Corn-associated weed detection model based on WAAP-YOLO

To address the challenges of corn-associated weed detection, such as diverse shapes, dense occlusion, complex backgrounds and scale variation, an improved object detection model, WAAP-YOLO, was proposed. First, the backbone was improved by replacing some convolutions with wavelet pooling convolution...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyong MENG, Yawei JIA, Xiuqing ZHANG, Yongjing NI, Ming ZHANG, Qi WU, Chenxi WU
Format: Article
Language:zho
Published: Hebei University of Science and Technology 2025-08-01
Series:Journal of Hebei University of Science and Technology
Subjects:
Online Access:https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202504004?st=article_issue
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304138702127104
author Zhiyong MENG
Yawei JIA
Xiuqing ZHANG
Yongjing NI
Ming ZHANG
Qi WU
Chenxi WU
author_facet Zhiyong MENG
Yawei JIA
Xiuqing ZHANG
Yongjing NI
Ming ZHANG
Qi WU
Chenxi WU
author_sort Zhiyong MENG
collection DOAJ
description To address the challenges of corn-associated weed detection, such as diverse shapes, dense occlusion, complex backgrounds and scale variation, an improved object detection model, WAAP-YOLO, was proposed. First, the backbone was improved by replacing some convolutions with wavelet pooling convolutions, effectively avoiding aliasing artifacts. Second, an aggregated attention mechanism was introduced to construct the C2f-AA module, improving the model′s ability to extract weed features in complex backgrounds. Finally, ASF-P2-Net was proposed to replace the original neck network, incorporating the P2 detection head through the scale sequence fusion module, reducing model complexity and significantly improving small object detection performance. Experimental results show that the WAAP-YOLO detection algorithm achieves 97.2% mAP@0.5, 85.8% mAP@0.5∶0.95, 94.0% F1 score, and a parameter count of 2.1×106, outperforming common object detection models such as YOLOv5s, YOLOv8n, and YOLOv10n. The proposed model can significantly enhance cornfield weed recognition accuracy, which provides some reference for advancing the intelligent and sustainable development of the agricultural industry.
format Article
id doaj-art-d9d002c172f24b2788d89bc887eee3de
institution Kabale University
issn 1008-1542
language zho
publishDate 2025-08-01
publisher Hebei University of Science and Technology
record_format Article
series Journal of Hebei University of Science and Technology
spelling doaj-art-d9d002c172f24b2788d89bc887eee3de2025-08-20T03:55:48ZzhoHebei University of Science and TechnologyJournal of Hebei University of Science and Technology1008-15422025-08-0146438639410.7535/hbkd.2025yx04004b202504004Corn-associated weed detection model based on WAAP-YOLOZhiyong MENG0Yawei JIA1Xiuqing ZHANG2Yongjing NI3Ming ZHANG4Qi WU5Chenxi WU6School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei 050018, ChinaTo address the challenges of corn-associated weed detection, such as diverse shapes, dense occlusion, complex backgrounds and scale variation, an improved object detection model, WAAP-YOLO, was proposed. First, the backbone was improved by replacing some convolutions with wavelet pooling convolutions, effectively avoiding aliasing artifacts. Second, an aggregated attention mechanism was introduced to construct the C2f-AA module, improving the model′s ability to extract weed features in complex backgrounds. Finally, ASF-P2-Net was proposed to replace the original neck network, incorporating the P2 detection head through the scale sequence fusion module, reducing model complexity and significantly improving small object detection performance. Experimental results show that the WAAP-YOLO detection algorithm achieves 97.2% mAP@0.5, 85.8% mAP@0.5∶0.95, 94.0% F1 score, and a parameter count of 2.1×106, outperforming common object detection models such as YOLOv5s, YOLOv8n, and YOLOv10n. The proposed model can significantly enhance cornfield weed recognition accuracy, which provides some reference for advancing the intelligent and sustainable development of the agricultural industry.https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202504004?st=article_issuecomputer neural networks; weed recognition; wavelet pooling; attention mechanism; multi-scale fusion
spellingShingle Zhiyong MENG
Yawei JIA
Xiuqing ZHANG
Yongjing NI
Ming ZHANG
Qi WU
Chenxi WU
Corn-associated weed detection model based on WAAP-YOLO
Journal of Hebei University of Science and Technology
computer neural networks; weed recognition; wavelet pooling; attention mechanism; multi-scale fusion
title Corn-associated weed detection model based on WAAP-YOLO
title_full Corn-associated weed detection model based on WAAP-YOLO
title_fullStr Corn-associated weed detection model based on WAAP-YOLO
title_full_unstemmed Corn-associated weed detection model based on WAAP-YOLO
title_short Corn-associated weed detection model based on WAAP-YOLO
title_sort corn associated weed detection model based on waap yolo
topic computer neural networks; weed recognition; wavelet pooling; attention mechanism; multi-scale fusion
url https://xuebao.hebust.edu.cn/hbkjdx/article/pdf/b202504004?st=article_issue
work_keys_str_mv AT zhiyongmeng cornassociatedweeddetectionmodelbasedonwaapyolo
AT yaweijia cornassociatedweeddetectionmodelbasedonwaapyolo
AT xiuqingzhang cornassociatedweeddetectionmodelbasedonwaapyolo
AT yongjingni cornassociatedweeddetectionmodelbasedonwaapyolo
AT mingzhang cornassociatedweeddetectionmodelbasedonwaapyolo
AT qiwu cornassociatedweeddetectionmodelbasedonwaapyolo
AT chenxiwu cornassociatedweeddetectionmodelbasedonwaapyolo