基于SSD算法的垃圾识别分类研究  

Research on Garbage Identification and Classification Based on SSD Algorithm

作　　者：彭昕昀[1] 李嘉乐 李婉[2] 刘杏洲 张程发 林显新 欧嘉诚 PENG Xin-yun;LI Jia-le;LI Wan;LIU Xing-zhou;ZHANG Cheng-fa;LIN Xian-xin;OU Jia-cheng(School of Physics and Mechanical and Electrical Engineering;Editorial Department of Journal,Shaoguan University,Shaoguan 512005,Guangdong,China)

机构地区：[1]韶关学院物理与机电工程学院 [2]韶关学院学报编辑部,广东韶关512005

出　　处：《韶关学院学报》2019年第6期15-20,共6页Journal of Shaoguan University

基　　金：韶关学院大学生创新训练计划项目省级立项(201810576054);韶关学院第十七批校级教育教学改革研究一般项目(SYJY20161724);2017年韶关学院质量工程建设项目(韶学院[2017]301号)

摘　　要：目前垃圾识别分类的主要技术是利用传统的机器视觉算法,或者采用传感器进行筛选识别.垃圾的类型多样,对垃圾进行分拣时,先对垃圾进行准确的识别分类是非常必要的.通过搜集多种类型的垃圾图片,构建检测数据集,采用基于SSD的垃圾识别检测算法,利用数据增强,提高模型的鲁棒性,可以达到对不同种类的垃圾进行快速和准确的识别.实验结果表明该方法检测准确率高、耗时短、鲁棒性好.At present, the main technology of garbage identification and classification is to use traditional machine vision algorithm, or to use sensors to screen identification. There are many types of garbage, and it is very necessary to identify and classify the garbage accurately before sorting it. By collecting various types of garbage pictures, constructing detection data sets, using SSD based garbage identification detection algorithm, using data enhancement to improve the robustness of the model, fast and accurate identification of different types of garbage can be achieved. The experimental results show that the method is high, time-consuming, and good robustness.

关 键 词：垃圾识别 SSD 深度学习 目标检测 

分 类 号：T249[一般工业技术]