Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model

In agriculture and forestry, pest detection is critical for increasing crop yields and reducing economic losses. However, traditional deep learning models face challenges in resource-constrained environments, such as insufficient accuracy, slow inference speed, and large model sizes, which hinder th...

Full description

Saved in:
Bibliographic Details
Main Authors: He Gong, Xiaodan Ma, Ying Guo
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/12/3068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106249873063936
author He Gong
Xiaodan Ma
Ying Guo
author_facet He Gong
Xiaodan Ma
Ying Guo
author_sort He Gong
collection DOAJ
description In agriculture and forestry, pest detection is critical for increasing crop yields and reducing economic losses. However, traditional deep learning models face challenges in resource-constrained environments, such as insufficient accuracy, slow inference speed, and large model sizes, which hinder their practical application. To address these issues, this study proposes an improved YOLOv7-tiny model designed to deliver efficient, accurate, and lightweight pest detection solutions. The main improvements are as follows: 1. Lightweight Network Design: The backbone network is optimized by integrating GhostNet and Dynamic Region-Aware Convolution (DRConv) to enhance computational efficiency. 2. Feature Sharing Enhancement: The introduction of a Cross-layer Feature Sharing Network (CotNet Transformer) strengthens feature fusion and extraction capabilities. 3. Activation Function Optimization: The traditional ReLU activation function is replaced with the Gaussian Error Linear Unit (GELU) to improve nonlinear expression and classification performance. Experimental results demonstrate that the improved model surpasses YOLOv7-tiny in accuracy, inference speed, and model size, achieving a MAP@0.5 of 92.8%, reducing inference time to 4.0 milliseconds, and minimizing model size to just 4.8 MB. Additionally, compared to algorithms like Faster R-CNN, SSD, and RetinaNet, the improved model delivers superior detection performance. In conclusion, the improved YOLOv7-tiny provides an efficient and practical solution for intelligent pest detection in agriculture and forestry.
format Article
id doaj-art-06df951687754bdbb9f55f7729c1864a
institution Kabale University
issn 2073-4395
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-06df951687754bdbb9f55f7729c1864a2024-12-27T14:04:53ZengMDPI AGAgronomy2073-43952024-12-011412306810.3390/agronomy14123068Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny ModelHe Gong0Xiaodan Ma1Ying Guo2College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaIn agriculture and forestry, pest detection is critical for increasing crop yields and reducing economic losses. However, traditional deep learning models face challenges in resource-constrained environments, such as insufficient accuracy, slow inference speed, and large model sizes, which hinder their practical application. To address these issues, this study proposes an improved YOLOv7-tiny model designed to deliver efficient, accurate, and lightweight pest detection solutions. The main improvements are as follows: 1. Lightweight Network Design: The backbone network is optimized by integrating GhostNet and Dynamic Region-Aware Convolution (DRConv) to enhance computational efficiency. 2. Feature Sharing Enhancement: The introduction of a Cross-layer Feature Sharing Network (CotNet Transformer) strengthens feature fusion and extraction capabilities. 3. Activation Function Optimization: The traditional ReLU activation function is replaced with the Gaussian Error Linear Unit (GELU) to improve nonlinear expression and classification performance. Experimental results demonstrate that the improved model surpasses YOLOv7-tiny in accuracy, inference speed, and model size, achieving a MAP@0.5 of 92.8%, reducing inference time to 4.0 milliseconds, and minimizing model size to just 4.8 MB. Additionally, compared to algorithms like Faster R-CNN, SSD, and RetinaNet, the improved model delivers superior detection performance. In conclusion, the improved YOLOv7-tiny provides an efficient and practical solution for intelligent pest detection in agriculture and forestry.https://www.mdpi.com/2073-4395/14/12/3068pestYOLOv7-tinyfeature extractiontarget detectiondeep learning
spellingShingle He Gong
Xiaodan Ma
Ying Guo
Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
Agronomy
pest
YOLOv7-tiny
feature extraction
target detection
deep learning
title Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
title_full Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
title_fullStr Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
title_full_unstemmed Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
title_short Research on a Target Detection Algorithm for Common Pests Based on an Improved YOLOv7-Tiny Model
title_sort research on a target detection algorithm for common pests based on an improved yolov7 tiny model
topic pest
YOLOv7-tiny
feature extraction
target detection
deep learning
url https://www.mdpi.com/2073-4395/14/12/3068
work_keys_str_mv AT hegong researchonatargetdetectionalgorithmforcommonpestsbasedonanimprovedyolov7tinymodel
AT xiaodanma researchonatargetdetectionalgorithmforcommonpestsbasedonanimprovedyolov7tinymodel
AT yingguo researchonatargetdetectionalgorithmforcommonpestsbasedonanimprovedyolov7tinymodel