基于图像的空气质量等级检测

Air Quality Grade Detection Based on Image

目前国内主要依靠各种精密仪器检测空气中的污染物浓度.由于仪器的成本较高,国家通过在每个城市设立监测站来检测空气质量,这种空气质量检测方法是粗粒度的,不能覆盖城市的每个角落.本文提出了一种基于图像的空气质量等级检测方法,旨在通过移动设备采集的图像检测空气质量等级,移动设备的普及使得通过图像细粒度检测空气质量成为可能,该方法利用空气污染对图像颜色通道和灰度通道局部信息熵的影响构建空气质量等级检测模型.在本文构建的空气质量图像库进行了模型测试和比较分析,实验结果表明:本文方法能够准确地评估空气质量等级,比其他已有相关方法更适用于空气质量等级检测.

At present,the concentration of pollutants in the air is detected mainly by a variety of precision testing instruments.Because of the high cost of instruments,the state set up monitoring stations in every city to detect air quality,which is coarse-grained and cannot cover every corner of the city.This paper presents an air quality detection method based on images taken by mobile devices.Now the popularity of mobile devices makes it possible for the fine-grained detection of the air quality through images.Our method carries on the analysis of color channel information entropy and gray channel information entropy,which can reflect air quality,and then we build the air quality grade detection model based on these image features.The proposed method is compared with other existing methods on our air quality image database from the estimation accuracy and the time consumption,and the experimental results show that our method is more suitable for air quality grade detection.