Multi-modal image feature fusion-based PM2.5 concentration estimation

PM2.5 can be suspended in the air for a long time, so it has great harm to human health and atmospheric environment quality. Real-time and reliable estimation of PM2.5 concentration is of great significance. This paper proposes a novel multi-modal image information fusion-based PM2.5 concentration estimator. Specifically, in the depth domain, we estimate PM2.5 concentration by calculating the depth error between the PM2.5 image and its corresponding dehazing result. In the texture domain, we measure PM2.5 concentration using the following two modules: (1) The PM2.5 concentration is represented by calculating the entropy difference between the PM2.5 image and its dehazing image; (2) We first compute the error map between the PM2.5 image and its dehazing image, and then calculate the color similarity between the PM2.5 image and the obtained error map to measure PM2.5 concentration. Finally, we use support vector regression to perform regression learning on the above-mentioned multi-modal features learned from the depth domain and texture domain to obtain the final PM2.5 concentration estimator. Experiments show that the proposed method can measure PM2.5 concentration more efficiently than the existing PM2.5 concentration estimation algorithms.