Using Photo Images with Deep Residual Network for PM2.5 Value Estimation

Abstract

Fine particles (PM2.5) become an important issue in Asia. The fine particles are related for causing of severe health problems. This paper focuses on using photo images with deep residual network for PM2.5 value estimation. The proposed framework has been designed to reduce the computational complexity and improve the estimation accuracy. Regression analysis is also introduced in the proposed framework by using LSTM with the meteorological data and the features extracted from the modified ResNet model. The images with HDR and without HDR technique are applied to the image feature extraction process. Thus, the PM2.5 value estimation process can be started using the mobile phone camera.