GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny

Aimed at the problem of the difference between intra-class and inter-class pathogenic spores of Wheat Scab image being small and difficult to distinguish, in this paper, we propose a lightweight decoupled Wheat Scab spore detection network based on Yolov7-tiny (GSD-YOLO). Specifically, considering t...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongyan Zhang, Wenfeng Tao, Tao Cheng, Xingen Zhou, Gensheng Hu, Hongbo Qiao, Wei Guo, Ziheng Wang, Chunyan Gu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/14/12/2278
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106433615036416
author Dongyan Zhang
Wenfeng Tao
Tao Cheng
Xingen Zhou
Gensheng Hu
Hongbo Qiao
Wei Guo
Ziheng Wang
Chunyan Gu
author_facet Dongyan Zhang
Wenfeng Tao
Tao Cheng
Xingen Zhou
Gensheng Hu
Hongbo Qiao
Wei Guo
Ziheng Wang
Chunyan Gu
author_sort Dongyan Zhang
collection DOAJ
description Aimed at the problem of the difference between intra-class and inter-class pathogenic spores of Wheat Scab image being small and difficult to distinguish, in this paper, we propose a lightweight decoupled Wheat Scab spore detection network based on Yolov7-tiny (GSD-YOLO). Specifically, considering the limitations of the storage space and power consumption of actual field detection equipment, the original detection head is optimized as a decoupled head, and the GSConv lightweight module is embedded to reduce the parameters of the model and the number of calculations required. In addition, we utilize an improved Spore–Copy data augmentation strategy to improve the detection performance and generalization ability of the algorithm to fit the large numbers, morphology, and variety of wheat disease spores in the actual field and to improve the efficiency of constructing a large data set of diverse spores. The experimental results show that the mAP of the proposed algorithm reaches 98.0%, which is 3.9 percentage points higher than that of the original model. At the same time, the detection speed of the algorithm is 114 f/s, and the memory is 13.1 MB, which meets the application requirements of hardware deployment and real-time detection. It can provide some technical support to the prevention and grading of Wheat Scab in actual farmland.
format Article
id doaj-art-a6c2c9e9246040a6b181f95b8f722ed8
institution Kabale University
issn 2077-0472
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-a6c2c9e9246040a6b181f95b8f722ed82024-12-27T14:03:14ZengMDPI AGAgriculture2077-04722024-12-011412227810.3390/agriculture14122278GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-TinyDongyan Zhang0Wenfeng Tao1Tao Cheng2Xingen Zhou3Gensheng Hu4Hongbo Qiao5Wei Guo6Ziheng Wang7Chunyan Gu8College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, ChinaNational Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, ChinaTexas A&M AgriLife Research Center, 1509 Aggie Drive, Beaumont, TX 77713, USANational Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou 450002, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou 450002, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, ChinaInstitute of Plant Protection and Agro-Products Safety, Anhui Academy of Agricultural Sciences, Hefei 230031, ChinaAimed at the problem of the difference between intra-class and inter-class pathogenic spores of Wheat Scab image being small and difficult to distinguish, in this paper, we propose a lightweight decoupled Wheat Scab spore detection network based on Yolov7-tiny (GSD-YOLO). Specifically, considering the limitations of the storage space and power consumption of actual field detection equipment, the original detection head is optimized as a decoupled head, and the GSConv lightweight module is embedded to reduce the parameters of the model and the number of calculations required. In addition, we utilize an improved Spore–Copy data augmentation strategy to improve the detection performance and generalization ability of the algorithm to fit the large numbers, morphology, and variety of wheat disease spores in the actual field and to improve the efficiency of constructing a large data set of diverse spores. The experimental results show that the mAP of the proposed algorithm reaches 98.0%, which is 3.9 percentage points higher than that of the original model. At the same time, the detection speed of the algorithm is 114 f/s, and the memory is 13.1 MB, which meets the application requirements of hardware deployment and real-time detection. It can provide some technical support to the prevention and grading of Wheat Scab in actual farmland.https://www.mdpi.com/2077-0472/14/12/2278wheat scab sporestarget detectionYOLOGSConvdecoupled head
spellingShingle Dongyan Zhang
Wenfeng Tao
Tao Cheng
Xingen Zhou
Gensheng Hu
Hongbo Qiao
Wei Guo
Ziheng Wang
Chunyan Gu
GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
Agriculture
wheat scab spores
target detection
YOLO
GSConv
decoupled head
title GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
title_full GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
title_fullStr GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
title_full_unstemmed GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
title_short GSD-YOLO: A Lightweight Decoupled Wheat Scab Spore Detection Network Based on Yolov7-Tiny
title_sort gsd yolo a lightweight decoupled wheat scab spore detection network based on yolov7 tiny
topic wheat scab spores
target detection
YOLO
GSConv
decoupled head
url https://www.mdpi.com/2077-0472/14/12/2278
work_keys_str_mv AT dongyanzhang gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT wenfengtao gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT taocheng gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT xingenzhou gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT genshenghu gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT hongboqiao gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT weiguo gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT zihengwang gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny
AT chunyangu gsdyoloalightweightdecoupledwheatscabsporedetectionnetworkbasedonyolov7tiny