Lightweighted Wheat Leaf Diseases and Pests Detection Model Based on Improved YOLOv8

doi:10.12133/j.smartag.SA202309010

Abstract

Abstract:

Objective To effectively tackle the unique attributes of wheat leaf pests and diseases in their native environment, a high-caliber and efficient pest detection model named YOLOv8-SS (You Only Look Once Version 8-SS) was proposed. This innovative model is engineered to accurately identify pests, thereby providing a solid scientific foundation for their prevention and management strategies. Methods A total of 3 639 raw datasets of images of wheat leaf pests and diseases were collected from 6 different wheat pests and diseases in various farmlands in the Yuchong County area of Gansu Province, at different periods of time, using mobile phones. This collection demonstrated the team's proficiency and commitment to advancing agricultural research. The dataset was meticulously constructed using the LabelImg software to accurately label the images with targeted pest species. To guarantee the model's superior generalization capabilities, the dataset was strategically divided into a training set and a test set in an 8:2 ratio. The dataset includes thorough observations and recordings of the wheat leaf blade's appearance, texture, color, as well as other variables that could influence these characteristics. The compiled dataset proved to be an invaluable asset for both training and validation activities. Leveraging the YOLOv8 algorithm, an enhanced lightweight convolutional neural network, ShuffleNetv2, was selected as the basis network for feature extraction from images. This was accomplished by integrating a 3×3 Depthwise Convolution (DWConv) kernel, the h-swish activation function, and a Squeeze-and-Excitation Network (SENet) attention mechanism. These enhancements streamlined the model by diminishing the parameter count and computational demands, all while sustaining high detection precision. The deployment of these sophisticated methodologies exemplified the researchers' commitment and passion for innovation. The YOLOv8 model employs the SEnet attention mechanism module within both its Backbone and Neck components, significantly reducing computational load while bolstering accuracy. This method exemplifies the model's exceptional performance, distinguishing it from other models in the domain. By integrating a dedicated small target detection layer, the model's capabilities have been augmented, enabling more efficient and precise pest and disease detection. The introduction of a new detection feature map, sized 160×160 pixels, enables the network to concentrate on identifying small-targeted pests and diseases, thereby enhancing the accuracy of pest and disease recognition. Results and Discussion The YOLOv8-SS wheat leaf pests and diseases detection model has been significantly improved to accurately detect wheat leaf pests and diseases in their natural environment. By employing the refined ShuffleNet V2 within the DarkNet-53 framework, as opposed to the conventional YOLOv8, under identical experimental settings, the model exhibited a 4.53% increase in recognition accuracy and a 4.91% improvement in F₁-Score, compared to the initial model. Furthermore, the incorporation of a dedicated small target detection layer led to a subsequent rise in accuracy and F₁-Scores of 2.31% and 2.16%, respectively, despite a minimal upsurge in the number of parameters and computational requirements. The integration of the SEnet attention mechanism module into the YOLOv8 model resulted in a detection accuracy rate increase of 1.85% and an F₁-Score enhancement of 2.72%. Furthermore, by swapping the original neural network architecture with an enhanced ShuffleNet V2 and appending a compact object detection sublayer (namely YOLOv8-SS), the resulting model exhibited a heightened recognition accuracy of 89.41% and an F₁-Score of 88.12%. The YOLOv8-SS variant substantially outperformed the standard YOLOv8, showing a remarkable enhancement of 10.11% and 9.92% in accuracy, respectively. This outcome strikingly illustrates the YOLOv8-SS's prowess in balancing speed with precision. Moreover, it achieves convergence at a more rapid pace, requiring approximately 40 training epochs, to surpass other renowned models such as Faster R-CNN, MobileNetV2, SSD, YOLOv5, YOLOX, and the original YOLOv8 in accuracy. Specifically, the YOLOv8-SS boasted an average accuracy 23.01%, 15.13%, 11%, 25.21%, 27.52%, and 10.11% greater than that of the competing models, respectively. In a head-to-head trial involving a public dataset (LWDCD 2020) and a custom-built dataset, the LWDCD 2020 dataset yielded a striking accuracy of 91.30%, outperforming the custom-built dataset by a margin of 1.89% when utilizing the same network architecture, YOLOv8-SS. The AI Challenger 2018-6 and Plant-Village-5 datasets did not perform as robustly, achieving accuracy rates of 86.90% and 86.78% respectively. The YOLOv8-SS model has shown substantial improvements in both feature extraction and learning capabilities over the original YOLOv8, particularly excelling in natural environments with intricate, unstructured backdrops. Conclusion The YOLOv8-SS model is meticulously designed to deliver unmatched recognition accuracy while consuming a minimal amount of storage space. In contrast to conventional detection models, this groundbreaking model exhibits superior detection accuracy and speed, rendering it exceedingly valuable across various applications. This breakthrough serves as an invaluable resource for cutting-edge research on crop pest and disease detection within natural environments featuring complex, unstructured backgrounds. Our method is versatile and yields significantly enhanced detection performance, all while maintaining a lean model architecture. This renders it highly appropriate for real-world scenarios involving large-scale crop pest and disease detection.

Key words: wheat leaf, pests and diseases detection, ShuffleNet V2, YOLOv8, lightweight model

YANG Feng, YAO Xiaotong. Lightweighted Wheat Leaf Diseases and Pests Detection Model Based on Improved YOLOv8[J]. Smart Agriculture, 2024, 6(1): 147-157.

Figures/Tables 14

Fig. 1

Table1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Table 2

Table 3

Table 4

Fig.7

Table 5

Table 6

Fig. 8

References 30

1	曾圣然, 尚禹. 分子生物学在小麦栽培方面的研究和未来方向[J]. 种子科技, 2021, 39(15): 22-23.
	ZENG S R, SHANG Y. Research and future direction of molecular biology in wheat cultivation[J]. Seed science & technology, 2021, 39(15): 22-23.
2	李跃, 刘万才, 赵中华. 2022年全国小麦病虫害发生防治概况及对策思考[J]. 中国植保导刊, 2023, 43(1): 52-54, 92.
	LI Y, LIU W C, ZHAO Z H. The occurrence and management of wheat insect pests and diseases in China in 2022 and reflections on pest control measures[J]. China plant protection, 2023, 43(1): 52-54, 92.
3	兰玉彬, 王天伟, 陈盛德, 等. 农业人工智能技术:现代农业科技的翅膀[J]. 华南农业大学学报, 2020, 41(6): 1-13.
	LAN Y B, WANG T W, CHEN S D, et al. Agricultural artificial intelligence technology: Wings of modern agricultural science and technology[J]. Journal of South China agricultural university, 2020, 41(6): 1-13.
4	SLADOJEVIC S, ARSENOVIC M, ANDERLA A, et al. Deep neural networks based recognition of plant diseases by leaf image classification[J]. Computational intelligence and neuroscience, 2016, 2016: ID 3289801.
5	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
6	张航, 程清, 武英洁, 等. 一种基于卷积神经网络的小麦病害识别方法[J]. 山东农业科学, 2018, 50(3): 137-141.
	ZHANG H, CHENG Q, WU Y J, et al. A method of wheat disease identification based on convolutional neural network[J]. Shandong agricultural sciences, 2018, 50(3): 137-141.
7	贾少鹏, 高红菊, 杭潇. 基于深度学习的农作物病虫害图像识别技术研究进展[J]. 农业机械学报, 2019, 50(S1): 313-317.
	JIA S P, GAO H J, HANG X. Research progress on image recognition technology of crop pests and diseases based on deep learning[J]. Transactions of the Chinese society for agricultural machinery, 2019, 50(S1): 313-317.
8	DENG F, PU S L, CHEN X H, et al. Hyperspectral image classification with capsule network using limited training samples[J]. Sensors, 2018, 18(9): ID 3153.
9	XUE Z Y, XU R J, BAI D, et al. YOLO-tea: A tea disease detection model improved by YOLOv5[J]. Forests, 2023, 14(2): ID 415.
10	HUANG Q D, WU X C, WANG Q, et al. Knowledge distillation facilitates the lightweight and efficient plant diseases detection model[J]. Plant phenomics, 2023, 5: ID 0062.
11	JIANG Z C, DONG Z X, JIANG W P, et al. Recognition of rice leaf diseases and wheat leaf diseases based on multi-task deep transfer learning[J]. Computers and electronics in agriculture, 2021, 186: ID 106184.
12	DONG X Y, WANG Q, HUANG Q D, et al. PDDD-PreTrain: A series of commonly used pre-trained models support image-based plant disease diagnosis[J]. Plant phenomics, 2023, 5: ID 0054.
13	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-Excitation Networks[J]. IEEE trans pattern anal mach intell, 2020, 42(8): 2011-2023.
14	TANG Z Y, LIU X L, LI Y, et al. Multi-atlas brain parcellation using squeeze-and-excitation fully convolutional networks[J]. IEEE transactions on image processing, 2020, 29: 6864-6872.
15	REDMON J, FARHADI A. YOLOv3: An Incremental Improvement[J]. arXiv e-prints, 2018.DOI:10.48550/arXiv.1804.02767 .
16	SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: Inverted residuals and linear bottlenecks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, New Jersey, USA: IEEE, 2018: 4510-4520.
17	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.
18	ALOM M Z, TAHA T M, YAKOPCIC C,et al. The history began from AlexNet: A comprehensive survey on deep learning approaches[EB/OL]. arXiv:1803.01164 [cs.CV], 2018.
19	MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: Practical guidelines for efficient CNN architecture design[C]// European conference on computer vision. Cham, Switzerland: Springer, 2018: 122-138.
20	ZHANG X Y, ZHOU X Y, LIN M X, et al. ShuffleNet: An extremely efficient convolutional neural network for mobile devices[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, New Jersey, USA: IEEE, 2018: 6848-6856.
21	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2015: 3431-3440.
22	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, New Jersey, USA: IEEE, 2018: 8759-8768.
23	SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL]. arXiv:1409.1556 [cs.CV], 2014.
24	JIAO L C, ZHANG F, LIU F, et al. A survey of deep learning-based object detection[J]. IEEE access, 2019, 7: 128837-128868.
25	CAI D L, ZHANG Z Y, ZHANG Z. Corner-point and foreground-area IoU loss: Better localization of small objects in bounding box regression[J]. Sensors, 2023, 23(10): ID 4961.
26	SHEPLEY A J, FALZON G, KWAN P, et al. Confluence: A robust non-IoU alternative to non-maxima suppression in object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(10): 11561-11574.
27	HUGHES D P, SALATHE M. An open access repository of images on plant health to enable the development of mobile disease diagnostics[EB/OL]. arXiv: 1511.08060, 2015.
28	GOYAL L, SHARMA C M, SINGH A, et al. Leaf and spike wheat disease detection & classification using an improved deep convolutional architecture[J]. Informatics in medicine unlocked, 2021, 25: ID 100642.
29	邓洁. 基于深度学习的小麦病虫害图像识别系统的开发与应用[D]. 太谷: 山西农业大学, 2022.
	DENG J. Development and application of an image recognition system for wheat diseases and insect pests based on deep learning[D]. Taigu: Shanxi Agricultural University, 2022.
30	韩强. 面向小目标检测的改进YOLOv8算法研究[D]. 长春: 吉林大学, 2023.
	HAN Q. Research on improved YOLOv8 algorithm for small target detection[D]. Changchun: Jilin University, 2023.

小麦病虫害类别	训练集样本数量/张	测试集样本数量/张	样本总数量/张
健康小麦	230	58	288
黄锈病	550	138	688
褐锈病	578	144	722
黑穗病	647	162	809
秆锈病	496	124	620
小麦蚜虫	410	102	512

配置	配置名称	详细信息
硬件配置	CPU	Intel（R）Core（TM）i7-11700
	运行内存大小	32 GB
	GPU	英伟达 GTX 3080TI
	显存大小	12 GB
软件配置	操作系统	Windows 11
	Python版本	3.7
	深度学习框架	Pytorch 1.8.0
	CUDA	11.1

网络模型	主干网络	精确率/%	召回率/%	mAP_0.5/%	F ₁分数/%	检测速度/s
YOLOv8	DarkNet-53	79.30	79.11	79.56	78.20	0.77
YOLOv8	ShuffleNetv2	80.21	80.16	80.61	80.07	0.77
YOLOv8	改进ShuffleNetv2	83.83	83.75	83.69	83.11	0.75

序号	改进ShuffleNetV2网络	SEnet注意力机制模块	小目标检测层	精确率/%	F ₁分数/%	参数量/G	运算量/G
1	×	×	×	79.30	78.20	3.011	8.20
2	√	×	×	83.83	83.11	2.115	5.76
3	×	√	×	81.15	80.92	3.012	8.20
4	√	×	√	85.54	85.27	2.123	5.81
5	√	√	√	89.41	88.12	2.124	5.82

对比模型名称	精确率/%	召回率/%	mAP_0.5/%	F ₁分数/%	检测速度/s
Faster R-CNN	66.40	60.30	63.40	61.22	0.49
MobileNetv2	74.28	74.13	74.8	74.08	0.63
SSD	78.41	78.27	78.21	78.14	1.37
YOLOv5	64.80	61.28	65.24	61.67	0.82
YOLOX	61.89	61.50	60.78	63.54	0.51
YOLOv8	79.30	79.11	79.56	78.20	0.77
YOLOv8-SS	89.41	89.20	91.24	88.12	0.78