基于深度学习的垃圾分类方法综述

doi:10.19678/j.issn.1000-3428.0061338

摘要/Abstract

摘要： 垃圾分类是保护生态环境、促进经济发展的有效措施，利用深度学习进行垃圾分类已成为当前学术界和工业界的研究热点。传统垃圾分类主要由人工进行分拣和分类，存在劳动强度大、分选效率低、工作环境差等缺点，急需智能化、自动化的分类方法来替代。近年来研究人员已经开始初步探索利用深度学习技术进行垃圾分类并提出一些有效的方法。从方法、数据集和研究方向等方面分析深度学习垃圾分类方法的研究现状，介绍不同深度学习模型在垃圾分类中的应用和发展，研究基于ResNet方法、基于DenseNet方法、基于单阶段目标检测方法和基于卷积神经网络与迁移学习相结合方法等多种典型方法的性能和特点并对比其优缺点，对现有的垃圾分类公开数据集进行概述与总结。在此基础上，分析深度学习在垃圾分类领域面临的挑战，并对其发展趋势及未来的研究方向进行展望。

关键词: 垃圾分类, 深度学习, 卷积神经网络, ResNet系统, DensenNet系统, 单阶段目标检测

Abstract: Garbage classification is an effective measure to protect ecological environment and promote economic development.Traditional garbage classification relies heavily on manual work in waste sorting.It is labor-intensive and limited in efficiency, and workers have to suffer from the poor environment.In recent years, intelligent and automated garbage classification methods using deep learning has become a hot research topic.This paper reviews the existing studies of deep learning-based garbage classification from the perspectives of method, dataset and research direction, and introduces the application and development of different deep learning models in garbage classification.The paper analyzes the performance and features of various typical methods, such as the ResNet-based method, DenseNet-based method, single-stage target detection method and the method combining convolution neural network with transfer learning, comparing their advantages and disadvantages.In addition, the paper summarizes the existing public datasets of garbage classification.On this basis, the paper discusses the current challenges faced by deep learning applications in the field of garbage classification, and the development trends as well as future research directions.

Key words: garbage classification, deep learning, Convolutional Neural Network(CNN), ResNet system, DensenNet system, single-stage target detection

中图分类号:

TP391

李金玉, 陈晓雷, 张爱华, 李策, 林冬梅. 基于深度学习的垃圾分类方法综述[J]. 计算机工程, 2022, 48(2): 1-9.

LI Jinyu, CHEN Xiaolei, ZHANG Aihua, LI Ce, LIN Dongmei. Survey of Garbage Classification Methods Based on Deep Learning[J]. Computer Engineering, 2022, 48(2): 1-9.

http://www.ecice06.com/CN/Y2022/V48/I2/1

图/表 6

20220226123925

20220226123930

20220226123934

20220226123937

20220226123941

20220226123947

参考文献

[1] LECUN Y, BENGIO Y, HINTON G.Deep learning[J].Nature, 2015, 521(7553):436-444.
[2] DENG L, YU D.Deep learning:methods and applications[J].Foundations and Trends in Signal Processing, 2014, 7(3/4):197-387.
[3] JAISAL E K.Data-mining and analytics:rising concerns over privacy and people's security[C]//Proceedings of the 42nd Indian Social Science Congress Conference.New Delhi, Indian:[s.n.], 2018:346-455.
[4] HE K, ZHANG X, REN S, et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[5] ADEDEJI O, WANG Z.Intelligent waste classification system using deep learning convolutional neural network[J].Procedia Manufacturing, 2019, 35:607-612.
[6] PLATT J.Sequential minimal optimization:a fast algorithm for training support vector machines[EB/OL].[2020-03-01].https://www.researchgate.net/publication/2624239.
[7] SONG F, ZHANG Y, ZHANG J.Optimization of CNN-based garbage classification model[C]//Proceedings of the 4th IEEE International Conference on Computer Science and Application Engineering.Washington D.C., USA:IEEE Press, 2020:1-5.
[8] SZEGEDY C, IOFFE S, VANHOUCKE V, et al.Inception-v4, inception-ResNet and the impact of residual connections on learning[EB/OL].[2020-03-01].https://arxiv.org/pdf/1602.07261.pdf.
[9] 董子源, 韩卫光.基于卷积神经网络的垃圾图像分类算法[J].计算机系统应用, 2020, 29(8):199-204. DONG Z Y, HAN W G.Garbage image classification algorithm based on convolutional neural network[J].Computer Systems & Applications, 2020, 29(8):199-204.(in Chinese)
[10] WANG Y, ZHANG X.Autonomous garbage detection for intelligent urban management[C]//Proceedings of the 2nd International Conference on Electronic Information Technology and Computer Engineering.Shanghai:EDP Sciences, 2018:140-147.
[11] VO A H, SON L H, VO M T, et al.A novel framework for trash classification using deep transfer learning[J].IEEE Access, 2019, 7:178631-178639.
[12] KANG Z, YANG J, LI G, et al.An automatic garbage classification system based on deep learning[J].IEEE Access, 2020, 8:140019-140029.
[13] 袁建野, 南新元, 蔡鑫, 等.基于轻量级残差网路的垃圾图片分类方法[J].环境工程, 2021, 39(2):110-115. YUAN J Y, NAN X Y, CAI X, et al.Junk image classification method based on lightweight residual network[J].Environmental Engineering, 2021, 39(2):110-115.(in Chinese)
[14] 梁斌, 刘全, 徐进.基于多注意力卷积神经网络的特定目标情感分析[J].计算机研究与发展, 2017, 54(8):1724-173. LIANG B, LIU Q, XU J.Target-specific sentiment analysis based on multi-attention convolutional neural network[J].Computer Research and Development, 2017, 54(8):1724-173.(in Chinese)
[15] ZHU X, CHENG D, ZHANG Z, et al.An empirical study of spatial attention mechanisms in deep networks[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:6688-6697.
[16] GAN Y Q, GE B.Research on lightweight convolutional neural network in garbage classification[C]//Proceedings of IOP Conference on Earth and Environmental Science.[S.1.]:IOP Publishing, 2021:320-231.
[17] HUANG G, LIU Z, VAN DER M L, et al.Densely connected convolutional networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:4700-4708.
[18] SUSANTH G S, LIVINGSTON L M J, LIVINGSTON L G.Garbage waste segregation using deep learning techniques[C]//Proceedings of IOP Conference on Materials Science and Engineering.[S.1.]:IOP Publishing, 2021:204-213.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[EB/OL].[2020-03-01].https://web.cs.ucdavis.edu/~yjlee/teaching/ecs289g-winter2018/alexnet.pdf.
[20] BIRCANOGLU C, ATAY M, BESER F, et al.Recyclenet:intelligent waste sorting using deep neural networks[C]//Proceedings of 2018 IEEE Innovations in Intelligent Systems and Applications.Washington D.C., USA:IEEE Press, 2018:1-7.
[21] MAO W L, CHEN W C, WANG C T, et al.Recycling waste classification using optimized convolutional neural network[J].Resources, Conservation and Recycling, 2021, 164(1):105-112.
[22] 刘俊明, 孟卫华.基于深度学习的单阶段目标检测算法研究综述[J].航空兵器, 2020, 27(3):44-53. LIU J M, MENG W H.A survey of research on single-stage target detection algorithms based on deep Learning[J].Aero Weaponry, 2020, 27(3):44-53.(in Chinese)
[23] LIU Y, GE Z, LÜ G, et al.Research on automatic garbage detection system based on deep learning and narrowband internet of things[J].Journal of Physics, 2018, 1069:120-132.
[24] HOWARD A G, ZHU M, CHEN B, et al.Mobilenets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2020-03-01].https://arxiv preprint arxiv:1704.04861.
[25] 宁凯, 张东波, 印峰, 等.基于视觉感知的智能扫地机器人的垃圾检测与分类[J].中国图象图形学报, 2019, 24(8):1358-1368. NING K, ZHANG D B, YIN F.et al.Garbage detection and classification of intelligent sweeping robot based on visual perception[J].Chinese Journal of Image and Graphics, 2019, 24(8):1358-1368.(in Chinese)
[26] KUMAR S, YADAV D, GUPTA H, et al.A novel YOLOv3 algorithm-based deep learning approach for waste segregation:towards smart waste management[J].Electronics, 2021, 10(1):14.
[27] 吴子沛.面向垃圾分类的瓶罐识别分类系统[D].邯郸:河北工程大学, 2020. WU Z P.Recognition and classification system of bottles and cans for garbage classification[D].Handan:Hebei University of Engineering, 2020.(in Chinese)
[28] YE A, PANG B, JIN Y, et al.A YOLO-based neural network with VAE for intelligent garbage detection and classification[C]//Proceedings of the 3rd IEEE International Conference on Algorithms, Computing and Artificial Intelligence.Washington D.C., USA:IEEE Press, 2020:1-7.
[29] MA W, WANG X, YU J.A lightweight feature fusion single shot multibox detector for garbage detection[J].IEEE Access, 2020, 8:188577-188586.
[30] LIU W, ANGUELOV D, ERHAN D, et al.SSD:single shot multibox detector[C]//Proceedings of European Cconference on Computer Vision.Berlin, Germany:Springer, 2016:21-37.
[31] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2999-3007.
[32] FENG J, TANG X.Office garbage intelligent classification based on inception-v3 transfer learning model[C//Proceedings of the 4th IEEE International Conference on Control Engineering and Artificial Intelligence.Washington D.C., USA:IEEE Press, 2020:8-15.
[33] SZZEGEDY C, VANHOUCKE V, IOFFE S, et al.Rethinking the inception architecture for computer vision[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:2818-2826.
[34] 高明, 陈玉涵, 张泽慧, 等.基于新型空间注意力机制和迁移学习的垃圾图像分类算法[J].系统工程理论与实践, 2021, 41(2):498-512. GAO M, CHEN Y H, ZHANG Z H, et al.Garbage image classification algorithm based on new spatial attention mechanism and transfer learning[J].System Engineering Theory and Practice, 2021, 41(2):498-512.(in Chinese)
[35] 康庄, 杨杰, 郭濠奇.基于机器视觉的垃圾自动分类系统设计[J].浙江大学学报(工学版), 2020, 54(7):1272-1280. KANG Z, YANG J, GUO H Q.Design of automatic garbage classification system based on machine vision[J].Journal of Zhejiang University(Engineering Science Edition), 2020, 54(7):1272-1280.(in Chinese)
[36] SHI C, XIA R, WANG L.A Novel multi-branch channel expansion network for garbage image classification[J].IEEE Access, 2020, 8:154436-154452.
[37] CHOLLET F.Xception:deep learning with depthwise separable convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1251-1258.
[38] CAO L, XIANG W.Application of convolutional neural network based on transfer learning for garbage classification[C]//Proceedings of the 5th IEEE Information Technology and Mechatronics Engineering Conference.Washington D.C., USA:IEEE Press, 2020:1032-1036.
[39] PANWAR H, GUPTA P K, SIDDIQUI M K, et al.Aqua vision:automating the detection of waste in water bodies using deep transfer learning[J].Case Studies in Chemical and Environmental Engineering, 2020:100-116.
[40] YANG J, ZENG Z, WANG K, et al.GarbageNet:a unified learning framework for robust garbage classification[J].IEEE Transactions on Artificial Intelligence, 2021, 58(1):3214-3226.
[41] YANG M, THUNG G.Classification of trash for recyclability status[EB/OL].[2020-03-01].http://cs229.stanford.edu/proj2016/report.
[42] MITTAL G, YAGNIK K B, GARG M, et al.Spotgarbage:smartphone app to detect garbage using deep learning[C]//Proceedings of 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing.New York, USA:ACM Press, 2016:940-945.
[43] PROENCA P F, SIMOES P.TACO:trash annotations in context for litter detection[EB/OL].[2020-03-01].https://arxiv preprint arxiv:2003.06975.
[44] YOO D, KWEON I S.Learning loss for active learning[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:93-102.
[45] CHANGPINYO S, CHAO W L, GONG B, et al.Synthesized classifiers for zero-shot learning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:5327-5336.
[46] PAN S J, TSANG I W, KWOK J T, et al.Domain adaptation via transfer component analysis[J].IEEE Transactions on Neural Networks, 2011, 22(2):199-210.
[47] TAN C, SUN F, KONG T, et al.A survey on deep transfer learning[C]//Proceedings of International Conference on Artificial Neural Networks.Berlin, Germany:Springer, 2018:270-279.
[48] 李志华, 于杨.基于检测的多目标跟踪算法综述[J].物联网技术, 2021, 11(4):20-24. LI Z H, YU Y.Survey of detection-based multi-target tracking algorithms[J].Internet of Things Technology, 2021, 11(4):20-24.(in Chinese)
[49] LIN T Y, DOLLAR P, GIRSHIICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2117-2125.
[50] SINGH B, DAVIS L S.An analysis of scale invariance in object detection snip[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:3578-3587.

选择文件类型/文献管理软件名称

选择包含的内容