基于卷积神经网络的经济林产品检测与分选研究进展

编号 lyqk009587

中文标题 基于卷积神经网络的经济林产品检测与分选研究进展

作者 张晓  刘英  李玉荣  费叶琦 

作者单位 1. 南京林业大学机械电子工程学院，南京 210037;
2. 农业农村部南京农业机械化研究所，南京 210014

期刊名称 世界林业研究 

年份 2021 

卷号 34

期号 5

栏目名称 专题论述 

中文摘要 经济林作为重要森林资源，其种植面积及产品产量逐年增加。随着科学技术的不断创新与升级，经济林产品加工产业快速发展、衍伸产品日趋增多，急需智能化检测、采收与分选技术与装备。深度融合人工智能技术与经济林产品加工产业，是实现高效化、精准化、智能化发展的重要手段之一。文中综合比较了深度学习技术中不同卷积神经网络算法及模型的优缺点，综述了其在经济林产品检测与分选中的研究进展，并针对研究应用过程中存在的问题提出了进一步深入研究建议，以期为经济林产品检测与分选的智能化发展提供参考。

关键词 卷积神经网络  经济林  目标检测  产品分选  应用研究 

基金项目 江苏省农业科技自主创新资金项目[CX（18）3071]；江苏省重点研发计划（产业前瞻与关键核心技术）项目（BE2019112）

英文标题 Research on Detection and Sorting of Products from Non-Wood Forest Based on Convolution Neural Network

作者英文名 Zhang Xiao, Liu Ying, Li Yurong, Fei Yeqi

单位英文名 1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China;
2. Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China

英文摘要 Non-wood forest is an important forest resource, and its planting area and yield have been increasing year by year. With the innovation and upgrading of science and technology, its product processing industry has been developing rapidly, with more augmented product. In this sense, the technologies and equipment for intelligent detection, picking and sorting are urgently needed. The integration of deep integration of artificial intelligence technology with non-wood forest products industry is one of the important means to achieve efficient, precise and intelligent development. This paper comprehensively compares the advantages and disadvantages of different convolution neural network algorithms and models based on deep learning technology, reviews the research progress in detection and sorting of the products from non-wood forest, and puts forward suggestions in view of the problems rising in the process of research and application, with an expectation to provide a reference for the intelligent development of product detection and sorting for non-wood forest.

英文关键词 convolution neural network;non-wood forest;target detection;product sorting;application research

起始页码 81

截止页码 86

投稿时间 2021/4/2

最后修改时间 2021/5/10

作者简介 张晓，女，汉族，博士生，主要从事机器视觉、木材与林果检测方面的研究，E-mail：zhangxiao_xhx@126.com

通讯作者介绍 刘英，女，汉族，博士，教授，主要从事无损检测、图像处理方面的研究，E-mail：lying_new@163.com

E-mail zhangxiao_xhx@126.com;lying_new@163.com

分类号 S7-05, S759.3

DOI 10.13348/j.cnki.sjlyyj.2021.0048.y

参考文献 [1] 吕永来. “十三五”头两年全国经济林产品产量完成情况分析[J]. 中国林业产业,2019(5):6-13.
[2] 许斐然, 贾卫国, 吕柳, 等. 我国经济林产业发展问题分析与对策研究[J]. 中国林业经济,2021(3):1-3, 48.
[3] 吕永来. 2016: 林业产业发展成果丰硕[J]. 中国林业产业,2017(7):38-39.
[4] 南玉龙, 张慧春, 郑加强, 等. 深度学习在林业中的应用[J]. 世界林业研究,2021. DOI:10.13348/j.cnki.sjlyyj.2021.0020.y
[5] 王金鹏, 高凯, 姜洪喆, 等. 基于改进的轻量化卷积神经网络火龙果检测方法[J]. 农业工程学报,2020,36(20):218-225.
[6] CHEN Y, ZHAO X, JIA X. Spectral–spatial classification of hyperspectral data based on deep belief network[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(6):2381-2392.
[7] FARHANA S, ABU S, PARAMARTHA D. Evolution of image segmentation using deep convolutional neural network: a survey[J]. Knowledge-Based Systems, 2020:201-202.
[8] JOSE N, MARCO M, RUBER H. A review of convolutional neural network applied to fruit image processing[J]. Applied Sciences, 2020, 10(10):3443-3450.
[9] 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.
[10] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C].2018 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Salt Lake City, UT, 2018: 7132-7141.
[11] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[12] HE K, GKIOXARI G, DOLLAR P, et al. Mask RCNN[C]// Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV)， Venice, Italy, 2017: 2980-2988.
[13] 许高建, 张蕴, 赖小燚. 基于Faster R-CNN深度网络的茶叶嫩芽图像识别方法[J]. 光电子?激光,2020,31(11):1131-1139.
[14] 朱超伟.灵武长枣图像识别系统的开发[D].银川: 宁夏大学, 2020.
[15] 闫建伟, 赵源, 张乐伟, 等. 改进Faster-RCNN自然环境下识别刺梨果实[J]. 农业工程学报,2019,35(18):143-150.
[16] 陈斌, 饶洪辉, 王玉龙, 等. 基于 Faster-RCNN的自然环境下油茶果检测研究[J]. 江西农业学报,2021,33(1):67-70.
[17] 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.
[18] 张习之. 基于卷积神经网络的自然光照下油茶果识别技术研究[D].长沙: 中南林业科技大学, 2019.
[19] 倪超, 张云, 高捍东, 等. 基于多目视觉的马尾松苗木形态学参数提取研究[J]. 林业工程学报,2018,3(2):123-128.
[20] BARGOTI S, UNDERWOOD J P. Image segmentation for fruit detection and yield estimation in apple orchards[J]. Field Robot, 2017, 34(6):1039-1060.
[21] MADELEINE S, SUCHET B, JAMES U. Image based mango fruit detection, localisation and yield estimation using multiple view geometry[J]. Sensors, 2016, 16(11):1915. DOI:10.3390/s16111915
[22] 李成吉, 张淑娟, 孙海霞, 等. 基于计算机视觉的核桃外观缺陷检测[J]. 现代食品科技,2019,35(8):247-253, 246.
[23] 雷凯栋. 基于高光谱、计算机视觉对核桃壳、仁及分心木的识别[D].太原: 山西农业大学, 2018.
[24] 段宇飞, 皇甫思思, 王焱清, 等. 基于机器视觉的油茶果果壳与茶籽分选方法研究[J]. 中国农机化学报,2020,41(6):171-178.
[25] 海潮.基于深度学习的红枣缺陷识别技术研究[D].郑州: 郑州大学, 2019.
[26] ZHOU H, ZHUANG Z, LIU Y, et al. Defect classification of green plums based on deep learning[J]. Sensors, 2020, 20(23):6993. DOI:10.3390/s20236993
[27] 谢为俊, 丁冶春, 王凤贺, 等. 基于卷积神经网络的油茶籽完整性识别方法[J]. 农业机械学报,2020,51(7):13-21.
[28] 王立扬, 张瑜, 沈群, 等. 基于改进型LeNet-5的苹果自动分级方法[J]. 中国农机化学报,2020,41(7):105-110.
[29] 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, 18(4):1126-1137.
[30] ALTAHERI H, ALSULAIMAN M, MUHAMMAD G. Date fruit classification for robotic harvesting in a natural environment using deep learning[J]. IEEE Access, 2019, 7(1):117115-117133.
[31] GU Y, CHEN B, XU C, et al. Deep learning trackers review and challenge[J]. Journal of Information Hiding and Privacy Protection, 2019, 1(1):23-33.
[32] STEINBRENER J, POSCH K, LEITNER R. Hyperspectral fruit and vegetable classification using convolutional neural networks[J]. Computers and Electronics in Agriculture, 2019, 162(6):364-372.
[33] 张泽苗, 霍欢, 赵逢禹. 深层卷积神经网络的目标检测算法综述[J]. 小型微型计算机系统,2019,40(9):1825-1831.

发布日期 2021-06-30

PDF全文 浏览全文