thumbnail

Topic

Technologies and technical equipment for agriculture and food industry

Volume

Volume 72 / No. 1 / 2024

Pages : 280-290

Metrics

Volume viewed 0 times

Volume downloaded 0 times

DETECTION OF APPLE LEAF DISEASES TARGET BASED ON IMPROVED YOLOV7

基于改进YOLOV7的苹果叶病害目标检测

DOI : https://doi.org/10.35633/inmateh-72-26

Authors

Lingqing FENG

Shanxi Agricultural University

(*) Yujing LIU

Shanxi Agricultural University

Zongwei JIA

Shanxi Agricultural University

Hua YANG

Shanxi Agricultural University

Jiaxiong GUAN

Shanxi Agricultural University

Huiru ZHU

Shanxi Agricultural University

Yiming HOU

Shanxi Agricultural University

(*) Corresponding authors:

[email protected] |

Yujing LIU

Abstract

Apple leaf diseases significantly threaten the yield and quality of apples. In order to detect apple leaf diseases in a timely and accurate manner, this study proposed a detection method for apple leaf diseases based on an improved YOLOv7 model. The method integrated a Similarity-based Attention Mechanism(SimAM) into the traditional YOLOv7 model. Additionally, the regression loss function is modified from Complete Intersection over Union (CIoU) to Structured Intersection over Union (SIoU). Experimental results demonstrates that the improved model exhibits an overall recognition precision of 92%, a recall rate of 99%, and a mean average precision (mAP) of 96.1%. These metrics show a respective improvement of 14.4%, 38.85%, and 18.69% compared to the preimproved YOLOv7. When compared with seven other target detection models in comparative experiments, the improved YOLOv7 model achieves higher accuracy, lower rates of missed and false detections in disease target detection. The model excels in detecting disease categories in complex environments and identifying small targets at early disease stages. It can provide technical support for effective detection of apple leaf diseases.

Abstract in Chinese

苹果叶部病害严重危害苹果的产量和品质,为了实现及时且准确地对苹果叶病害进行检测,提出了一种基于改进YOLOv7模型的苹果叶部病害检测方法,在传统的YOLOv7模型基础上融合了无参数注意力机制SimAM;并将回归损失函数由CIoU(Complete Intersection over Union)改进为SIoU(Structured Intersection over Union )。试验结果表明,改进后的模型整体识别精准度、召回率、平均精度均值mAP(Mean average precision)分别为 92%,99%,96.1%;与改进前YOLOv7相比,分别提升14.4%,38.85%,18.69%,与对比实验中的其他7种目标检测模型相比,改进模型检测精度更高、漏检和错检率低、在复杂环境以及病害初期小目标检测中表现优良。可以为苹果叶病害有效检测提供技术支持。

Indexed in

Clarivate Analytics.
 Emerging Sources Citation Index
Scopus/Elsevier
Google Scholar
Crossref
Road