ERL-YOLOv8n: A Potato Disease Detection Network for Complex Field Environments

DOI: https://doi.org/10.62517/jbdc.202501401

Author(s)

Feng Gong1,2, Yingsheng Chen2, *

Affiliation(s)

1School of Computer Science and Engineering, Chongqing Three Gorges University, Chongqing, China 2Big Data and Information Security Engineering Technology Research Center, Chongqing College of Humanities, Science and Technology, Chongqing, China *Corresponding Author

Abstract

To address the challenge of balancing accuracy and efficiency in potato disease detection models under complex field conditions, this study proposes an improved lightweight detection algorithm, ERL-YOLOv8n. The algorithm optimizes the YOLOv8n model in three key aspects: First, the Receptive Field Attention Convolutional Block Attention Module (RFCBAMConv) is introduced into the backbone network to enhance the model's adaptive perception of disease spot features at various scales. Second, an EPSA (ECA and Polarized Self-Attention) module is embedded in the neck network to improve the model's anti-interference capability in complex backgrounds by fusing multi-dimensional feature information. Finally, the LSGE (Large Selective Kernel Network and Spatial Group-wise Enhance) attention mechanism is incorporated to synergistically optimize the backbone and neck, effectively improving detection accuracy for large-scale targets and complex scenes. Ablation and comparative experiments demonstrate that the ERL-YOLOv8n model achieves significant improvements in key performance metrics while maintaining high detection speed. Compared to the original YOLOv8n model, its precision, recall, and mAP@50 increased by 1.4, 5.7, and 2.3 percentage points, respectively. The improved model exhibits enhanced robustness and superior detection performance, particularly in the early identification of early and late blight, providing reliable technical support for practical applications in precision agriculture.

Keywords

Potato Disease; Object Detection; YOLOv8n; Deep Learning; Attention Mechanism

References

[1]Yuan Y J. Potato Planting Technology and Common Pest and Disease Control Strategies—A Case Study of Ningjin County. Southern Agricultural Machinery, 2023, 54(06): 66-68, 86. [2]Javed R, Imran K, Ghulam A, et al. Multi-Level Deep Learning Model for Potato Leaf Disease Recognition. Electronics, 2021, 10(17): 2064-2064. [3]Wang L B, Zhang B, Yao J F, et al. Potato Leaf Disease Recognition and Lesion Detection Based on Convolutional Neural Networks. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 122-129. [4]Niu Y X, Sun Z H, Ren W, et al. Few-Shot Potato Disease Leaf Detection Based on a Layered Feature Alignment Network. Journal of Chinese Agricultural Mechanization, 2024, 45(02): 250-258. [5]Sun J M, Bi Z Y, Niu L D. Recognition of Potato Leaf Diseases Using an EfficientNet v2 Network with a Feature Fusion Transformer. Jiangsu Agricultural Sciences, 2024, 52(08): 166-176. [6]Liu K Q. Research on Potato Leaf Disease Recognition Based on YOLOv3-SPP. Automation Application, 2022, (06): 21-24+28. DOI: 10.19769/ j. zdhy.2022.06.006. [7]Zeng L, Peng Y. Potato Leaf Disease Detection Algorithm Based on Improved YOLOv8. Journal of Luoyang Institute of Science and Technology (Natural Science Edition), 2024, 34(03): 62-69. [8]Gao X, Zhang Y. Detection of Fruit using YOLOv8-based Single Stage Detectors. International Journal of Advanced Computer Science and Applications (IJACSA), 2023, 14(12). [9]Zhang X, Liu C, Yang D, et al. RFAConv: Innovating spatial attention and standard convolutional operation. arXiv preprint arXiv:2304. 03198, 2023. [10]Q. W, B. W, P.Z, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2020,11531-11539. [11]Huajun L, Fuqiang L, Xinyi F, et al. Polarized self-attention: Towards high-quality pixel-wise mapping. Neurocomputing, 2022, 506158-167. [12]Zhong T. Research on Methods for Crop Leaf Disease Type Identification and Detection Based on Deep Learning. Tianjin University of Technology, 2024. DOI: 10.27360/d.cnki.gtlgy.2024.001314. [13]Zhou Y F, Liu D Y, Zhou Y P. Crop Disease Leaf Detection Based on Multimodal Feature Alignment. Journal of Chinese Agricultural Mechanization, 2024, 45(07): 180-187. DOI: 10.13733/j.jcam.issn.2095-5553.2024.07.027. [14]Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module //Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018: 3-19. [15]Wang Z T, Zou Y B, Wu C L, et al. Beyond Single Perception: An Agricultural Pest Detection Algorithm MRA-YOLOX. Computer Engineering and Applications, 2024, 60(16): 206-216. [16]Li X, Hu X, Yang J. Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks. CoRR, 2019, abs/1905.09646 [17]Y. Li, Q. Hou, Z. Zheng, M. -M. Cheng, J. Yang and X. Li, "Large Selective Kernel Network for Remote Sensing Object Detection," 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023, pp. 16748-16759, DOI: 10.1109/ICCV51070.2023.01540. [18]Nagachandrika B, Prasath R, Joe P I. An automatic classification framework for identifying type of plant leaf diseases using multi-scale feature fusion-based adaptive deep network. Biomedical Signal Processing and Control, 2024, 95(PA): 106316-.