Flock behaviour analysis using computer vision and deep learning techniques on egg farms

Luo, Zhen

Flock behaviour analysis using computer vision and deep learning techniques on egg farms

Luo, Zhen

Permalink

Publication Type:: Thesis
Issue Date:: 2026

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (7.84 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Luo, Zhen
dc.date.accessioned	2026-11-02T02:58:40Z
dc.date.available	2026-11-02T02:58:40Z
dc.date.issued	2026
dc.identifier.uri	http://hdl.handle.net/10453/197290
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	This thesis investigates the use of deep learning and computer vision techniques for automated monitoring of laying hen behaviour in commercial egg farms. Laying hen behaviour is an important indicator of animal welfare, health, and productivity; however, traditional monitoring methods are labour-intensive, subjective, and difficult to scale in large commercial environments. To address these challenges, this research develops a real-time, non-invasive monitoring framework capable of detecting and analysing eating, drinking, and other flock behaviours under practical farm conditions. A key contribution of this work is the development of ChickenbehaviourView, the first top-down multi-task chicken behaviour dataset, containing 16,991 annotated instances collected from commercial egg farms in Australia. The dataset supports behaviour detection, tracking, and quantitative analysis. State-of-the-art detection and tracking models were evaluated and integrated into a prototype monitoring system capable of generating hourly and daily behavioural statistics. Environmental data, including shed temperature, were incorporated to analyse behavioural trends and welfare-related changes. The proposed framework demonstrates the feasibility of scalable, automated poultry monitoring and contributes practical tools for precision livestock farming and welfare-focused poultry production.	en_US.UTF-8
dc.format	Thesis (MSc (CompSc))
dc.language.iso	en_US	en_US.UTF-8
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2026 Zhen Luo
dc.rights	au.edu.uts.lib/cph
dc.title	Flock behaviour analysis using computer vision and deep learning techniques on egg farms	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

This thesis investigates the use of deep learning and computer vision techniques for automated monitoring of laying hen behaviour in commercial egg farms. Laying hen behaviour is an important indicator of animal welfare, health, and productivity; however, traditional monitoring methods are labour-intensive, subjective, and difficult to scale in large commercial environments. To address these challenges, this research develops a real-time, non-invasive monitoring framework capable of detecting and analysing eating, drinking, and other flock behaviours under practical farm conditions. A key contribution of this work is the development of ChickenbehaviourView, the first top-down multi-task chicken behaviour dataset, containing 16,991 annotated instances collected from commercial egg farms in Australia. The dataset supports behaviour detection, tracking, and quantitative analysis. State-of-the-art detection and tracking models were evaluated and integrated into a prototype monitoring system capable of generating hourly and daily behavioural statistics. Environmental data, including shed temperature, were incorporated to analyse behavioural trends and welfare-related changes. The proposed framework demonstrates the feasibility of scalable, automated poultry monitoring and contributes practical tools for precision livestock farming and welfare-focused poultry production.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/197290