Image and Spectrum Based Deep Feature Analysis for Particle Matter Estimation with Weather Informatio

Zanbo Zhu, Ruobing Zhao, Jianyuan Ni, Jing Zhang

Abstract: Air pollution is a major global risk to human health and environment. Particle matter (PM) with diameters less than 2.5 micrometers (PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> ) is more harmful to human health than other air pollutants because it can penetrate deeply into lungs and damage human respiratory system. A new imagebased deep feature analysis method is presented in this paper for PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentration estimation. Firstly, low level and high level features are extracted from images and their spectrums by a deep learning neural network, and then regression models are created using the extracted deep features to estimate the PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentrations, which are future refined by the collected weather information. The proposed method was evaluated using a PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> dataset with 1460 photos and the experimental results demonstrated that our method outperformed other state-of-the-art methods.