|本期目录/Table of Contents|

[1]李龙,李梦霞,李志良.基于改进YOLO v8的水稻害虫识别方法[J].江苏农业科学,2024,52(20):209-219.
 Li Long,et al.Rice pest identification method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(20):209-219.
点击复制

基于改进YOLO v8的水稻害虫识别方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第20期
页码:
209-219
栏目:
病虫害智能检测
出版日期:
2024-10-20

文章信息/Info

Title:
Rice pest identification method based on improved YOLO v8
作者:
李龙 李梦霞 李志良
长江大学计算机科学学院,湖北荆州 434000
Author(s):
Li Longet al
关键词:
目标检测水稻害虫深度学习YOLO v8极化自注意力
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
实时监测稻田害虫泛滥情况是预防水稻产量降低的重要手段之一。针对当前的目标检测算法在实际稻田环境下检测精度较低且模型计算量较大、难以实现实时检测等问题,提出一种基于YOLO v8的改进的水稻害虫识别算法YOLO v8-SDPS。首先在主干网络中用SD_Conv卷积替代标准卷积,重构特征提取模块,在降低参数量的同时尽可能保留害虫目标的边缘特征信息,提升对害虫目标的特征提取能力;其次在颈部引入基于Slim-Neck范式的GSConv模块和VoV-GSCSP模块,在减少模型计算量的同时提升模型的检测精度;最后在SPPF层前引入PSA注意力模块,降低背景的噪声干扰,使模型更加关注个体的空间位置信息。用本研究提出的算法在经数据增强后的自建水稻害虫数据集上进行试验,结果表明,YOLO v8-SDPS获得86.6%的平均检测精度,相较于原始YOLO v8n模型提升41百分点。同时改进后的模型参数量为2.62 M,计算量为7.5 GFLOPs,相较于基准模型分别降低16.8%和157%,实现了模型轻量化和较高检测精度的平衡。在害虫小且密集、背景干扰严重、光照强烈等复杂环境下,YOLO v8-SDPS均能较好地识别出目标个体,有效地降低漏检率和误检率,具有较好的鲁棒性,可为稻田实时巡检提供有效技术支持。
Abstract:
-

参考文献/References:

[1]褚世海,李儒海,黄启超,等. 湖北省水稻田农药使用现状调查[J]. 中国植保导刊,2022,42(12):65-68.
[2]钟朝军,戴长庚,毛向华. 水稻主要虫害绿色防控技术研究[J]. 耕作与栽培,2022,42(6):123-124.
[3]蒋心璐,陈天恩,王聪,等. 农业害虫检测的深度学习算法综述[J]. 计算机工程与应用,2023,59(6):30-44.
[4]Zou K L,Ge L Z,Zhou H,et al. Broccoli seedling pest damage degree evaluation based on machine learning combined with color and shape features[J]. Information Processing in Agriculture,2021,8(4):505-514.
[5]田冉,陈梅香,董大明,等. 红外传感器与机器视觉融合的果树害虫识别及计数方法[J]. 农业工程学报,2016,32(20):195-201.
[6]Rustia D J A,Lin C E,Chung J Y,et al. Application of an image and environmental sensor network for automated greenhouse insect pest monitoring[J]. Journal of Asia-Pacific Entomology,2020,23(1):17-28.
[7]王春桃,梁炜健,郭庆文,等. 农业害虫智能视觉检测研究综述[J]. 中国农机化学报,2023,44(7):207-213.
[8]温艳兰,陈友鹏,王克强,等. 基于机器视觉的病虫害检测综述[J]. 中国粮油学报,2022,37(10):271-279.
[9]Domingues T,Brando T,Ferreira J C.Machine learning for detection and prediction of crop diseases and pests:a comprehensive survey[J]. Agriculture,2022,12(9):1350.
[10]Kasinathan T,Uyyala S R.Machine learning ensemble with image processing for pest identification and classification in field crops[J]. Neural Computing and Applications,2021,33(13):7491-7504.
[11]吴子炜,夏芳,陆林峰,等. 基于改进YOLO v5的水稻主要害虫识别方法[J]. 江苏农业科学,2023,51(21):218-224.
[12]温艳兰,陈友鹏,王克强,等. 基于迁移学习和改进残差网络的复杂背景下害虫图像识别[J]. 江苏农业科学,2023,51(8):171-177.
[13]Krizhevsky A,Sutskever I,Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90.
[14]Xiao J Q,Zhou Z Y. Research progress of RNN language model[C]//2020 IEEE International Conference on Artificial Intelligence and Computer Applications(ICAICA).Dalian,China:IEEE,2020:1285-1288.
[15]Vaswani A,Shazeer N,Parmar N,et al. Attention is all you need[EB/OL]. (2017-06-12)[2024-04-01]. https://arxiv.org/abs/1706.03762.
[16]慕君林,马博,王云飞,等. 基于深度学习的农作物病虫害检测算法综述[J]. 农业机械学报,2023,54(增刊2):301-313.
[17]佘颢,吴伶,单鲁泉. 基于SSD网络模型改进的水稻害虫识别方法[J]. 郑州大学学报(理学版),2020,52(3):49-54.
[18]范春全,何彬彬. 基于迁移学习的水稻病虫害识别[J]. 中国农业信息,2020,32(2):36-44.
[19]Wu X P,Zhan C,Lai Y K,et al. IP102:a large-scale benchmark dataset for insect pest recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA:IEEE,2019:8779-8788.
[20]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).Las Vegas,NV,USA:IEEE,2016:779-788.
[21]Redmon J,Farhadi A. YOLO9000:better,faster,stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu,HI,USA:IEEE,2017:6517-6525.
[22]Redmon J,Farhadi A. YOLO v3:an incremental improvement[EB/OL]. (2018-04-08)[2023-12-16]. https://arxiv.org/abs/1804.02767v1.
[23]Thuan D. Evolution of Yolo algorithm and YOLO v5:the State-of-the-Art object detention algorithm[J/OL]. Oulu University of Applied Sciences,2021:1-61(2021-03-04)[2023-04-27]. https://urn.fi/URN:NBN:fi:amk-202103042892.
[24]Fu J,Liu J,Tian H J,et al. Dual attention network for scene segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA:IEEE,2019:3141-3149.
[25]Sunkara R,Luo T. No more strided convolutions or pooling:a new CNN building block for low-resolution images and Small objects[EB/OL]. (2022-08-07)[2023-11-13]. https://doi.org/10.48550/arXiv.2208.03641.
[26]毛远宏,贺占庄,刘露露. 目标跟踪中基于深度可分离卷积的剪枝方法[J]. 西安交通大学学报,2021,55(1):52-59.
[27]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]. (2022-06-06)[2023-11-01]. https://arxiv.org/abs/2206.02424v3.
[28]Liu H J,Liu F Q,Fan X Y,et al. Polarized self-attention:towards high-quality pixel-wise mapping[J]. Neurocomputing,2022,506:158-167.

相似文献/References:

[1]罗巍,陈曙东,王福涛,等.基于深度学习的大型食草动物种群监测方法[J].江苏农业科学,2020,48(20):247.
 Luo Wei,et al.Monitoring method of large herbivore population based on deep learning[J].Jiangsu Agricultural Sciences,2020,48(20):247.
[2]罗智心,姚静,张茹,等.二化螟36 d标准化饲养技术与管理体系[J].江苏农业科学,2021,49(24):100.
 Luo Zhixin,et al.A 36-days standardized mass rearing technique and management system for rice stem borer,Chilo suppressalis (Lepidoptera:Crambidae)[J].Jiangsu Agricultural Sciences,2021,49(20):100.
[3]陈恩会,褚姝频,王炜,等.基于RetinaNet模型的梨小食心虫智能识别计数方法[J].江苏农业科学,2021,49(24):205.
 Chen Enhui,et al.Intelligent recognition and counting method of Grapholitha molesta based on RetinaNet model[J].Jiangsu Agricultural Sciences,2021,49(20):205.
[4]陶雪阳,施振旦,郭彬彬,等.基于RFID与目标检测的种鹅个体产蛋信息监测方法[J].江苏农业科学,2023,51(5):200.
 Tao Xueyang,et al.Monitoring method of individual egg-laying information of breeding geese based on RFID and object detection[J].Jiangsu Agricultural Sciences,2023,51(20):200.
[5]严陈慧子,田芳明,谭峰,等.基于改进YOLOv4的水稻病害快速检测方法[J].江苏农业科学,2023,51(6):187.
 Yanchen Huizi,et al.Rapid detection method of rice diseases based on improved YOLOv4[J].Jiangsu Agricultural Sciences,2023,51(20):187.
[6]周绍发,肖小玲,刘忠意,等.改进的基于YOLOv5s苹果树叶病害检测[J].江苏农业科学,2023,51(13):212.
 Zhou Shaofa,et al.Improved apple leaf disease detection based on YOLOv5s[J].Jiangsu Agricultural Sciences,2023,51(20):212.
[7]姜国权,杨正元,霍占强,等.基于改进YOLOv5网络的疏果前苹果检测方法[J].江苏农业科学,2023,51(14):205.
 Jiang Guoquan,et al.Apple detection method before thinning fruit based on improved YOLOv5 model[J].Jiangsu Agricultural Sciences,2023,51(20):205.
[8]王圆圆,林建,王姗.基于YOLOv4-tiny模型的水稻早期病害识别方法[J].江苏农业科学,2023,51(16):147.
 Wang Yuanyuan,et al.An early rice disease recognition method based on YOLOv4-tiny model[J].Jiangsu Agricultural Sciences,2023,51(20):147.
[9]吴子炜,夏芳,陆林峰,等.基于改进YOLO v5的水稻主要害虫识别方法[J].江苏农业科学,2023,51(21):218.
 Wu Ziwei,et al.An identification method for rice major pests based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2023,51(20):218.
[10]倪智涛,胡伟健,李宝山,等.一种基于图像分类与目标检测协同的番茄细粒度病害识别方法[J].江苏农业科学,2023,51(22):221.
 Ni Zhitao,et al.A novel method for tomato fine-grained disease recognition based on image classification and target detection[J].Jiangsu Agricultural Sciences,2023,51(20):221.

备注/Memo

备注/Memo:
收稿日期:2024-04-09
基金项目:国家自然科学基金(编号:62173049、62273060);湖北省教育厅科学研究计划(编号:D20211302)。
作者简介:李龙(2000—),男,湖北武汉人,硕士研究生,研究方向为深度学习与目标检测。E-mail:2022710628@yangtzeu.edu.cn。
通信作者:李梦霞,博士,副教授,硕士生导师,研究方向为油气田软件开发、最优化理论与算法。E-mail:limengxia@yangtzeu.edu.cn。
更新日期/Last Update: 2024-10-20