|本期目录/Table of Contents|

[1]赵方,左官芳,顾思睿,等.基于改进YOLO v5s的温室番茄检测模型轻量化研究[J].江苏农业科学,2024,52(8):200-209.
 Zhao Fang,et al.Lightweight research of greenhouse tomato detection model based on improved YOLO v5s[J].Jiangsu Agricultural Sciences,2024,52(8):200-209.
点击复制

基于改进YOLO v5s的温室番茄检测模型轻量化研究(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8期
页码:
200-209
栏目:
农业工程与信息技术
出版日期:
2024-04-20

文章信息/Info

Title:
Lightweight research of greenhouse tomato detection model based on improved YOLO v5s
作者:
赵方1左官芳12顾思睿2任肖恬1陶旭2
1.南京信息工程大学电子与信息工程学院,江苏南京 210044; 2.无锡学院电子信息工程学院,江苏无锡 214105
Author(s):
Zhao Fanget al
关键词:
番茄小目标检测YOLO v5s轻量化网络注意力机制
Keywords:
-
分类号:
S126
DOI:
-
文献标志码:
A
摘要:
番茄检测模型的检测速度和识别精度会直接影响到番茄采摘机器人的采摘效率,因此,为实现复杂温室环境下对番茄精准实时的检测与识别,为采摘机器人视觉系统研究提供重要的参考价值,提出一种以YOLO v5s模型为基础,使用改进的MobileNet v3结构替换主干网络,平衡模型速度和精度。同时,在颈部网络引入Ghost轻量化模块和CBAM注意力机制,在保证模型检测精度的同时提高模型的检测速度。通过扩大网络的输入尺寸,并设置不同尺度的检测网络来提高对远距离小目标番茄的识别精度。采用SIoU损失函数来提高模型训练的收敛速度。最终,改进YOLO v5s模型检测番茄的精度为94.4%、召回率为92.5%、均值平均精度为96.6%、模型大小为71 MB、参数量为3.69 M、浮点运算(FLOPs)为6.0 G,改进的模型很好地平衡了模型检测速度和模型识别精度,能够快速准确地检测和识别复杂温室环境下的番茄,且对远距离小目标番茄等复杂场景都能实现准确检测与识别,该轻量化模型未来能够应用到嵌入式设备,对复杂环境下的温室番茄实现实时准确的检测与识别。
Abstract:
-

参考文献/References:

[1] 王海楠,弋景刚,张秀花. 番茄采摘机器人识别与定位技术研究进展[J]. 中国农机化学报,2020,41(5):188-196.
[2]李寒,陶涵虓,崔立昊,等. 基于SOM-K-means算法的番茄果实识别与定位方法[J]. 农业机械学报,2021,52(1):23-29.
[3]孙建桐,孙意凡,赵然,等. 基于几何形态学与迭代随机圆的番茄识别方法[J]. 农业机械学报,2019,50(增刊1):22-26,61.
[4]封靖川,胡小龙,李斌. 基于特征融合的目标检测算法研究[J]. 数字技术与应用,2018,36(12):114-115.
[5]Liu W,Anguelov D,Erhan D,et al. SSD:single shot MultiBox detector[M]//Computer Vision-ECCV 2016.Cham:Springer International Publishing,2016:21-37.
[6]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. Las Vegas,2016:779-788.
[7]Girshick R,Donahue J,Darrell T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition.ACM,2014:580-587.
[8]Girshick R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. ACM,2015:1440-1448.
[9]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.
[10]He K M,Gkioxari G,Dollár P,et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision. Venice,2017:2980-2988.
[11]张文静,赵性祥,丁睿柔,等. 基于Faster R-CNN算法的番茄识别检测方法[J]. 山东农业大学学报(自然科学版),2021,52(4):624-630.
[12]Yuan T,Lyu L,Zhang F,et al. Robust cherry tomatoes detection algorithm in greenhouse scene based on SSD[J]. Agriculture,2020,10(5):160.
[13]何斌,张亦博,龚健林,等. 基于改进YOLO v5的夜间温室番茄果实快速识别[J]. 农业机械学报,2022,53(5):201-208.
[14]Shorten C,Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data,2019,6(1):60.
[15]Howard A,Sandler M,Chen B,et al. Searching for MobileNet v3[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul,2019:1314-1324.
[16]Howard A G,Zhu M,Chen B,et al. Mobilenets:effificient convolutional neural networks for mobile vision applications[EB/OL].(2017-04-17)[2023-04-24]. https://arxiv.org/abs/1704.04861.
[17]Sandler M,Howard A,Zhu M L,et al. MobileNet v2:inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,2018:4510-4520.
[18]Hu J,Shen L,Sun G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,2018:7132-7141.
[19]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. Seattle,2020:1577-1586.
[20]Woo S,Park J,Lee J Y,et al. CBAM:convolutional block attention module[M]//Computer Vision-ECCV 2018.Cham:Springer International Publishing,2018:3-19.
[21]Zheng Z H,Wang P,Ren D W,et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics,2022,52(8):8574-8586.
[22]Zheng Z H,Wang P,Liu W,et al. Distance-IoU loss:faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12993-13000.
[23]Gevorgyan Z. SIoU loss:more powerful learning for bounding box regression[EB/OL]. (2022-05-25)[2023-04-24]. https://arxiv.org/abs/2205.12740.

相似文献/References:

[1]何从亮,毛久庚,甘小虎,等.玻璃温室番茄长季节基质袋栽培技术[J].江苏农业科学,2013,41(04):158.
[2]李永灿,余文贵,陈怀谷,等.番茄灰霉病菌产毒条件优化[J].江苏农业科学,2013,41(05):94.
 Li Yongcan,et al.Optimization of toxigenic conditions of tomato Botrytis cinerea[J].Jiangsu Agricultural Sciences,2013,41(8):94.
[3]赵秋月,甘潇,张广臣.Na2CO3胁迫对番茄幼苗生长的影响[J].江苏农业科学,2013,41(05):128.
 Zhao Qiuyue,et al.Effect of Na2CO3 stress on growth of tomato seedlings[J].Jiangsu Agricultural Sciences,2013,41(8):128.
[4]耿德刚,徐俊伟,戈振超,等.温室大棚番茄滴灌试验研究及效益分析[J].江苏农业科学,2013,41(05):132.
 Geng Degang,et al.Drip irrigation experimental and benefit analysis on greenhouse tomato[J].Jiangsu Agricultural Sciences,2013,41(8):132.
[5]杜中平,聂书明.不同配方基质对番茄生长特性、光合特性及产量的影响[J].江苏农业科学,2013,41(05):138.
 Du Zhongping,et al.Effects of different substrates on growth,photosynthetic characteristics and yield of tomato[J].Jiangsu Agricultural Sciences,2013,41(8):138.
[6]赵河,毛秀杰,叶景学.抗叶霉病不同基因型番茄的光合特性[J].江苏农业科学,2014,42(11):185.
 Zhao He,et al(8).Photosynthetic characteristics of different genotypes of tomato with resistance to leaf mold[J].Jiangsu Agricultural Sciences,2014,42(8):185.
[7]陈素娟,孙娜娜.不同基质配比对番茄秧苗生长的影响[J].江苏农业科学,2013,41(06):128.
 Chen Sujuan,et al.Effect of different substrate compositions on growth of tomato seedling[J].Jiangsu Agricultural Sciences,2013,41(8):128.
[8]孙禛禛,吴秋霞,温新宇,等.转反义LetAPX基因番茄抗氧化酶活性在苗期、花期、果期的变化[J].江苏农业科学,2015,43(12):188.
 Sun Zhenzhen,et al.Study on antioxidant enzymes activity during seedling,flowering and fruiting of tomato with antisense LetAPX gene[J].Jiangsu Agricultural Sciences,2015,43(8):188.
[9]李晓慧,张恩让,何玉安,等.亚高温及外源物质调节下番茄的生理响应[J].江苏农业科学,2013,41(07):135.
 Li Xiaohui,et al.Physiological response of tomato under the regulation of sub-high temperature and exogenous substances[J].Jiangsu Agricultural Sciences,2013,41(8):135.
[10]李建宏,张楠,张泽,等.番茄红素提取与测定方法的优化[J].江苏农业科学,2013,41(08):259.
 Li Jianhong,et al.Optimization of lycopene extraction and determination method[J].Jiangsu Agricultural Sciences,2013,41(8):259.

备注/Memo

备注/Memo:
收稿日期:2023-06-05
基金项目:江苏省高等学校基础科学(自然科学)研究面上项目(编号:22KJB140015);江苏省无锡市创新创业资金“太湖之光”科技攻关计划(基础研究)项目(编号:K20221043);教育部产学合作协同育人项目(编号:220604210140248)。
作者简介:赵方(1997—),男,山东临沂人,硕士,主要从事嵌入式人工智能。E-mail:zhaofang_1997@163.com。
通信作者:左官芳,硕士,高级工程师,主要从事嵌入式设计研究。E-mail:zgf@cwxu.edu.cn。
更新日期/Last Update: 2024-04-20