Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs

Abstract Timely and accurate detection of ear tag dropout is crucial for standardized precision breeding, health monitoring, and breeding evaluation. Reserve breeding pigs exhibit high activity levels and frequent interactions, leading to a higher prevalence of ear tag dropout. However, detection is...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijun Duan, Fang Wang, Xueliang Fu, Honghui Li, Buyu Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-09679-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849237871165177856
author Weijun Duan
Fang Wang
Xueliang Fu
Honghui Li
Buyu Wang
author_facet Weijun Duan
Fang Wang
Xueliang Fu
Honghui Li
Buyu Wang
author_sort Weijun Duan
collection DOAJ
description Abstract Timely and accurate detection of ear tag dropout is crucial for standardized precision breeding, health monitoring, and breeding evaluation. Reserve breeding pigs exhibit high activity levels and frequent interactions, leading to a higher prevalence of ear tag dropout. However, detection is challenging due to motion blur, small tag size, and significant target scale variations. To address this, we propose a motion blur-aware multi-scale framework, Adapt-Cascade. First, a Weight-Adaptive Attention Module (WAAM) enhances the extraction of motion blur features. Second, Density-Aware Dilated Convolution (DA-DC) dynamically adjusts the convolutional receptive field to improve small ear tag detection. Third, a Feature-Guided Multi-Scale Region Proposal strategy (FGMS-RP) strengthens multi-scale target detection. Integrated into the Cascade Mask R-CNN framework with Focal Loss, Adapt-Cascade achieves 93.46% accuracy at 19.2 frames per second in detecting ear tag dropout in reserve breeding pigs. This model provides a high-accuracy solution for intelligent pig farm management.
format Article
id doaj-art-a95afb98cd1e48908d8f171eb71948c0
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a95afb98cd1e48908d8f171eb71948c02025-08-20T04:01:51ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-09679-4Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigsWeijun Duan0Fang Wang1Xueliang Fu2Honghui Li3Buyu Wang4College of Computer and Information Engineering, Inner Mongolia Agricultural UniversityCollege of Computer and Information Engineering, Inner Mongolia Agricultural UniversityCollege of Computer and Information Engineering, Inner Mongolia Agricultural UniversityCollege of Computer and Information Engineering, Inner Mongolia Agricultural UniversityCollege of Computer and Information Engineering, Inner Mongolia Agricultural UniversityAbstract Timely and accurate detection of ear tag dropout is crucial for standardized precision breeding, health monitoring, and breeding evaluation. Reserve breeding pigs exhibit high activity levels and frequent interactions, leading to a higher prevalence of ear tag dropout. However, detection is challenging due to motion blur, small tag size, and significant target scale variations. To address this, we propose a motion blur-aware multi-scale framework, Adapt-Cascade. First, a Weight-Adaptive Attention Module (WAAM) enhances the extraction of motion blur features. Second, Density-Aware Dilated Convolution (DA-DC) dynamically adjusts the convolutional receptive field to improve small ear tag detection. Third, a Feature-Guided Multi-Scale Region Proposal strategy (FGMS-RP) strengthens multi-scale target detection. Integrated into the Cascade Mask R-CNN framework with Focal Loss, Adapt-Cascade achieves 93.46% accuracy at 19.2 frames per second in detecting ear tag dropout in reserve breeding pigs. This model provides a high-accuracy solution for intelligent pig farm management.https://doi.org/10.1038/s41598-025-09679-4Adapt-CascadeEar tag dropoutMotion blur adaptationMulti-scale detectionReserve breeding pigs
spellingShingle Weijun Duan
Fang Wang
Xueliang Fu
Honghui Li
Buyu Wang
Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
Scientific Reports
Adapt-Cascade
Ear tag dropout
Motion blur adaptation
Multi-scale detection
Reserve breeding pigs
title Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
title_full Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
title_fullStr Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
title_full_unstemmed Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
title_short Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
title_sort motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs
topic Adapt-Cascade
Ear tag dropout
Motion blur adaptation
Multi-scale detection
Reserve breeding pigs
url https://doi.org/10.1038/s41598-025-09679-4
work_keys_str_mv AT weijunduan motionblurawaremultiscaleadaptivecascadeframeworkforeartagdropoutdetectioninreservebreedingpigs
AT fangwang motionblurawaremultiscaleadaptivecascadeframeworkforeartagdropoutdetectioninreservebreedingpigs
AT xueliangfu motionblurawaremultiscaleadaptivecascadeframeworkforeartagdropoutdetectioninreservebreedingpigs
AT honghuili motionblurawaremultiscaleadaptivecascadeframeworkforeartagdropoutdetectioninreservebreedingpigs
AT buyuwang motionblurawaremultiscaleadaptivecascadeframeworkforeartagdropoutdetectioninreservebreedingpigs