Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy

Abstract Pest management is essential for agricultural production and food security, as pests can cause significant crop losses and economic impact. Early pest detection is key to timely intervention. While object detection models perform well on various datasets, they assume i.i.d. data, which is o...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Fu, Shiyu Wang, Mingqiu Dong, Hao Sun, Mohammed Abdulhakim Al-Absi, Kaijie Zhang, Qian Chen, Liqun Xiao, Xuewei Wang, Ye Li
Format: Article
Language:English
Published: BMC 2025-04-01
Series:Plant Methods
Subjects:
Online Access:https://doi.org/10.1186/s13007-025-01371-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713534251827200
author Rui Fu
Shiyu Wang
Mingqiu Dong
Hao Sun
Mohammed Abdulhakim Al-Absi
Kaijie Zhang
Qian Chen
Liqun Xiao
Xuewei Wang
Ye Li
author_facet Rui Fu
Shiyu Wang
Mingqiu Dong
Hao Sun
Mohammed Abdulhakim Al-Absi
Kaijie Zhang
Qian Chen
Liqun Xiao
Xuewei Wang
Ye Li
author_sort Rui Fu
collection DOAJ
description Abstract Pest management is essential for agricultural production and food security, as pests can cause significant crop losses and economic impact. Early pest detection is key to timely intervention. While object detection models perform well on various datasets, they assume i.i.d. data, which is often not the case in diverse real-world environments, leading to decreased accuracy. To solve the problem, we propose the CrossDomain-PestDetect (CDPD) method, which is based on the YOLOv9 model and incorporates a test-time adaptation (TTA) framework. CDPD includes Dynamic Data Augmentation (DynamicDA), a Dynamic Adaptive Gate (DAG), and a Multi-Task Dynamic Adaptation Model (MT-DAM). Our DynamicDA enhances images for each batch by combining strong and weak augmentations. The MT-DAM integrates an object detection model with an image segmentation model, exchanging information through feature fusion at the feature extraction layer. During testing, test-time adaptation updates both models, continuing feature fusion during forward propagation. DAG adaptively controls the degree of feature fusion to improve detection capabilities. Self-supervised learning enables the model to adapt during testing to changing environments. Experiments show that without test-time adaptation, our method achieved a 7.6% increase in mAP50 over the baseline in the original environment and a 16.1% increase in the target environment. Finally, with test-time adaptation, the mAP50 score in the unseen target environment reaches 73.8%, which is a significant improvement over the baseline.
format Article
id doaj-art-4ef51c53cb5b49d290f540063a56ef88
institution DOAJ
issn 1746-4811
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series Plant Methods
spelling doaj-art-4ef51c53cb5b49d290f540063a56ef882025-08-20T03:13:57ZengBMCPlant Methods1746-48112025-04-0121112310.1186/s13007-025-01371-yPest detection in dynamic environments: an adaptive continual test-time domain adaptation strategyRui Fu0Shiyu Wang1Mingqiu Dong2Hao Sun3Mohammed Abdulhakim Al-Absi4Kaijie Zhang5Qian Chen6Liqun Xiao7Xuewei Wang8Ye Li9Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologyShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologyBeijing Institute of TechnologyShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologyDepartment of Smart Computing, Kyungdong UniversityShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologySichuan Technology and Business UniversitySouthwest Jiaotong UniversityShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologyShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and TechnologyAbstract Pest management is essential for agricultural production and food security, as pests can cause significant crop losses and economic impact. Early pest detection is key to timely intervention. While object detection models perform well on various datasets, they assume i.i.d. data, which is often not the case in diverse real-world environments, leading to decreased accuracy. To solve the problem, we propose the CrossDomain-PestDetect (CDPD) method, which is based on the YOLOv9 model and incorporates a test-time adaptation (TTA) framework. CDPD includes Dynamic Data Augmentation (DynamicDA), a Dynamic Adaptive Gate (DAG), and a Multi-Task Dynamic Adaptation Model (MT-DAM). Our DynamicDA enhances images for each batch by combining strong and weak augmentations. The MT-DAM integrates an object detection model with an image segmentation model, exchanging information through feature fusion at the feature extraction layer. During testing, test-time adaptation updates both models, continuing feature fusion during forward propagation. DAG adaptively controls the degree of feature fusion to improve detection capabilities. Self-supervised learning enables the model to adapt during testing to changing environments. Experiments show that without test-time adaptation, our method achieved a 7.6% increase in mAP50 over the baseline in the original environment and a 16.1% increase in the target environment. Finally, with test-time adaptation, the mAP50 score in the unseen target environment reaches 73.8%, which is a significant improvement over the baseline.https://doi.org/10.1186/s13007-025-01371-yPest detectionUnseen environmentDomain adaptationTest-time adaptationSelf-supervised learning
spellingShingle Rui Fu
Shiyu Wang
Mingqiu Dong
Hao Sun
Mohammed Abdulhakim Al-Absi
Kaijie Zhang
Qian Chen
Liqun Xiao
Xuewei Wang
Ye Li
Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
Plant Methods
Pest detection
Unseen environment
Domain adaptation
Test-time adaptation
Self-supervised learning
title Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
title_full Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
title_fullStr Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
title_full_unstemmed Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
title_short Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
title_sort pest detection in dynamic environments an adaptive continual test time domain adaptation strategy
topic Pest detection
Unseen environment
Domain adaptation
Test-time adaptation
Self-supervised learning
url https://doi.org/10.1186/s13007-025-01371-y
work_keys_str_mv AT ruifu pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT shiyuwang pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT mingqiudong pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT haosun pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT mohammedabdulhakimalabsi pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT kaijiezhang pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT qianchen pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT liqunxiao pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT xueweiwang pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy
AT yeli pestdetectionindynamicenvironmentsanadaptivecontinualtesttimedomainadaptationstrategy