[1]王明吉a,陈秋梦a,任福深b,等.基于yolov4的垃圾检测系统[J].工业仪表与自动化装置,2021,(05):20-23+72.[doi:10.19950/j.cnki.cn61-1121/th.2021.05.005]
　WANG Mingjia,CHEN Qiumenga,REN Fushenb,et al.Garbage detection system based on yolov4[J].Industrial Instrumentation & Automation,2021,(05):20-23+72.[doi:10.19950/j.cnki.cn61-1121/th.2021.05.005]
点击复制

基于yolov4的垃圾检测系统

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年05期
页码:
20-23+72
栏目:
出版日期:
2021-10-15

文章信息/Info

Title:
Garbage detection system based on yolov4
作者:
王明吉a; 陈秋梦a1; 任福深b; 胡 庆b; 刘 博a; 王一安b
东北石油大学 a.物理与电子工程学院；b.机械工程学院，黑龙江 大庆 163318
Author(s):
WANG Mingjia; CHEN Qiumenga; REN Fushenb; HU Qingb; LIU Boa; WANG Yianb
a.School of Physics and Electronic Engineering;
b.School of Mechanical Engineering, Northeast Petroleum University, Heilongjiang Daqing 163318,China
关键词:
垃圾分类; 定位; k-means++; 摄像头
Keywords:
garbage classification;  targeting;  k-means++;  camera
分类号:
TP399
DOI:
10.19950/j.cnki.cn61-1121/th.2021.05.005
文献标志码:
A
摘要:
为解决垃圾分类困难问题，根据大量垃圾图片的特点，提出了基于yolov4的垃圾检测的方法，实现垃圾的自动识别分类和定位。该方法通过手机拍摄以及百度等收集不同种类的垃圾图像集，运用图像增强的方式进行图像预处理，再利用迁移学习模型和k-mean++聚类算法进行垃圾网络分类模型的训练测试，最后将训练好的模型通过摄像头对采集的垃圾图片实时识别分类和定位。实验表明：该方法的mAP达到95.15%，能够快速有效地对垃圾分类和定位。
Abstract:
In order to solve the difficult problem of garbage classification, according to the characteristics of a large number of garbage pictures, a method based on yolov4 garbage detection is proposed to realize the automatic identification and classification and positioning of garbage. This method collects different kinds of junk image sets through mobile phone shooting and Baidu, uses image enhancement to pre-process images, uses migration learning model and k-mean-clustering algorithm to carry out the training test of garbage network classification model, and finally uses the trained model to identify and classify and locate the collected garbage images in real time through the camera. Experiments show that the mAP of this method reaches 95.15%, which can classify and locate garbage quickly and effectively.

参考文献/References:

[1]靳晓菲.我国城市生活垃圾分类政策实施现状与改进对策[J].清洗世界,2020,35(12):112-114.

[2]赵国莲.城市生活垃圾分类收集处理的现状及对策[J].环境与发展,2020,32(10):32-33+35.
[3]马济飞.城市生活垃圾分类问题研究[J].环境与发展,2020,32(9):31-34.
[4]李慧颖,李薇,邢艳芳,等.基于TensorFlow的人脸识别系统设计[J].计算机时代,2020 (9):61-63.
[5]董峻妃,郑伯川,杨泽静.基于卷积神经网络的车牌字符识别[J].计算机应用,2017,37(7):2014-2018.
[6]孙钰,周焱,袁明帅,等.基于深度学习的森林虫害无人机实时监测方法[J].农业工程学报,2018,34(21):74-81.
[7]马钰锡,谭励,董旭,等.面向智能监控的行为识别[J].中国图象图形学报,2019,24(02):282-290.
[8]齐鑫宇,龚劬,李佳航,等.基于深度学习的垃圾图片处理与识别[J].电脑知识与技术,2021,17(09):20-24.
[9]向伟,史晋芳,刘桂华,等.改进CaffeNet模型在水面垃圾识别中的应用[J].传感器与微系统,2019,38(08):150-152+156.
[10]武凌,王浩,张晓春,等.基于深度迁移学习的垃圾分类系统设计与实现[J].沈阳大学学报(自然科学版),2020,32(6):496-502.
[11]YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks?[J]. Eprint Arxiv, 2014, 27:3320-3328.
[12]ARTHUR D, VASSILVITSKII S. K-means++: The advantages of careful seeding[C]. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, SIAM,2007:1027-1035.
[13]BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: Optimal speed and accuracy of object detection[J]. 2020.
[14]REDMON J, FARHADI A. YOLOv3: An incremental improvement[J]. arXiv e-prints, 2018.
[15]LINDE Y, BUZO A, GRAY R. The K-means algorithm[J]. IEEE Transactions on Professional Communication, 1980, 28.

相似文献/References:

[1]潘峥嵘,何 平,谯自健.基于ZigBee网络的城市交通疏导系统[J].工业仪表与自动化装置,2015,(05):49.
　PAN Zhengrong,HE Ping,QIAO Zijian.The urban traffic guidance system based on ZIGBEE network[J].Industrial Instrumentation & Automation,2015,(05):49.
[2]孟祥忠,刘 健,李 鹏.多AGV定位和路径规划方法研究[J].工业仪表与自动化装置,2019,(05):7.[doi:1000-0682(2019)05-0000-00]
　MENG Xiangzhong,LIU Jian,LI Peng.Research on multi-AGV location and path planning method[J].Industrial Instrumentation & Automation,2019,(05):7.[doi:1000-0682(2019)05-0000-00]
[3]于 雯,王 艳,张佳佳,等.多功能智能垃圾桶结构设计和功能实现[J].工业仪表与自动化装置,2022,(01):117.[doi:10.19950/j.cnki.cn61-1121/th.2022.01.024]
　YU Wen,WANG Yan,ZHANG Jiajia,et al.Structural design and function realization of multifunctional intelligence garbage bin[J].Industrial Instrumentation & Automation,2022,(05):117.[doi:10.19950/j.cnki.cn61-1121/th.2022.01.024]
[4]赵 鑫,孟令军,刘威宏.基于Zynq平台的垃圾分类系统实现[J].工业仪表与自动化装置,2022,(05):26.[doi:10.19950/j.cnki.cn61-1121/th.2022.05.005]
　ZHAO Xin,MENG Lingjun,LIU Weihong.Implementation of waste sorting system based on Zynq platform[J].Industrial Instrumentation & Automation,2022,(05):26.[doi:10.19950/j.cnki.cn61-1121/th.2022.05.005]
[5]曹智超,姚恩涛,冯嘉瑞.柔性细长管材拣选机械手同步控制技术研究[J].工业仪表与自动化装置,2022,(06):119.[doi:10.19950/j.cnki.cn61-1121/th.2022.06.023]
　CAO Zhichao,YAO Entao,FENG Jiarui.Research on synchronous control technology of flexible slender pipe picking manipulator[J].Industrial Instrumentation & Automation,2022,(05):119.[doi:10.19950/j.cnki.cn61-1121/th.2022.06.023]

备注/Memo

备注/Memo:
收稿日期：2021-05-07
作者简介：
王明吉(1963)，男，博士，教授，主要研究方向是光电检测及信息处理技术。
更新日期/Last Update: 1900-01-01