|本期目录/Table of Contents|

[1]刘忠意,魏登峰,李萌,等.基于改进YOLO v5的橙子果实识别方法[J].江苏农业科学,2023,51(19):173-181.
 Liu Zhongyi,et al.Orange fruit recognition method based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2023,51(19):173-181.
点击复制

基于改进YOLO v5的橙子果实识别方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第19期
页码:
173-181
栏目:
农业工程与信息技术
出版日期:
2023-10-05

文章信息/Info

Title:
Orange fruit recognition method based on improved YOLO v5
作者:
刘忠意魏登峰李萌周绍发鲁力董雨雪
长江大学计算机科学学院,湖北荆州 434000
Author(s):
Liu Zhongyiet al
关键词:
YOLO v5橙子识别RepVGG损失函数ECA注意力鬼影混洗卷积
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对自然环境下橙子检测存在枝叶遮挡、相邻果实重叠等情况而导致检测效果差的问题,提出一种改进的YOLO v5方法。首先,在主干网络部分使用RepVGG(re-param VGG)模块替换原始C3模块,加强网络对特征信息的提取能力;其次,在颈部网络使用鬼影混洗卷积(ghost-shuffle convolution)代替原有的标准卷积,能够在保证精度的前提下,降低模型参数量;再次,在预测头前加入ECA(efficient channel attention)注意力模块,能够更加准确定位目标信息;最后,引入EIOU(efficient intersection over union)损失函数加速预测框的收敛,提高其回归精度。改进的YOLO v5网络在自然环境下的橙子检测中平均精度达到90.1%,相比于目前热门的检测网络CenterNet、YOLO v3和YOLO v4其在识别效果方面有一定的提升。可见,所提出的改进网络在橙子检测上更有优势,能为今后智能采摘机器人的研发提供理论支撑和技术参考。
Abstract:
-

参考文献/References:

[1]Gao J B,Dai S H,Huang J J,et al. Kiwifruit detection method in orchard via an improved light-weight YOLO v4[J]. Agronomy,2022,12(9):2081.
[2]Hussin R,Juhari M R,Kang N W,et al. Digital image processing techniques for object detection from complex background image[J]. Procedia Engineering,2012,41:340-344.
[3]Payne A B,Walsh K B,Subedi P P,et al. Estimation of mango crop yield using image analysis-Segmentation method[J]. Computers and Electronics in Agriculture,2013,91:57-64.
[4]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.
[5]Parvathi S,Tamil S S.Detection of maturity stages of coconuts in complex background using Faster R-CNN model[J]. Biosystems Engineering,2021,202:119-132.
[6]Tian Y N,Yang G D,Wang Z,et al. Apple detection during different growth stages in orchards using the improved YOLO-V3 model[J]. Computers and Electronics in Agriculture,2019,157:417-426.
[7]Chen W K,Lu S L,Liu B H,et al. CitrusYOLO:a algorithm for Citrus detection under orchard environment based on YOLO v4[J]. Multimedia Tools and Applications,2022,81(22):31363-31389.
[8]Wang C Y,Liao H Y M,Wu Y H,et al. CSPNet:a new backbone that can enhance learning capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle,2020:1571-1580.
[9]李刚,齐铭伟,张飞扬,等. 基于RepVGG-YOLOv4的焦罐提升机状态检测[J]. 工业控制计算机,2022,35(6):43-45.
[10]高梦圆,马双宝,董玉婕,等. 基于实例分割苹果采摘机器人视觉定位与检测[J]. 江苏农业科学,2022,50(3):201-208.
[11]Li H L,Li J,Wei H B,et al. Slim-neck by GSConv:a better design paradigm of detector architectures for autonomous vehicles[DB/OL]. ArXiv(Computer Science).(2022-06-06)[2022-12-29]. https://arxiv.org/vc/arxiv/papers/2206/2206.02424v1.pdf.
[12]张欣怡,张飞,郝斌,等. 基于改进YOLO v5的口罩佩戴检测算法[J/OL]. 计算机工程.(2022-12-08)[2022-12-29]. https://kns.cnki.net/kcms/detail//31.1289.tp.20221207.1007.002.html.
[13]王卓,王健,王枭雄,等. 基于改进YOLO v4的自然环境苹果轻量级检测方法[J]. 农业机械学报,2022,53(8):294-302.
[14]Wang Q L,Wu B G,Zhu P F,et al. ECA-net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle,2020:11531-11539.
[15]Hu J,Shen L,Sun G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake,2018:7132-7141.
[16]Zhang Y F,Ren W Q,Zhang Z,et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing,2022,506:146-157.

相似文献/References:

[1]杜鹏程,蒋笃忠,向阳,等.基于YOLO v5s目标检测算法的烤烟鲜叶成熟度识别方法[J].江苏农业科学,2023,51(19):158.
 Du Pengcheng,et al.Identification method for fresh leaf maturity of flue-cured tobacco based on YOLO v5s target detection algorithm[J].Jiangsu Agricultural Sciences,2023,51(19):158.
[2]李滨,樊健.基于YOLO v5的水稻害虫分类[J].江苏农业科学,2024,52(2):175.
 Li Bin,et al.Classification of rice pests based on YOLO v5[J].Jiangsu Agricultural Sciences,2024,52(19):175.
[3]蔡易南,肖小玲.基于改进YOLO v5n的葡萄叶病虫害检测模型轻量化方法[J].江苏农业科学,2024,52(7):198.
 Cai Yinan,et al.Lightweight method of grape leaf diseases and insect pests detection model based on improved YOLO v5n[J].Jiangsu Agricultural Sciences,2024,52(19):198.
[4]温彬彬,张华,孟祥龙.基于改进YOLO v5的轻量化苹果检测方法[J].江苏农业科学,2024,52(12):217.
 Wen Binbin,et al.A lightweight apple detection method based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2024,52(19):217.
[5]吴坚,秦玉广.基于改进YOLO v5的农田苗草检测方法[J].江苏农业科学,2024,52(13):197.
 Wu Jian,et al.Detection of seedlings and weeds in farmland based on an improved YOLO v5 algorithm[J].Jiangsu Agricultural Sciences,2024,52(19):197.
[6]李炳鑫,宋涛,高婕,等.基于YOLO v5模型的缺钙草莓叶片识别方法[J].江苏农业科学,2024,52(20):74.
 Li Bingxin,et al.Identification method of calcium-deficient strawberry leaves based on YOLO v5 model[J].Jiangsu Agricultural Sciences,2024,52(19):74.
[7]王博,胡蓉华.基于轻量化神经网络的桃树叶片病害检测方法[J].江苏农业科学,2025,53(5):138.
 Wang Bo,et al.A peach leaf disease detection method based on lightweight neural network[J].Jiangsu Agricultural Sciences,2025,53(19):138.

备注/Memo

备注/Memo:
收稿日期:2023-02-02
基金项目:新疆维吾尔自治区创新人才建设专项自然科学计划(自然科学基金)基金项目(编号:2020D01A132)。
作者简介:刘忠意(1999—),男,湖北黄冈人,硕士研究生,从事深度学习与目标检测研究。E-mail:2021710621@yangtzeu.edu.cn。
通信作者:魏登峰,硕士,副教授,从事计算机网络、软件工程、人工智能研究。E-mail:100933@yangtzeu.edu.cn。
更新日期/Last Update: 2023-10-05