Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study

As a crucial characteristic waterfowl breed, the egg-laying performance of Lion-Headed Geese serves as a core indicator for precision breeding. Under large-scale flat rearing and selection practices, high phenotypic similarity among individuals within the same pedigree coupled with traditional manua...

Full description

Saved in:
Bibliographic Details
Main Authors: Hengyuan Zhang, Zhenlong Wu, Tiemin Zhang, Canhuan Lu, Zhaohui Zhang, Jianzhou Ye, Jikang Yang, Degui Yang, Cheng Fang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/13/1345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849429343931990016
author Hengyuan Zhang
Zhenlong Wu
Tiemin Zhang
Canhuan Lu
Zhaohui Zhang
Jianzhou Ye
Jikang Yang
Degui Yang
Cheng Fang
author_facet Hengyuan Zhang
Zhenlong Wu
Tiemin Zhang
Canhuan Lu
Zhaohui Zhang
Jianzhou Ye
Jikang Yang
Degui Yang
Cheng Fang
author_sort Hengyuan Zhang
collection DOAJ
description As a crucial characteristic waterfowl breed, the egg-laying performance of Lion-Headed Geese serves as a core indicator for precision breeding. Under large-scale flat rearing and selection practices, high phenotypic similarity among individuals within the same pedigree coupled with traditional manual observation and existing automation systems relying on fixed nesting boxes or RFID tags has posed challenges in achieving accurate goose–egg matching in dynamic environments, leading to inefficient individual selection. To address this, this study proposes YOLO-Goose, an improved YOLOv8s-based method, which designs five high-contrast neck rings (DoubleBar, Circle, Dot, Fence, Cylindrical) as individual identifiers. The method constructs a lightweight model with a small-object detection layer, integrates the GhostNet backbone to reduce parameter count by 67.2%, and employs the GIoU loss function to optimize neck ring localization accuracy. Experimental results show that the model achieves an <i>F1 score</i> of 93.8% and <i>mAP50</i> of 96.4% on the self-built dataset, representing increases of 10.1% and 5% compared to the original YOLOv8s, with a 27.1% reduction in computational load. The dynamic matching algorithm, incorporating spatiotemporal trajectories and egg positional data, achieves a 95% matching rate, a 94.7% matching accuracy, and a 5.3% mismatching rate. Through lightweight deployment using TensorRT, the inference speed is enhanced by 1.4 times compared to PyTorch-1.12.1, with detection results uploaded to a cloud database in real time. This solution overcomes the technical bottleneck of individual selection in flat rearing environments, providing an innovative computer-vision-based approach for precision breeding of pedigree Lion-Headed Geese and offering significant engineering value for advancing intelligent waterfowl breeding.
format Article
id doaj-art-1dedb97a282c4119a3d427b1be45eff7
institution Kabale University
issn 2077-0472
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-1dedb97a282c4119a3d427b1be45eff72025-08-20T03:28:24ZengMDPI AGAgriculture2077-04722025-06-011513134510.3390/agriculture15131345Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental StudyHengyuan Zhang0Zhenlong Wu1Tiemin Zhang2Canhuan Lu3Zhaohui Zhang4Jianzhou Ye5Jikang Yang6Degui Yang7Cheng Fang8Guangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaAs a crucial characteristic waterfowl breed, the egg-laying performance of Lion-Headed Geese serves as a core indicator for precision breeding. Under large-scale flat rearing and selection practices, high phenotypic similarity among individuals within the same pedigree coupled with traditional manual observation and existing automation systems relying on fixed nesting boxes or RFID tags has posed challenges in achieving accurate goose–egg matching in dynamic environments, leading to inefficient individual selection. To address this, this study proposes YOLO-Goose, an improved YOLOv8s-based method, which designs five high-contrast neck rings (DoubleBar, Circle, Dot, Fence, Cylindrical) as individual identifiers. The method constructs a lightweight model with a small-object detection layer, integrates the GhostNet backbone to reduce parameter count by 67.2%, and employs the GIoU loss function to optimize neck ring localization accuracy. Experimental results show that the model achieves an <i>F1 score</i> of 93.8% and <i>mAP50</i> of 96.4% on the self-built dataset, representing increases of 10.1% and 5% compared to the original YOLOv8s, with a 27.1% reduction in computational load. The dynamic matching algorithm, incorporating spatiotemporal trajectories and egg positional data, achieves a 95% matching rate, a 94.7% matching accuracy, and a 5.3% mismatching rate. Through lightweight deployment using TensorRT, the inference speed is enhanced by 1.4 times compared to PyTorch-1.12.1, with detection results uploaded to a cloud database in real time. This solution overcomes the technical bottleneck of individual selection in flat rearing environments, providing an innovative computer-vision-based approach for precision breeding of pedigree Lion-Headed Geese and offering significant engineering value for advancing intelligent waterfowl breeding.https://www.mdpi.com/2077-0472/15/13/1345Lion-Head Geeseobject detectioncomputer visionprecision livestock farminggoose egg identification and assignment
spellingShingle Hengyuan Zhang
Zhenlong Wu
Tiemin Zhang
Canhuan Lu
Zhaohui Zhang
Jianzhou Ye
Jikang Yang
Degui Yang
Cheng Fang
Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
Agriculture
Lion-Head Geese
object detection
computer vision
precision livestock farming
goose egg identification and assignment
title Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
title_full Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
title_fullStr Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
title_full_unstemmed Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
title_short Improved YOLO-Goose-Based Method for Individual Identification of Lion-Head Geese and Egg Matching: Methods and Experimental Study
title_sort improved yolo goose based method for individual identification of lion head geese and egg matching methods and experimental study
topic Lion-Head Geese
object detection
computer vision
precision livestock farming
goose egg identification and assignment
url https://www.mdpi.com/2077-0472/15/13/1345
work_keys_str_mv AT hengyuanzhang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT zhenlongwu improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT tieminzhang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT canhuanlu improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT zhaohuizhang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT jianzhouye improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT jikangyang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT deguiyang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy
AT chengfang improvedyologoosebasedmethodforindividualidentificationoflionheadgeeseandeggmatchingmethodsandexperimentalstudy