="/cs/project/TM04000023" target="_blank" >TM04000023: Výzkum a vývoj klíčových technologií pro chovy drůbeže – systém pro monitorování zvířat a prostředí a inteligentní management chovu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

WORLDS POULTRY SCIENCE JOURNAL

ISSN

0043-9339

e-ISSN

1743-4777

Svazek periodika

81

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

32

Strana od-do

3-34

Kód UT WoS článku

001391146400001

EID výsledku v databázi Scopus

2-s2.0-86000387071