基于图像处理的空气质量识别方法研究  

Research on Air Quality Recognition Method Based on Image Processing

作　　者：刘一睿 杜建卫[1] 曹佳兴 何天润 崔宸赫 王佳乐 LIU Yirui;DU Jianwei;CAO Jiaxing;HE Tianrun;CUI Chenhe;WANG Jiale(Zhiyuan College,Beijing Institute of Petrochemical Technology,Beijing 102617,China;School of Information Engineering,Beijing Institute of Petrochemical Technology,Beijing 102617,China)

机构地区：[1]北京石油化工学院致远学院,北京102617 [2]北京石油化工学院信息工程学院,北京102617

出　　处：《北京石油化工学院学报》2022年第4期42-46,共5页Journal of Beijing Institute of Petrochemical Technology

基　　金：URT项目“基于图像处理的空气质量识别方法研究(2021X00034)”资助

摘　　要：针对图像处理识别空气质量问题,将多种图像颜色进行空间转换,使RGB的值转换成HSV空间,从而得出更加精准的颜色信息,再利用K均值聚类技术确定图像的主要颜色,并用RGB值反映出来。通过算法训练有关空气质量的54张图片,进而确定6个等级的RGB平均值,将RGB分别作为图像的三类特征,利用K近邻法判断图像的空气质量后,即可以通过图像处理识别空气质量,给出空气质量好坏的判别。经过计算分析对比,将RGB的值转换成HSV空间的方法会使结果更加精确。The research aims to solve the problem of identifying air quality based on image processing.Researchers spatially shift a variety of image colors,convert the value of RGB into HSV space,so as to obtain more accurate color information,and use K mean clustering technology to determine the main color of the image reflected by RGB.Through the algorithm training of fifty-four pictures about air quality,the average value of RGB of six levels is determined.RGB is used as the three types of characteristics of the image,and the air quality of the image is judged by using the K neighbor method.The air quality can be thereby identified by image processing,and the judgment of air quality is given.By comparison,the method of converting the value of RGB into HSV space will make the results more accurate.

关 键 词：环境问题 空间转换 K均值聚类 K近邻法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]