Improvement of the YOLOv5 Model in the Optimization of the Brown Spot Disease Recognition Algorithm of Kidney Bean

The kidney bean is an important cash crop whose growth and yield are severely affected by brown spot disease. Traditional target detection models cannot effectively screen out key features, resulting in model overfitting and weak generalization ability. In this study, a Bi-Directional Feature Pyrami...

Full description

Saved in:
Bibliographic Details
Published in:Plants (Basel) 2023-11, Vol.12 (21), p.3765
Main Authors: Su, Pengyan, Li, Hao, Wang, Xiaoyun, Wang, Qianyu, Hao, Bokun, Feng, Meichen, Sun, Xinkai, Yang, Zhongyu, Jing, Binghan, Wang, Chao, Qin, Mingxing, Song, Xiaoyan, Xiao, Lujie, Sun, Jingjing, Zhang, Meijun, Yang, Wude
Format: Article
Language:English
Subjects:
Accuracy
Agricultural research
Algorithms
attention mechanism
Beans
Brown spot
Cash crops
Crop diseases
Deep learning
Diagnosis
disease detection
Diseases and pests
Environmental information
Feature extraction
feature fusion
Kidney bean
kidney bean brown spot
Kidney beans
Leaves
Machine learning
Machine vision
Modules
Object recognition
Optimization
Performance evaluation
Plant diseases
Recall
Semantics
Target detection
Target spot
YOLOv5-SE-BiFPN
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The kidney bean is an important cash crop whose growth and yield are severely affected by brown spot disease. Traditional target detection models cannot effectively screen out key features, resulting in model overfitting and weak generalization ability. In this study, a Bi-Directional Feature Pyramid Network (BiFPN) and Squeeze and Excitation (SE) module were added to a YOLOv5 model to improve the multi-scale feature fusion and key feature extraction abilities of the improved model. The results show that the BiFPN and SE modules show higher heat in the target location region and pay less attention to irrelevant environmental information in the non-target region. The detection Precision, Recall, and mean average Precision (mAP@0.5) of the improved YOLOv5 model are 94.7%, 88.2%, and 92.5%, respectively, which are 4.9% higher in Precision, 0.5% higher in Recall, and 25.6% higher in the mean average Precision compared to the original YOLOv5 model. Compared with the YOLOv5-SE, YOLOv5-BiFPN, FasterR-CNN, and EfficientDet models, detection Precision improved by 1.8%, 3.0%, 9.4%, and 9.5%, respectively. Moreover, the rate of missed and wrong detection in the improved YOLOv5 model is only 8.16%. Therefore, the YOLOv5-SE-BiFPN model can more effectively detect the brown spot area of kidney beans.
ISSN:2223-7747
2223-7747
DOI:10.3390/plants12213765