BroilerTrack: Automatic multi-camera multi-broiler tracking

Efficient and continuous tracking of individual broilers is critical for improving poultry management, welfare, and breeding decisions in commercial settings. However, standard Multi-Object Tracking (MOT) techniques face significant challenges in poultry environments due to occlusions, high object s...

Full description

Saved in:
Bibliographic Details
Main Authors: Thinh Phan, Hoang Kim Tran, Andrew Lockett, Isaac Phillips, Hao Vo, Duy Le, Michael T. Kidd, James Mason, Santiago Avendano, Ngan Le
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S277237552500543X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228270902444032
author Thinh Phan
Hoang Kim Tran
Andrew Lockett
Isaac Phillips
Hao Vo
Duy Le
Michael T. Kidd
James Mason
Santiago Avendano
Ngan Le
author_facet Thinh Phan
Hoang Kim Tran
Andrew Lockett
Isaac Phillips
Hao Vo
Duy Le
Michael T. Kidd
James Mason
Santiago Avendano
Ngan Le
author_sort Thinh Phan
collection DOAJ
description Efficient and continuous tracking of individual broilers is critical for improving poultry management, welfare, and breeding decisions in commercial settings. However, standard Multi-Object Tracking (MOT) techniques face significant challenges in poultry environments due to occlusions, high object similarity, and dense flocks.In this work, we introduce BroilerTrack, a novel multi-camera multi-broiler tracking framework tailored for the poultry industry. Unlike traditional approaches that rely heavily on appearance features, BroilerTrack employs a position-based tracking strategy in a unified coordinate system (unified plane), thereby circumventing identity ambiguity caused by the homogeneous appearance of broilers. Our proposed BroilerTrack system comprises three key modules: Top-view Aggregation, Side-view Distribution, and Identification Assignment, enabling robust identification (ID) consistency across multiple calibrated views. Furthermore, we present a new Multi-View Broiler dataset collected under commercial-like conditions, featuring synchronized footage from six strategically placed cameras (two top-view and four side-view). Notably, our method requires no unified-plane annotations during training and achieves superior performance over state-of-the-art Multi-camera MOT methods on both detection and association metrics. This work provides a scalable, non-intrusive solution for real-time poultry monitoring, with strong potential for applications in behavior analysis, welfare optimization, and automated breeding selection.
format Article
id doaj-art-0611cbfbd4f24824b243b5236ca448d2
institution Kabale University
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-0611cbfbd4f24824b243b5236ca448d22025-08-23T04:49:51ZengElsevierSmart Agricultural Technology2772-37552025-12-011210131210.1016/j.atech.2025.101312BroilerTrack: Automatic multi-camera multi-broiler trackingThinh Phan0Hoang Kim Tran1Andrew Lockett2Isaac Phillips3Hao Vo4Duy Le5Michael T. Kidd6James Mason7Santiago Avendano8Ngan Le9Department of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United StatesDepartment of Poultry Science, University of Arkansas, Fayetteville, AR, United StatesAviagen, Huntsville, AL, United StatesAviagen, Huntsville, AL, United StatesDepartment of Electrical Engineering & Computer Science, University of Arkansas, Fayetteville, AR, United States; Corresponding author.Efficient and continuous tracking of individual broilers is critical for improving poultry management, welfare, and breeding decisions in commercial settings. However, standard Multi-Object Tracking (MOT) techniques face significant challenges in poultry environments due to occlusions, high object similarity, and dense flocks.In this work, we introduce BroilerTrack, a novel multi-camera multi-broiler tracking framework tailored for the poultry industry. Unlike traditional approaches that rely heavily on appearance features, BroilerTrack employs a position-based tracking strategy in a unified coordinate system (unified plane), thereby circumventing identity ambiguity caused by the homogeneous appearance of broilers. Our proposed BroilerTrack system comprises three key modules: Top-view Aggregation, Side-view Distribution, and Identification Assignment, enabling robust identification (ID) consistency across multiple calibrated views. Furthermore, we present a new Multi-View Broiler dataset collected under commercial-like conditions, featuring synchronized footage from six strategically placed cameras (two top-view and four side-view). Notably, our method requires no unified-plane annotations during training and achieves superior performance over state-of-the-art Multi-camera MOT methods on both detection and association metrics. This work provides a scalable, non-intrusive solution for real-time poultry monitoring, with strong potential for applications in behavior analysis, welfare optimization, and automated breeding selection.http://www.sciencedirect.com/science/article/pii/S277237552500543XMultiple broiler trackingMulti-camera multi-broiler trackingBroiler monitoringBroiler trackingBroiler detection
spellingShingle Thinh Phan
Hoang Kim Tran
Andrew Lockett
Isaac Phillips
Hao Vo
Duy Le
Michael T. Kidd
James Mason
Santiago Avendano
Ngan Le
BroilerTrack: Automatic multi-camera multi-broiler tracking
Smart Agricultural Technology
Multiple broiler tracking
Multi-camera multi-broiler tracking
Broiler monitoring
Broiler tracking
Broiler detection
title BroilerTrack: Automatic multi-camera multi-broiler tracking
title_full BroilerTrack: Automatic multi-camera multi-broiler tracking
title_fullStr BroilerTrack: Automatic multi-camera multi-broiler tracking
title_full_unstemmed BroilerTrack: Automatic multi-camera multi-broiler tracking
title_short BroilerTrack: Automatic multi-camera multi-broiler tracking
title_sort broilertrack automatic multi camera multi broiler tracking
topic Multiple broiler tracking
Multi-camera multi-broiler tracking
Broiler monitoring
Broiler tracking
Broiler detection
url http://www.sciencedirect.com/science/article/pii/S277237552500543X
work_keys_str_mv AT thinhphan broilertrackautomaticmulticameramultibroilertracking
AT hoangkimtran broilertrackautomaticmulticameramultibroilertracking
AT andrewlockett broilertrackautomaticmulticameramultibroilertracking
AT isaacphillips broilertrackautomaticmulticameramultibroilertracking
AT haovo broilertrackautomaticmulticameramultibroilertracking
AT duyle broilertrackautomaticmulticameramultibroilertracking
AT michaeltkidd broilertrackautomaticmulticameramultibroilertracking
AT jamesmason broilertrackautomaticmulticameramultibroilertracking
AT santiagoavendano broilertrackautomaticmulticameramultibroilertracking
AT nganle broilertrackautomaticmulticameramultibroilertracking