Using digital image and curve regression model to classify air quality

Abstract

Monitoring air quality is an important issue for people's health. The pollutant that has the greatest impact on air quality is PM2.5 concentration. Since PM2.5 concentration is positively correlated with air quality and visibility, the main objective of this study is to use PM2.5 concentration estimation technology to classify the air quality level. The proposed method is based on digital image processing and is a simple and low-cost method of assessing air quality. The image will be extracted with high-frequency information, contrast and entropy as features. Three regression models are used for training to get the relationship with PM2.5 concentration. The air quality level is classified by the estimated concentration of PM2.5. Air quality is divided into 3 levels, allowing the public to directly understand the current level of air pollution. This study uses images taken by two air quality monitoring stations as experimental samples. In addition to images, the collected data also includes PM2.5 concentration, relative humidity and AQI values. The experimental results show that the method proposed in this paper is suitable for classifying the air quality level.