Crop Pest Target Detection Algorithm in Complex Scenes:YOLOv8-Extend

doi:10.12133/j.smartag.SA202311007

Abstract

Abstract:

[Objective] It is of great significance to improve the efficiency and accuracy of crop pest detection in complex natural environments, and to change the current reliance on expert manual identification in the agricultural production process. Targeting the problems of small target size, mimicry with crops, low detection accuracy, and slow algorithm reasoning speed in crop pest detection, a complex scene crop pest target detection algorithm named YOLOv8-Entend was proposed in this research. [Methods] Firstly, the GSConv was introduecd to enhance the model's receptive field, allowing for global feature aggregation. This mechanism enables feature aggregation at both node and global levels simultaneously, obtaining local features from neighboring nodes through neighbor sampling and aggregation operations, enhancing the model's receptive field and semantic understanding ability. Additionally, some Convs were replaced with lightweight Ghost Convolutions and HorBlock was utilized to capture longer-term feature dependencies. The recursive gate convolution employed gating mechanisms to remember and transmit previous information, capturing long-term correlations. Furthermore, Concat was replaced with BiFPN for richer feature fusion. The bidirectional fusion of depth features from top to bottom and from bottom to top enhances the transmission of feature information acrossed different network layers. Utilizing the VoVGSCSP module, feature maps of different scales were connected to create longer feature map vectors, increasing model diversity and enhancing small object detection. The convolutional block attention module (CBAM) attention mechanism was introduced to strengthen features of field pests and reduce background weights caused by complexity. Next, the Wise IoU dynamic non-monotonic focusing mechanism was implemented to evaluate the quality of anchor boxes using "outlier" instead of IoU. This mechanism also included a gradient gain allocation strategy, which reduced the competitiveness of high-quality anchor frames and minimizes harmful gradients from low-quality examples. This approach allowed WIoU to concentrate on anchor boxes of average quality, improving the network model's generalization ability and overall performance. Subsequently, the improved YOLOv8-Extend model was compared with the original YOLOv8 model, YOLOv5, YOLOv8-GSCONV, YOLOv8-BiFPN, and YOLOv8-CBAM to validate the accuracy and precision of model detection. Finally, the model was deployed on edge devices for inference verification to confirm its effectiveness in practical application scenarios. [Results and Discussions] The results indicated that the improved YOLOv8-Extend model achieved notable improvements in accuracy, recall, mAP@0.5, and mAP@0.5:0.95 evaluation indices. Specifically, there were increases of 2.6%, 3.6%, 2.4% and 7.2%, respectively, showcasing superior detection performance. YOLOv8-Extend and YOLOv8 run respectively on the edge computing device JETSON ORIN NX 16 GB and were accelerated by TensorRT, mAP@0.5 improved by 4.6%, FPS reached 57.6, meeting real-time detection requirements. The YOLOv8-Extend model demonstrated better adaptability in complex agricultural scenarios and exhibited clear advantages in detecting small pests and pests sharing similar growth environments in practical data collection. The accuracy in detecting challenging data saw a notable increased of 11.9%. Through algorithm refinement, the model showcased improved capability in extracting and focusing on features in crop pest target detection, addressing issues such as small targets, similar background textures, and challenging feature extraction. [Conclusions] The YOLOv8-Extend model introduced in this study significantly boosts detection accuracy and recognition rates while upholding high operational efficiency. It is suitable for deployment on edge terminal computing devices to facilitate real-time detection of crop pests, offering technological advancements and methodologies for the advancement of cost-effective terminal-based automatic pest recognition systems. This research can serve as a valuable resource and aid in the intelligent detection of other small targets, as well as in optimizing model structures.

Key words: YOLOv8, pest detection, attention mechanism, edge computing, CBAM, BiFPN, VoVGSCSP, GSConv

ZHANG Ronghua, BAI Xue, FAN Jiangchuan. Crop Pest Target Detection Algorithm in Complex Scenes:YOLOv8-Extend[J]. Smart Agriculture, 2024, 6(2): 49-61.

Figures/Tables 19

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 2

Table 3

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Table 4

Fig. 12

Table 5

Fig. 13

Table 6

References 31

1	李健, 陈长明. 基于计算机视觉的农作物害虫自动检测研究综述[J]. 微型电脑应用, 2009, 25(12): 62-64, 78.
	LI J, CHEN C M. Research progress on automatic detection for crop pests based on computer vision[J]. Microcomputer applications, 2009, 25(12): 62-64, 78.
2	刁智华, 王欢, 宋寅卯, 等. 复杂背景下棉花病叶害螨图像分割方法[J]. 农业工程学报, 2013, 29(5): 147-152.
	DIAO Z H, WANG H, SONG Y M, et al. Segmentation method for cotton mite disease image under complex background[J]. Transactions of the Chinese society of agricultural engineering, 2013, 29(5): 147-152.
3	宋勇, 陈兵, 王琼, 等. 基于无人机多光谱影像的棉花黄萎病监测[J]. 棉花学报, 2023, 35(2): 87-100.
	SONG Y, CHEN B, WANG Q, et al. Monitoring of cotton Verticillium wilt based on unmanned aerial vehicle multispectral images[J]. Cotton science, 2023, 35(2): 87-100.
4	张楠楠, 张晓, 白铁成, 等. 基于CBAM-YOLO v7的自然环境下棉叶病虫害识别方法[J]. 农业机械学报, 2023, 54(S1): 239-244.
	ZHANG N N, ZHANG X, BAI T C, et al. Identification method of cotton leaf pests and diseases in natural environment based on CBAM-YOLOv7[J]. Transactions of the Chinese society for agricultural machinery, 2023, 54(S1): 239-244.
5	YUAN Z W, ZHANG J. Feature extraction and image retrieval based on AlexNet[C]// Proceedings of Eighth International Conference on Digital Image Processing (ICDIP 2016. San Francisco,USA: SPIE, 2016, 10033: 65-69.
6	HE J, LI S, SHEN J M, et al. Facial expression recognition based on VGGNet convolutional neural network[C]// 2018 Chinese Automation Congress (CAC). Piscataway, New Jersey, USA: IEEE, 2018: 4146-4151.
7	AL-QIZWINI M, BARJASTEH I, AL-QASSAB H, et al. Deep learning algorithm for autonomous driving using GoogLeNet[C]// 2017 IEEE Intelligent Vehicles Symposium (IV). Piscataway, New Jersey, USA: IEEE, 2017: 89-96.
8	TARG S, ALMEIDA D, LYMAN K. Resnet in resnet: Generalizing residual architectures[EB/OL]. arXiv: 1603.08029, 2016.
9	ZHU Y, NEWSAM S. DenseNet for dense flow[C]// 2017 IEEE International Conference on Image Processing (ICIP). New York, USA: ACM, 2017: 790-794.
10	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.
11	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2016: 779-788.
12	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2017: 6517-6525.
13	REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. arXiv: 1804. 02767, 2018.
14	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. arXiv: 2004.10934, 2020.
15	GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. arXiv: 2107. 08430, 2021.
16	王建, 徐闯. 基于YOLOv5s的脐橙虫害检测研究[J]. 工业控制计算机, 2023, 36(7): 105-106, 109.
	WANG J, XU C. Research on detection of navel orange pests based on YOLOv5s[J]. Industrial control computer, 2023, 36(7): 105-106, 109.
17	FUENTES A, YOON S, KIM S C, et al. A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition[J]. Sensors, 2017, 17(9): 2022.
18	何颖. 基于改进YOLOv5模型的经济林木虫害目标检测算法研究[D]. 昆明: 云南农业大学, 2022.
	HE Y. Research on object detection algorithm of economic forestry pests based on improved YOLOv5[D]. Kunming: Yunnan Agricultural University, 2022.
19	REZA M T, MEHEDI N, TASNEEM N A, et al. Identification of crop consuming insect pest from visual imagery using transfer learning and data augmentation on deep neural network[C]// 2019 22nd International Conference on Computer and Information Technology (ICCIT). Piscataway, New Jersey, USA: IEEE, 2019.
20	CHEN J W, LIN W J, CHENG H J, et al. A smartphone-based application for scale pest detection using multiple-object detection methods[J]. Electronics, 2021, 10(4): ID 372.
21	魏陈浩, 杨睿, 刘振丙, 等. 具有双层路由注意力的YOLOv8道路场景目标检测方法[J]. 图学学报, 2023, 44(6): 1104-1111.
	WEI C H, YANG R, LIU Z B, et al. YOLOv8 with bi-level routing attention for road scene object detection[J]. Journal of graphics, 2023, 44(6): 1104-1111.
22	LI R, WANG R J, XIE C J, et al. A coarse-to-fine network for aphid recognition and detection in the field[J]. Biosystems engineering, 2019, 187: 39-52.
23	LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles[EB/OL]. arXiv: 2206.02424, 2022.
24	HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2020: 1577-1586.
25	RAO Y M, ZHAO W L, TANG Y S, et al. HorNet: Efficient high-order spatial interactions with recursive gated convolutions [EB/OL]. [2022-07-28].
26	TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2020: 10778-10787.
27	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]// European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19.
28	TERVEN J R, ESPARZA D M C. A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond[EB/OL]. arXiv:2304.00501, 2023.
29	高腾, 张先武, 李柏. 深度学习在安全帽佩戴检测中的应用研究综述[J]. 计算机工程与应用, 2023, 59(6): 13-29.
	GAO T, ZHANG X W, LI B. Review on application of deep learning in helmet wearing detection[J]. Computer engineering and applications, 2023, 59(6): 13-29.
30	REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: A metric and a loss for bounding box regression[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2019: 658-666.
31	TONG Z, CHEN Y, XU Z, et al. Wise-IoU: Bounding box regression loss with dynamic focusing mechanism[EB/OL]. arXiv: 2301.10051, 2023.

类别	训练集	验证集	测试集	总计
蝽卵	748	111	110	969
稻螟蛉	1 586	128	180	1 894
大螟幼虫	789	80	125	994
红白蝙蝠蛾	385	60	39	484
黄肩型稻绿椿	835	205	151	1 191
点斑型稻绿蝽	924	171	115	1 210
全绿型稻绿蝽	778	95	113	986
蝗虫	1 245	189	240	1 674

名称	试验配置
编程语言	Python3.9
深度学习框架	Pytorch2.0.1
CPU	Intel（R）Core（TM）i9-10900X CPU @3.70 GHz
内存	128 GB
GPU	NVIDIA GeForce RTX 3090
CUDA	11.7
开发平台	Pycharm 2022.2

名称	试验配置
Epochs	200
Batch_size	64
Momentum	0.937
Weight decay	0.000 5
Learn rate	0.01
Optimizer	Adam
Workers	4
Imgsz	640

Methods	Precision	Recall	mAP@0.5	mAP@0.5∶0.95	Modelsize/M	FPS
YOLOv5s	0.959	0.91	0.947	0.721	13.70	66.7
YOLOv8n	0.958	0.939	0.964	0.739	5.93	72.6
YOLOv8n-GSCONV	0.965	0.954	0.970	0.741	20.20	56.4
YOLOv8n-BiFPN	0.982	0.975	0.975	0.745	5.93	68.5
YOLOv8n-CBAM	0.975	0.976	0.982	0.783	5.95	62.6
YOLOv8n-Extend	0.984	0.975	0.99	0.811	6.07	65.5

Methods	mAP@0.5	FPS
YOLOv5s	0.947	66.7
YOLOv5s-Jetson	0.912	54.7
YOLOv8n	0.964	72.6
YOLOv8n-Jetson	0.922	62.8
YOLOv8n-Extend	0.990	65.5
YOLOv8n-Extend-Jetson	0.968	57.6