Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases

Zumin Wang; Yuhao Zhang; Xiaomei Li; Lingyan Hu; Chunming Huang; Liming Chen; Mohand Tahar Kechadi; Rongli Gai

doi:10.1109/swc57546.2023.10448998

Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases

Zumin Wang
, Yuhao Zhang
, Xiaomei Li
, Lingyan Hu
, Chunming Huang
, Liming Chen
, Mohand Tahar Kechadi
, Rongli Gai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.

Original language	English
Title of host publication	2023 IEEE Smart World Congress (SWC)
Publisher	IEEE
Pages	1-9
Number of pages	9
ISBN (Electronic)	979-8-3503-1980-4
ISBN (Print)	979-8-3503-1981-1
DOIs	https://doi.org/10.1109/swc57546.2023.10448998
Publication status	Published online - 1 Mar 2024

Publication series

Name	2023 IEEE Smart World Congress (SWC)
Publisher	IEEE Control Society

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

* Corresponding author. The research was funded by the Science and Technology Innovation Foundation of Dalian (NO.2020JJ26SN058) The work was funded by a grant from the Study on Dynamic Feature Extraction and Modeling of Sweet Cherry Growth in Solar Greenhouse Based on Internet of Things Intelligence (No.2020JJ26SN058).

Funder number
2020JJ26SN058

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 2 Zero Hunger
SDG 12 Responsible Consumption and Production

Keywords

Cherry Leaf Disease
Object Detection
YOLO
Attention Mechanism
Knowledge Distillation

Access to Document

10.1109/swc57546.2023.10448998

Cite this

Wang, Z., Zhang, Y., Li, X., Hu, L., Huang, C., Chen, L., Kechadi, M. T., & Gai, R. (2024). Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases. In 2023 IEEE Smart World Congress (SWC) (pp. 1-9). (2023 IEEE Smart World Congress (SWC)). IEEE. Advance online publication. https://doi.org/10.1109/swc57546.2023.10448998

@inproceedings{96ec6fd2a34d4c529fdb6c6b9af6bd25,

title = "Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases",

abstract = "The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85\% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.",

keywords = "Cherry Leaf Disease, Object Detection, YOLO, Attention Mechanism, Knowledge Distillation",

author = "Zumin Wang and Yuhao Zhang and Xiaomei Li and Lingyan Hu and Chunming Huang and Liming Chen and Kechadi, \{Mohand Tahar\} and Rongli Gai",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.",

year = "2024",

month = mar,

day = "1",

doi = "10.1109/swc57546.2023.10448998",

language = "English",

isbn = "979-8-3503-1981-1",

series = "2023 IEEE Smart World Congress (SWC)",

publisher = "IEEE",

pages = "1--9",

booktitle = "2023 IEEE Smart World Congress (SWC)",

address = "United States",

}

TY - GEN

T1 - Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases

AU - Wang, Zumin

AU - Zhang, Yuhao

AU - Li, Xiaomei

AU - Hu, Lingyan

AU - Huang, Chunming

AU - Chen, Liming

AU - Kechadi, Mohand Tahar

AU - Gai, Rongli

PY - 2024/3/1

Y1 - 2024/3/1

N2 - The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.

AB - The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.

KW - Cherry Leaf Disease

KW - Object Detection

KW - YOLO

KW - Attention Mechanism

KW - Knowledge Distillation

UR - https://www.scopus.com/pages/publications/85187400015

U2 - 10.1109/swc57546.2023.10448998

DO - 10.1109/swc57546.2023.10448998

M3 - Conference contribution

SN - 979-8-3503-1981-1

T3 - 2023 IEEE Smart World Congress (SWC)

SP - 1

EP - 9

BT - 2023 IEEE Smart World Congress (SWC)

PB - IEEE

ER -

Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases

Abstract

Publication series

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this