A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests

Traditional sweet potato disease and pest detection methods have the limitations of low efficiency, poor accuracy and manual dependence, while deep learning-based target detection can achieve an efficient and accurate detection. This paper proposed an efficient sweet potato leaf disease and pest det...

Full description

Saved in:
Bibliographic Details
Main Authors: Kang Xu, Yan Hou, Wenbin Sun, Dongquan Chen, Danyang Lv, Jiejie Xing, Ranbing Yang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/5/503
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050818509635584
author Kang Xu
Yan Hou
Wenbin Sun
Dongquan Chen
Danyang Lv
Jiejie Xing
Ranbing Yang
author_facet Kang Xu
Yan Hou
Wenbin Sun
Dongquan Chen
Danyang Lv
Jiejie Xing
Ranbing Yang
author_sort Kang Xu
collection DOAJ
description Traditional sweet potato disease and pest detection methods have the limitations of low efficiency, poor accuracy and manual dependence, while deep learning-based target detection can achieve an efficient and accurate detection. This paper proposed an efficient sweet potato leaf disease and pest detection method SPLDPvB, as well as a low-complexity version SPLDPvT, to achieve accurate identification of sweet potato leaf spots and pests, such as hawk moth and wheat moth. First, a residual module containing three depthwise separable convolutional layers and a skip connection was proposed to effectively retain key feature information. Then, an efficient feature extraction module integrating the residual module and the attention mechanism was designed to significantly improve the feature extraction capability. Finally, in the model architecture, only the structure of the backbone network and the decoupling head combination was retained, and the traditional backbone network was replaced by an efficient feature extraction module, which greatly reduced the model complexity. The experimental results showed that the mAP0.5 and mAP0.5:0.95 of the proposed SPLDPvB model were 88.7% and 74.6%, respectively, and the number of parameters and the amount of calculation were 1.1 M and 7.7 G, respectively. Compared with YOLOv11S, mAP0.5 and mAP0.5:0.95 increased by 2.3% and 2.8%, respectively, and the number of parameters and the amount of calculation were reduced by 88.2% and 63.8%, respectively. The proposed model achieves higher detection accuracy with significantly reduced complexity, demonstrating excellent performance in detecting sweet potato leaf pests and diseases. This method realizes the automatic detection of sweet potato leaf pests and diseases and provides technical guidance for the accurate identification and spraying of pests and diseases.
format Article
id doaj-art-938d83d873c94a86b100b081e16980be
institution DOAJ
issn 2077-0472
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-938d83d873c94a86b100b081e16980be2025-08-20T02:53:19ZengMDPI AGAgriculture2077-04722025-02-0115550310.3390/agriculture15050503A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating PestsKang Xu0Yan Hou1Wenbin Sun2Dongquan Chen3Danyang Lv4Jiejie Xing5Ranbing Yang6College of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaKey Laboratory of Tropical Intelligent Agricultural Equipment, Ministry of Agriculture and Rural Affairs, Hainan University, Danzhou 571737, ChinaCollege of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaCollege of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaCollege of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaKey Laboratory of Tropical Intelligent Agricultural Equipment, Ministry of Agriculture and Rural Affairs, Hainan University, Danzhou 571737, ChinaKey Laboratory of Tropical Intelligent Agricultural Equipment, Ministry of Agriculture and Rural Affairs, Hainan University, Danzhou 571737, ChinaTraditional sweet potato disease and pest detection methods have the limitations of low efficiency, poor accuracy and manual dependence, while deep learning-based target detection can achieve an efficient and accurate detection. This paper proposed an efficient sweet potato leaf disease and pest detection method SPLDPvB, as well as a low-complexity version SPLDPvT, to achieve accurate identification of sweet potato leaf spots and pests, such as hawk moth and wheat moth. First, a residual module containing three depthwise separable convolutional layers and a skip connection was proposed to effectively retain key feature information. Then, an efficient feature extraction module integrating the residual module and the attention mechanism was designed to significantly improve the feature extraction capability. Finally, in the model architecture, only the structure of the backbone network and the decoupling head combination was retained, and the traditional backbone network was replaced by an efficient feature extraction module, which greatly reduced the model complexity. The experimental results showed that the mAP0.5 and mAP0.5:0.95 of the proposed SPLDPvB model were 88.7% and 74.6%, respectively, and the number of parameters and the amount of calculation were 1.1 M and 7.7 G, respectively. Compared with YOLOv11S, mAP0.5 and mAP0.5:0.95 increased by 2.3% and 2.8%, respectively, and the number of parameters and the amount of calculation were reduced by 88.2% and 63.8%, respectively. The proposed model achieves higher detection accuracy with significantly reduced complexity, demonstrating excellent performance in detecting sweet potato leaf pests and diseases. This method realizes the automatic detection of sweet potato leaf pests and diseases and provides technical guidance for the accurate identification and spraying of pests and diseases.https://www.mdpi.com/2077-0472/15/5/503sweet potatodeep learningtarget detectionfeature extractionlow complexity
spellingShingle Kang Xu
Yan Hou
Wenbin Sun
Dongquan Chen
Danyang Lv
Jiejie Xing
Ranbing Yang
A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
Agriculture
sweet potato
deep learning
target detection
feature extraction
low complexity
title A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
title_full A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
title_fullStr A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
title_full_unstemmed A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
title_short A Detection Method for Sweet Potato Leaf Spot Disease and Leaf-Eating Pests
title_sort detection method for sweet potato leaf spot disease and leaf eating pests
topic sweet potato
deep learning
target detection
feature extraction
low complexity
url https://www.mdpi.com/2077-0472/15/5/503
work_keys_str_mv AT kangxu adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT yanhou adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT wenbinsun adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT dongquanchen adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT danyanglv adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT jiejiexing adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT ranbingyang adetectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT kangxu detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT yanhou detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT wenbinsun detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT dongquanchen detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT danyanglv detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT jiejiexing detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests
AT ranbingyang detectionmethodforsweetpotatoleafspotdiseaseandleafeatingpests