[1]赵玉清,贾奥莹,王白娟,等.柑橘果实采摘机器人目标识别算法研究进展[J].江苏农业学报,2024,(08):1552-1560.[doi:doi:10.3969/j.issn.1000-4440.2024.08.019]
　ZHAO Yuqing,JIA Aoying,WANG Baijuan,et al.Research progress on target recognition algorithms for citrus fruit picking robots[J].,2024,(08):1552-1560.[doi:doi:10.3969/j.issn.1000-4440.2024.08.019]
点击复制

柑橘果实采摘机器人目标识别算法研究进展()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年08期
页码:
1552-1560
栏目:
综述
出版日期:
2024-08-30

文章信息/Info

Title:
Research progress on target recognition algorithms for citrus fruit picking robots
作者:
赵玉清1; 2; 3; 贾奥莹1; 3; 王白娟4; 邓航宇1; 3; 向铠铭1; 3; 张悦3; 5
(1.云南农业大学机电工程学院,云南昆明650201；2.昆明理工大学交通工程学院,云南昆明650093；3.云南省作物生产与智慧农业重点实验室,云南昆明650201；4.云南农业大学茶学院,云南昆明650201；5.云南农业大学大数据学院,云南昆明650201）
Author(s):
ZHAO Yuqing1; 2; 3; JIA Aoying1; 3; WANG Baijuan4; DENG Hangyu1; 3; XIANG Kaiming1; 3; ZHANG Yue3; 5
(1.Faculty of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, China;2.Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650093, China;3.The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province, Kunming 650201, China;4.College of Tea Science, Yunnan Agricultural University, Kunming 650201, China;5.College of Big Data, Yunnan Agricultural University, Kunming 650201, China)
关键词:
柑橘; 采摘机器人; 目标识别; 研究进展
Keywords:
citrus; picking robot; target recognition; research progress
分类号:
TP391.41
DOI:
doi:10.3969/j.issn.1000-4440.2024.08.019
文献标志码:
A
摘要:
水果采摘机器人作业是提高水果采摘效率,解决劳动力短缺的重要途经。准确高效的柑橘果实采摘机器人已成为农业机器人研究的热点之一。目标识别是柑橘果实采摘机器人精准高效完成采摘作业的首要任务与关键技术。本文综述了近年来应用于柑橘果实采摘机器人中的传统目标识别算法、机器学习算法和深度学习算法,阐述了不同目标识别算法的特征及应用情况,最后指出当前柑橘果实目标识别算法存在的问题,并对柑橘果实目标识别算法发展趋势进行展望。
Abstract:
Fruit picking robot operation is an important way to improve fruit picking efficiency and solve labor shortage. Accurate and efficient citrus fruit picking robot has become one of the hotspots in agricultural robot research. Target recognition is the primary task and key technology for citrus fruit picking robots to complete picking operations accurately and efficiently. The traditional target recognition algorithms, machine learning algorithms and deep learning algorithms applied to citrus fruit picking robots in recent years were reviewed in this paper, and the characteristics and applications of different target recognition algorithms were discussed. Finally, the problems existing in the current citrus fruit target recognition algorithms were pointed out, and the future development trend of citrus fruit target recognition algorithms was prospected.

参考文献/References:

[1]郑涵,罗强,张益维,等. 柑橘采摘机器人目标检测算法研究进展[J]. 南方农业,2022,16(21):119-122.
[2]国家统计局. 2023中国统计年鉴[M]. 北京:中国统计出版社,2023.
[3]李会宾,史云. 果园采摘机器人研究综述[J]. 中国农业信息,2019,31(6):1-9.

[4]毛嘉威. 柑橘采摘机械臂及其控制系统设计[D]. 成都:四川农业大学,2021.
[5]XIAO Y, TIAN Z, YU J, et al. A review of object detection based on deep learning[J]. Multimedia Tools and Applications,2020,79(33/34):23729-23791.
[6]孔翰博,王克强,蔡肯,等. 基于机器视觉的采摘机器人目标识别定位研究应用进展[J]. 电子技术与软件工程,2022(10):160-165.
[7]TIAN Y, YANG G, WANG Z, et al. Instance segmentation of apple flowers using the improved Mask R-CNN model[J]. Biosystems Engineering,2020,193:264-278.
[8]宋怀波,尚钰莹,何东健. 果实目标深度学习识别技术研究进展[J]. 农业机械学报,2023,54(1):1-19.
[9]KURTULMUS F, LEE W S, VARDAR. A green citrus detection using ‘eigenfruit’, color and circular Gabor texture features under natural outdoor conditions[J]. Computers and Electronics in Agriculture,2011,78(2):140-149.
[10]LU J, SANG N. Detecting citrus fruits and occlusion recovery under natural illumination conditions[J]. Computers and Electronics in Agriculture,2015,110:121-130.
[11]邹继欣,崔天时,邢伟. 基于DSP的柑橘果实自动识别系统[J]. 农机化研究,2015,37(2):166-170.
[12]邹伟. 基于机器视觉技术的柑橘果实成熟度分选研究[J]. 农业与技术,2023,43(17):41-44.
[13]张珺. 基于机器学习的智能农机采摘控制实验与仿真[J]. 集成电路应用,2023,40(6):70-72.
[14]方东玉. 基于SVM的柑橘品质检测技术[D]. 长沙:中南林业科技大学,2016.
[15]李华. 基于机器视觉的柑橘外观品质鉴定技术研究[D]. 郑州:河南农业大学,2024.
[16]LIN G, TANG Y, ZOU X, et al. In-field citrus detection and localisation based on RGB-D image analysis[J]. Biosystems Engineering,2019,186:34-44.
[17]申飘. 基于图像处理与机器学习的柑橘表面缺陷检测研究[D]. 长沙:中南林业科技大学,2023.
[18]CAI C, ZHOU G, LU C. Citrus surface defect identification based on PCS-2D-Otsu and CGWO-DT-SVM[J]. Multimedia Tools and Applications,2023，83（15）：43649-43672.
[19]BEHERA S K, ANITHA K, AMAT R, et al. ResNet101-SVM:hybrid convolutional neural network for citrus fruits classification[J]. Journal of Intelligent & Fuzzy Systems,2024,46(3):7035-7045.
[20]BERTHELOT D, CARLINI N, GOODFELLOW I, et al. Mixmatch:a holistic approach to semi-supervised learning[C/OL]//WALLACH H, LAROCHELLE H, BAYGELZIMER A, et al. Advances in neural information processing systems32(NeurIPS 2019). San Diego,USA:NeurIPS Foundation,2019. https://arxiv.org/pdf/1905.02249v2.
[21]吕佳,李帅军,曾梦瑶,等. 基于半监督SPM-YOLO V5的套袋柑橘检测算法[J]. 农业工程学报,2022,38(18):204-211.
[22]ROY P, KISLAY A, PLONSKI P A, et al. Vision-based preharvest yield mapping for apple orchards[J]. Computers and Electronics in Agriculture,2019,164:104897.
[23]CIARFUGLIA T A, MOTOI I M, SARACENI L, et al. Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data[J]. Computers and Electronics in Agriculture,2023,205:107624.
[24]ALBELWI S. Survey on self-supervised learning:auxiliary pretext tasks and contrastive learning methods in imaging[J]. Entropy,2022,24(4):551.
[25]姜欣悦. 基于图像识别的单株成熟柑橘树产量预估研究[J]. 南方农机,2022,53(23):66-68.
[26]SUN B, LIU K, FENG L, et al. The surface defects detection of citrus on trees based on a support vector machine[J]. Agronomy,2022,13(1):43.
[27]赵永强,饶元,董世鹏,等. 深度学习目标检测方法综述[J]. 中国图像图形学报,2020,25(4):629-654.
[28]董戈. 基于深度学习和图像处理的水果收获机器人抓取系统[J]. 农机化研究,2021,43(3):260-264.
[29]WANG Z, UNDERWOOD J, WALSH K B. Machine vision assessment of mango orchard flowering[J]. Computers and Electronics in Agriculture,2018,151:501-511.
[30]GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE. Proceedings of the IEEE conference on computer vision and pattern recognition. New Jersey:IEEE Computer Society,2014:580-587.
[31]GIRSHICK R. Fast R-cnn[C]// IEEE. Proceedings of the IEEE international conference on computer vision. New Jersey:IEEE Computer Society,2015:1440-1448.
[32]CAI Z, VASCONCELOS N. Cascade R-cnn:delving into high quality object detection[C]//IEEE. Proceedings of the IEEE conference on computer vision and pattern recognition. New Jersey:IEEE Computer Society,2018:6154-6162.
[33]杨国. 基于深度学习的自然环境下柑橘检测研究[D]. 长沙:中南林业科技大学,2023.
[34]任会,朱洪前. 基于深度学习的目标橘子识别方法研究[J]. 计算机时代,2021(1):57-60,64.
[35]YANG C H, XIONG L Y, WANG Z, et al. Integrated detection of citrus fruits and branches using a convolutional neural network[J]. Computers and Electronics in Agriculture,2020,174:105469.
[36]黄磊磊,苗玉彬. 基于深度学习的重叠柑橘分割与形态复原[J]. 农机化研究,2023,45(10):70-75.
[37]BEHERA S K, RATH A K, SETHY P K. Fruits yield estimation using Faster R-CNN with MIoU[J]. Multimedia Tools and Applications,2021,80(12):19043-19056.
[38]LU J, YANG R, YU C, et al. Citrus green fruit detection via improved feature network extraction[J]. Frontiers in Plant Science,2022,13:946154.
[39]MIN W, WANG Z, YANG J, et al. Vision-based fruit recognition via multi-scale attention CNN[J]. Computers and Electronics in Agriculture,2023,210:107911.

[40]孙国奇. 基于深度学习的果园环境下柑橘果实与枝干分割定位方法研究[D]. 桂林:广西师范大学,2023.

[41]贾艳平,桑妍丽,李月茹. 基于改进Faster R-CNN模型的水果分类识别[J]. 食品与机械,2023,39(8):129-135.

[42]LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//ECCV. European conference on computer vision 2016(Part I). Amsterdam:Springer International Publishing,2016:21-37.

[43]HOWARD A G, ZHU M, CHEN B, et al. Mobilenets:efficient convolutional neural networks for mobile vision applications[Z/OL]. （2017-04-17）. http://arxiv.org/abs/1704.04861.

[44]ZHANG X, ZHOU X, LIN M, et al. Shufflenet:an extremely efficient convolutional neural network for mobile devices[C]//IEEE:Proceedings of the IEEE conference on computer vision and pattern recognition. New Jersey:IEEE Computer Society,2018:6848-6856.

[45]LIU Z, LIN Y, CAO Y, et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//IEEE. Proceedings of the IEEE/CVF international conference on computer vision. New Jersey:IEEE Computer Society,2021:10012-10022.

[46]宋中山,刘越,郑禄,等. 基于改进YOLO V3的自然环境下绿色柑橘的识别算法[J]. 中国农机化学报,2021,42(11):159-165.

[47]陈文康,陆声链,刘冰浩,等. 基于改进YOLO V4的果园柑橘检测方法研究[J]. 广西师范大学学报(自然科学版),2021,39(5):134-146.

[48]刘芳. 基于YOLO V5的柑橘果实目标检测研究[J]. 信息与电脑(理论版),2022,34(2):152-154.

[49]CHEN W, LU S, LIU B, et al. Citrus YOLO:a algorithm for citrus detection under orchard environment based on YOLO V4[J]. Multimedia Tools and Applications,2022,81(22):31363-31389.
[50]庄昊龙,周嘉灏,林毓翰,等. 基于改进YOLO V5+DeepSort的柑橘果实识别与计数研究[J]. 南方农机,2023,54(15):9-13.
[51]JING J, ZHAI M, DOU S, et al. Optimizing the YOLO V7-Tiny model with multiple strategies for citrus fruit yield estimation in complex scenarios[J]. Agriculture,2024,14(2):303.
[52]易诗,李俊杰,张鹏,等. 基于特征递归融合YOLO V4网络模型的春见柑橘检测与计数[J]. 农业工程学报,2021,37(18):161-169.
[53]黄彤镔,黄河清,李震,等. 基于YOLO V5改进模型的柑橘果实识别方法[J]. 华中农业大学学报,2022,41(4):170-177.
[54]LIU X, LI G, CHEN W, et al. Detection of dense citrus fruits by combining coordinated attention and cross-scale connection with weighted feature fusion[J]. Applied Sciences,2022,12(13):6600.
[55]李子茂,李嘉晖,尹帆,等. 基于可形变卷积与SimAM注意力的密集柑橘检测算法[J]. 中国农机化学报,2023,44(2):156-162.
[56]周剑,徐中贵,谢知音. 基于空间金字塔池化的YOLOv3的柑橘多分级研究[J]. 现代农业装备,2023,44(2):35-43,97.
[57]LI C, MA W, LIU F, et al. Recognition of citrus fruit and planning the robotic picking sequence in orchards[J]. Signal, Image and Video Processing,2023,17(8):4425-4434.
[58]蹇川,郑永强,刘艳梅,等. 目标检测算法YOLO V5s用于柑桔成熟果实检测的改进[J]. 中国南方果树,2024,53(1):224-231.
[59]汤旸,杨光友,王焱清. 面向采摘机器人的改进YOLO V3-tiny轻量化柑橘识别方法[J]. 科学技术与工程,2022,22(31):13824-13832.
[60]杨国,黄文静,朱洪前,等. 自然环境下黄绿柑橘检测通用模型的构建[J]. 林业工程学报,2022,7(5):134-141.
[61]YANG R, HU Y, YAO Y, et al. Fruit target detection based on BCo-YOLO V5 model[J]. Mobile Information Systems,2022,2022:8457173.
[62]殷献博,邓小玲,兰玉彬,等. 基于改进YOLO X-Nano算法的柑橘梢期长势智能识别[J]. 华南农业大学学报,2023,44(1):142-150.
[63]黄辉,苏成悦,王银海. 基于改进YOLO V5的柑橘目标识别研究[J]. 电脑与信息技术,2024,32(2):27-29.
[64]帖军,赵捷,郑禄,等. 改进YOLO V5模型在自然环境下柑橘识别的应用[J]. 中国农业科技导报,2024,26(7):1-10.
[65]刘洁,李燕,肖黎明,等. 基于改进YOLO V4模型的橙果识别与定位方法[J]. 农业工程学报,2022,38(12):173-182.
[66]姜锟. 柑橘采摘机器人目标识别、定位与采摘研究[D]. 镇江:江苏大学,2023.
[67]王乙涵. 基于改进YOLO V7的自然环境下柑橘果实识别与定位方法研究[D]. 成都:四川农业大学,2023
[68]KONG D, WANG J, ZHANG Q, et al. Research on fruit spatial coordinate positioning by combining improved yolov8s and adaptive multi-resolution model[J]. Agronomy,2023,13(8):2122.
[69]熊俊涛,霍钊威,黄启寅,等. 结合主动光源和改进YOLO V5s模型的夜间柑橘检测方法[J]. 华南农业大学学报,2024,45(1):97-107.
[70]孙宝霞,梁翠晓,刘凯,等. 夜间环境下树上柑橘表征缺陷深度学习检测方法[J]. 林业工程学报,2021,6(6):148-155.
[71]FENG J, WANG Z, WANG S, et al. MSDD-YOLOX:An enhanced YOLO X for real-time surface defect detection of oranges by type[J]. European Journal of Agronomy,2023,149:126918.
[72]贾雪莹,赵春江,周娟,等. 基于改进YOLO V7模型的柑橘表面缺陷在线检测[J]. 农业工程学报,2023,39(23):142-151.

相似文献/References:

[1]刘波,杨长辉,熊龙烨,等.果园自然环境下采摘机器人路径识别方法[J].江苏农业学报,2019,(05):1222.[doi:doi:10.3969/j.issn.1000-4440.2019.05.032]
　LIU Bo,YANG Chang-hui,XIONG Long-ye,et al.Path recognition method of picking robot based on orchard natural environment[J].,2019,(08):1222.[doi:doi:10.3969/j.issn.1000-4440.2019.05.032]
[2]雷旺雄,卢军.葡萄采摘机器人采摘点的视觉定位[J].江苏农业学报,2020,(04):1015.[doi:doi:10.3969/j.issn.1000-4440.2020.04.029]
　LEI Wang-xiong,LU Jun.Visual positioning method for picking point of grape picking robot[J].,2020,(08):1015.[doi:doi:10.3969/j.issn.1000-4440.2020.04.029]
[3]沈丹,杨莉,胡威,等.柑橘胁迫响应基因WRKY47的克隆与表达分析[J].江苏农业学报,2021,(01):129.[doi:doi:10.3969/j.issn.1000-4440.2021.01.017]
　SHEN Dan,YANG Li,HU Wei,et al.Cloning and expression analysis of stress response gene WRKY47 in citrus[J].,2021,(08):129.[doi:doi:10.3969/j.issn.1000-4440.2021.01.017]
[4]陈光明,孔浩然,章永年,等.苹果机器人采摘存在的关键问题及对策[J].江苏农业学报,2022,38(06):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]
　CHEN Guang-ming,KONG Hao-ran,ZHANG Yong-nian,et al.Key problems and countermeasures of apple machine picking[J].,2022,38(08):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]

备注/Memo

备注/Memo:
收稿日期:2024-04-15基金项目:云南省科技厅重大科技专项（202302AE0900200105）；云南省科技厅科技计划农业联合专项（202301BD070001-105）作者简介:赵玉清(1975-),男,白族,云南大理人,硕士,教授，主要研究方向为智能农业机械装备。(E-mail)331863839@qq.com通讯作者:张悦,(E-mail)zyue1234@163.com
更新日期/Last Update: 2024-09-18