Computer vision-based approaches to cattle identification: A comparative evaluation of body texture, QR code, and numerical labelling

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12220%2F25%3A43910480" target="_blank" >RIV/60076658:12220/25:43910480 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/60076658:12410/25:43910480

Výsledek na webu

<a href="https://cjas.agriculturejournals.cz/artkey/cjs-202509-0001_computer-vision-based-approaches-to-cattle-identification-a-comparative-evaluation-of-body-texture-qr-code-a.php" target="_blank" >https://cjas.agriculturejournals.cz/artkey/cjs-202509-0001_computer-vision-based-approaches-to-cattle-identification-a-comparative-evaluation-of-body-texture-qr-code-a.php</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.17221/66/2025-CJAS" target="_blank" >10.17221/66/2025-CJAS</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Computer vision-based approaches to cattle identification: A comparative evaluation of body texture, QR code, and numerical labelling

Popis výsledku v původním jazyce

Cattle identification systems are advancing to meet the growing demands of precision livestock management, traceability, and ethical animal treatment. This study investigates three methods: body texture recognition, QR code collars, and numerical labelling, implemented using the YOLOv8 convolutional neural network. Each method was evaluated in terms of accuracy, scalability, adaptability to dynamic herd changes, and operational efficiency under various environmental conditions. Body texture recognition, while leveraging unique natural patterns and achieving a mean Average Precision (mAP50-95) of 0.78 proved limited by its reliance on frequent dataset retraining to accommodate changes in herd composition and susceptibility to misidentification in larger herds. QR code collars demonstrated adaptability in dynamic herds by enabling pre-trained convolutional neural networks to assign reserved codes to new animals without retraining, while removing animals involves simply deleting their codes from the system. This approach also achieved an mAP50-95 of 0.71, which was lower than the body texture-based approach, but offered greater flexibility in herd management. Despite this adaptability, this method demonstrated significant challenges in real-world environments. Occlusion caused by feeders, barriers, or animal movements, along with low-resolution imaging and poor lighting conditions, can compromise detection accuracy, particularly in larger herds with obstructive barn layouts. The numerical labelling method emerged as the most effective solution to dynamic cattle identification, achieving the highest mAP50-95 of 0.84. It provided a scalable and highly accurate approach that integrates seamlessly with automated systems. Unlike traditional body marking techniques such as ear notching and branding, numerical labelling is less invasive, painless, and highly scalable, aligning with ethical livestock management practices while maintaining consistent accuracy across diverse environmental conditions.

Název v anglickém jazyce

Computer vision-based approaches to cattle identification: A comparative evaluation of body texture, QR code, and numerical labelling

Popis výsledku anglicky

Cattle identification systems are advancing to meet the growing demands of precision livestock management, traceability, and ethical animal treatment. This study investigates three methods: body texture recognition, QR code collars, and numerical labelling, implemented using the YOLOv8 convolutional neural network. Each method was evaluated in terms of accuracy, scalability, adaptability to dynamic herd changes, and operational efficiency under various environmental conditions. Body texture recognition, while leveraging unique natural patterns and achieving a mean Average Precision (mAP50-95) of 0.78 proved limited by its reliance on frequent dataset retraining to accommodate changes in herd composition and susceptibility to misidentification in larger herds. QR code collars demonstrated adaptability in dynamic herds by enabling pre-trained convolutional neural networks to assign reserved codes to new animals without retraining, while removing animals involves simply deleting their codes from the system. This approach also achieved an mAP50-95 of 0.71, which was lower than the body texture-based approach, but offered greater flexibility in herd management. Despite this adaptability, this method demonstrated significant challenges in real-world environments. Occlusion caused by feeders, barriers, or animal movements, along with low-resolution imaging and poor lighting conditions, can compromise detection accuracy, particularly in larger herds with obstructive barn layouts. The numerical labelling method emerged as the most effective solution to dynamic cattle identification, achieving the highest mAP50-95 of 0.84. It provided a scalable and highly accurate approach that integrates seamlessly with automated systems. Unlike traditional body marking techniques such as ear notching and branding, numerical labelling is less invasive, painless, and highly scalable, aligning with ethical livestock management practices while maintaining consistent accuracy across diverse environmental conditions.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

Czech Journal of Animal Science : Živočišná výroba

ISSN

1212-1819

e-ISSN

1805-9309

Svazek periodika

70

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

14

Strana od-do

383-396

Kód UT WoS článku

001587077800002

EID výsledku v databázi Scopus

2-s2.0-105018332763