基于深度学习的小浆果一体化智能采摘与分选研究进展

编号 lyqk008591

中文标题 基于深度学习的小浆果一体化智能采摘与分选研究进展

作者 王德镇  黄玉萍  刘英 

作者单位 南京林业大学机械电子工程学院, 南京 210037

期刊名称 世界林业研究 

年份 2020 

卷号 33

期号 5

栏目编号 1

栏目名称 专题论述 

中文摘要 小浆果因具有较高的营养价值和保健作用深受人们喜爱，被国际市场誉为第3代水果。随着市场需求量的增加，林业小浆果的智能采摘与分选成为一种新的趋势。目前，由于现有技术自动化和智能化程度不高，导致大量人力、物力的投入。深度学习方法的飞速发展促进了检测技术的精确作业和检测精度的提高。文中概述了深度学习的发展进程，通过总结国内外关于深度学习方法在小浆果采摘与分选中的应用，提出深度学习方法在实际应用过程中存在的问题及解决措施，并展望深度学习方法在小浆果智能采摘与分选检测方面的发展趋势。

关键词 深度学习  小浆果  智能采摘  智能分选  检测 

基金项目 江苏省高等学校自然科研究面上项目“基于空间分辨光谱农产品深度信息多元组合的无损检测研究”（19KJB210003）。

英文标题 Research Progress on Integrated Intelligent Picking and Sorting of Small Berries Based on Deep Learning

作者英文名 Wang Dezhen, Huang Yuping, Liu Ying

单位英文名 College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China

英文摘要 Small berries are the favorite fruit of people as the third generation fruit known in the international market, due to the high nutrition and healthcare function. As the market demand increases, the intelligent picking and sorting for small berries become a new trend. At present, the commonly used technologies have the low degree of automation and intelligence, resulting in more human and material input, while the rapid development of the deep learning technology improves the accuracy and precision for detection technology. The paper reviews the development process of deep learning, summarizes the applications of deep learning to small berry picking and sorting, and identifies the problems and resolutions for the practical applications of deep learning. Finally, the development trend of intelligent picking and sorting detection for small berry is prospected by using deep learning.

英文关键词 deep learning;small berry;intelligent picking;intelligent sorting;detection

起始页码 59

截止页码 64

投稿时间 2019/11/1

最后修改时间 2020/4/17

作者简介 王德镇,男,硕士研究生,主要研究方向:机电一体化,E-mail:m15205196102@163.com。

通讯作者介绍 黄玉萍,女,博士,主要研究方向:农产品无损检测研究,E-mail:h.y.p_2010@163.com。

E-mail 黄玉萍,女,博士,主要研究方向:农产品无损检测研究,E-mail:h.y.p_2010@163.com。

分类号 S776.2

DOI 10.13348/j.cnki.sjlyyj.2020.0065.y

参考文献 [1] 李亚东, 唐雪东, 袁菲, 等. 我国小浆果生产现状、问题和发展趋势[J].东北农业大学学报, 2011,42(1):1-10.
[2] 刘莉莉, 姜传福. 蓝莓的营养成分及其保健功能研究[J].农业科技与装备, 2013(9):62-63.
[3] 刘欢.浆果之王蓝莓的营养保健作用研究[J].中国新技术新产品, 2009(19):228.
[4] 叶万军, 宋丽娟, 王志伟, 等. 黑龙江小浆果资源的综合利用与开发[J].中国林副特产, 2018(4):62-64.
[5] 成亮,王立杰,张国庆.一种自适应多功能水果采摘装置[J].林业工程学报,2020,5(2):130-136.
[6] 洪添胜, 李震, 吴春胤, 等. 高光谱图像技术在水果品质无损检测中的应用[J].农业工程学报, 2007(11):280-285.
[7] 彭翔, 邾继贵. 机器视觉检测与应用专题前言[J].光学学报, 2018,38(8):9-10.
[8] BAIETTO M, WILSON A D.Electronic-nose applications for fruit identification, ripeness and quality grading[J].Sensors, 2015.DOI:10.3390/s150100899.
[9] 张保华, 李江波, 樊书祥, 等.高光谱成像技术在果蔬品质与安全无损检测中的原理及应用[J].光谱学与光谱分析, 2014,34(10):2743-2751.
[10] WANG Z, HU M, ZHAI G. Application of deep learning architectures for accurate and rapid detection of internal mechanical damage of blueberry using hyperspectral transmittance data[J]. Sensors, 2018.DOI:10.3390/s18041126.
[11] STEINBRENER J, POSCH K, LEITNER R. Hyperspectral fruit and vegetable classification using convolutional neural networks[J]. Computers and Electronics in Agriculture, 2019, 162:364-372. DOI:10.1016/j.compag.2019.04.019.
[12] 胡侯立, 魏维, 胡蒙娜. 深度学习算法的原理及应用[J].信息技术, 2015(2):175-177.
[13] HINTON G E. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G.ImageNet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012.DOI:10.1145/3065386.
[15] 岳永鹏. 深度无监督学习算法研究[D].成都:西南石油大学, 2015.
[16] YIN Z, LIU W, CHAWLA S. Adversarial attack, defense, and applications with deep learning frameworks[J]. Deep Learning Applications for Cyber Security,2019. DOI:10.1007/978-3-030-13057-2_1.
[17] NONGMEIKAPAM K, KUMAR W K, MEETEI O N, et al. Increasing the effectiveness of handwritten manipuri meetei-mayek character recognition using multiple-hog-feature descriptors[J]. Sadhana, 2019, 44(5). DOI:10.1007/s12046-019-1086-0.
[18] GIRSHICK R. Fast R-CNN[J]. Computer Science, 2015. DOI:10.1109/ICCV.2015.169.
[19] TAIGMAN Y, YANG M, RANZATO M, et al. Deepface:closing the gap to human-level performance in face verification[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014.
[20] 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 & Machine Intelligence, 2015, 39(6):1137-1149.
[21] LE Q V, RANZATO M, MONGA R, et al. Building high-level features using large scale unsupervised learning[C]. International Conference on Machine Learning, Edinburgh, 2012.
[22] 郑胤, 陈权崎, 章毓晋. 深度学习及其在目标和行为识别中的新进展[J].中国图象图形学报, 2014,19(2):175-184.
[23] 韩非.蓝莓机器视觉识别与标定技术研究[D].哈尔滨:东北林业大学, 2011.
[24] CHITRAKAR R, HUANG C. Selection of candidate support vectors in incremental SVM for network intrusion detection[J].Telecom Power Technology, 2014, 45(3):231-241.
[25] MATHIAS M, BENENSON R, PEDERSOLI M, et al. Face detection without bells and whistles[C].European Conference on Computer Vision, Marseille, 2014.
[26] 曹艳玲. 基于BBO_MLP和纹理特征的图像分类算法研究[D]. 西安:西安电子科技大学, 2015.
[27] GONZALEZ S, ARELLANO C, TAPIA J E. Deepblueberry:quantification of blueberries in the wild using instance segmentation[J]. IEEE Access, 2019, 7:105776-105788. DOI:10.1109/ACCESS.2019.2933062.
[28] SCHUMANN A W, MOOD N S, MUNGOFA P D K, et al. Detection of three fruit maturity stages in wild blueberry fields using deep learning artificial neural networks[C]. ASABE Annual International Meeting, Boston, 2019.
[29] 李鑫.用于机器采摘的高架草莓识别与分级方法的研究[D].南京:东南大学, 2018.
[30] TU S, XUE Y, ZHENG C, et al. Detection of passion fruits and maturity classification using red-green-blue depth images[J]. Biosystems Engineering, 2018, 175:156-167. DOI:10.1016/j.biosystemseng.2018.09.004.
[31] JIANG Y, LI C, TAKEDA F.Nondestructive detection and quantification of blueberry bruising using near-infrared (nir) hyperspectral reflectance imaging[J]. Scientific Reports, 2016, 6(1):35679. DOI:10.1038/srep35679.
[32] ZORAN Z, Ferdinand V D H. Efficient adaptive density estimation per image pixel for the task of background subtraction[J]. Pattern Recognition Letters, 2006,27(7):773-780.
[33] LI H, LEE W S, WANG K. Identifying blueberry fruit of different growth stages using natural outdoor color images[J]. Computers and Electronics in Agriculture, 2014, 106:91-101. DOI:10.1016/j.compag.2014.05.015.
[34] FENG L, ZHU S, ZHOU L, et al. Detection of subtle bruises on winter jujube using hyperspectral imaging with pixel-wise deep learning method[J]. IEEE Access, 2019, 7:64494-64505.
[35] GU Y X, CHEN B J, XU C, ZHANG Y F, et al. Deep learning trackers review and challenge[J]. Journal of Information Hiding and Privacy Protection, 2019,1(1):23-33.
[36] KOIRALA A, WALSH K B, WANG Z, et al. Deep learning-method overview and review of use for fruit detection and yield estimation[J]. Computers and Electronics in Agriculture, 2019, 162:219-234. DOI:10.1016/j.compag.2019.04.017.
[37] 李彦冬.基于卷积神经网络的计算机视觉关键技术研究[D].成都:电子科技大学, 2017.
[38] AUDEBERT N,SAUX B,LEFÈVRE S. Deep learning for classification of hyperspectral data:a comparative review[J].IEEE Geoscience and Remote Sensing Magazine,2019,7(2):159-173.
[39] 王裕民, 顾乃杰, 张孝慈. 多GPU环境下的卷积神经网络并行算法[J].小型微型计算机系统, 2017,38(3):536-539.
[40] GRIFFITHS D, BOEHM J. A review on deep learning techniques for 3D sensed data classification[J].Remote Sensing, 2019,11(12):1499. DOI:10.3390/rs11121499.
[41] FANG Q,LI H, LUO X, et al. Detecting non-hardhat-use by a deep learning method from far-field surveillance videos[J]. Automation in Construction,2018,85:1-9.
[42] 刘万军, 梁雪剑, 曲海成.自适应增强卷积神经网络图像识别[J].中国图象图形学报, 2017,22(12):1723-1736.

PDF全文 浏览全文