High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion

IntroductionAphids are significant agricultural pests and vectors of plant viruses. Their Honeydew Excretion(HE) behavior holds critical importance for investigating feeding activities and evaluating plant resistance levels. Addressing the challenges of suboptimal efficiency, inadequate real-time ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongqiang Song, Jiahao Shen, Qiaoyi Liu, Wanyue Zhang, Ziqian Ren, Kaiwen Yang, Xinle Li, Jialei Liu, Fengming Yan, Wenqiang Li, Yuqing Xing, Lili Wu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1609222/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089406078124032
author Zhongqiang Song
Jiahao Shen
Qiaoyi Liu
Wanyue Zhang
Ziqian Ren
Kaiwen Yang
Xinle Li
Jialei Liu
Fengming Yan
Wenqiang Li
Yuqing Xing
Lili Wu
author_facet Zhongqiang Song
Jiahao Shen
Qiaoyi Liu
Wanyue Zhang
Ziqian Ren
Kaiwen Yang
Xinle Li
Jialei Liu
Fengming Yan
Wenqiang Li
Yuqing Xing
Lili Wu
author_sort Zhongqiang Song
collection DOAJ
description IntroductionAphids are significant agricultural pests and vectors of plant viruses. Their Honeydew Excretion(HE) behavior holds critical importance for investigating feeding activities and evaluating plant resistance levels. Addressing the challenges of suboptimal efficiency, inadequate real-time capability, and cumbersome operational procedures inherent in conventional manual and chemical detection methodologies, this research introduces an end-to-end multi-target behavior detection framework. This framework integrates spatiotemporal motion features with deep learning architectures to enhance detection accuracy and operational efficacy.MethodsThis study established the first fine-grained dataset encompassing aphid Crawling Locomotion(CL), Leg Flicking(LF), and HE behaviors, offering standardized samples for algorithm training. A rapid adaptive motion feature fusion algorithm was developed to accurately extract high-granularity spatiotemporal motion features. Simultaneously, the RT-DETR detection model underwent deep optimization: a spline-based adaptive nonlinear activation function was introduced, and the Kolmogorov-Arnold network was integrated into the deep feature stage of the ResNet50 backbone network to form the RK50 module. These modifications enhanced the model’s capability to capture complex spatial relationships and subtle features.Results and discussionExperimental results demonstrated that the proposed framework achieved an average precision of 85.9%. Compared with the model excluding the RK50 module, the mAP50 improved by 2.9%, and its performance in detecting small-target honeydew significantly surpassed mainstream algorithms. This study presents an innovative solution for automated monitoring of aphids’ fine-grained behaviors and provides a reference for insect behavior recognition research. The datasets, codes, and model weights were made available on GitHub (https://github.com/kuieless/RAMF-Aphid-Honeydew-Excretion-Behavior-Recognition).
format Article
id doaj-art-f00a7ea86a9d43859cafea8eba92afdf
institution DOAJ
issn 1664-462X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-f00a7ea86a9d43859cafea8eba92afdf2025-08-20T02:42:46ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-07-011610.3389/fpls.2025.16092221609222High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusionZhongqiang Song0Jiahao Shen1Qiaoyi Liu2Wanyue Zhang3Ziqian Ren4Kaiwen Yang5Xinle Li6Jialei Liu7Fengming Yan8Wenqiang Li9Yuqing Xing10Lili Wu11College of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Computing, City University of Hong Kong, Hong Kong SAR, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Plant Protection, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Plant Protection, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Science, Henan Agricultural University, Zhengzhou, Henan, ChinaIntroductionAphids are significant agricultural pests and vectors of plant viruses. Their Honeydew Excretion(HE) behavior holds critical importance for investigating feeding activities and evaluating plant resistance levels. Addressing the challenges of suboptimal efficiency, inadequate real-time capability, and cumbersome operational procedures inherent in conventional manual and chemical detection methodologies, this research introduces an end-to-end multi-target behavior detection framework. This framework integrates spatiotemporal motion features with deep learning architectures to enhance detection accuracy and operational efficacy.MethodsThis study established the first fine-grained dataset encompassing aphid Crawling Locomotion(CL), Leg Flicking(LF), and HE behaviors, offering standardized samples for algorithm training. A rapid adaptive motion feature fusion algorithm was developed to accurately extract high-granularity spatiotemporal motion features. Simultaneously, the RT-DETR detection model underwent deep optimization: a spline-based adaptive nonlinear activation function was introduced, and the Kolmogorov-Arnold network was integrated into the deep feature stage of the ResNet50 backbone network to form the RK50 module. These modifications enhanced the model’s capability to capture complex spatial relationships and subtle features.Results and discussionExperimental results demonstrated that the proposed framework achieved an average precision of 85.9%. Compared with the model excluding the RK50 module, the mAP50 improved by 2.9%, and its performance in detecting small-target honeydew significantly surpassed mainstream algorithms. This study presents an innovative solution for automated monitoring of aphids’ fine-grained behaviors and provides a reference for insect behavior recognition research. The datasets, codes, and model weights were made available on GitHub (https://github.com/kuieless/RAMF-Aphid-Honeydew-Excretion-Behavior-Recognition).https://www.frontiersin.org/articles/10.3389/fpls.2025.1609222/fullhoneydew excretion detectionaphid behavior recognitionrapid adaptive motion feature fusionKolmogorov-Arnold networksRT-DETR-RK50
spellingShingle Zhongqiang Song
Jiahao Shen
Qiaoyi Liu
Wanyue Zhang
Ziqian Ren
Kaiwen Yang
Xinle Li
Jialei Liu
Fengming Yan
Wenqiang Li
Yuqing Xing
Lili Wu
High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
Frontiers in Plant Science
honeydew excretion detection
aphid behavior recognition
rapid adaptive motion feature fusion
Kolmogorov-Arnold networks
RT-DETR-RK50
title High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
title_full High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
title_fullStr High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
title_full_unstemmed High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
title_short High-throughput end-to-end aphid honeydew excretion behavior recognition method based on rapid adaptive motion-feature fusion
title_sort high throughput end to end aphid honeydew excretion behavior recognition method based on rapid adaptive motion feature fusion
topic honeydew excretion detection
aphid behavior recognition
rapid adaptive motion feature fusion
Kolmogorov-Arnold networks
RT-DETR-RK50
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1609222/full
work_keys_str_mv AT zhongqiangsong highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT jiahaoshen highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT qiaoyiliu highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT wanyuezhang highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT ziqianren highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT kaiwenyang highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT xinleli highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT jialeiliu highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT fengmingyan highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT wenqiangli highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT yuqingxing highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion
AT liliwu highthroughputendtoendaphidhoneydewexcretionbehaviorrecognitionmethodbasedonrapidadaptivemotionfeaturefusion