Citation

Wang, Guangcheng and Shi, Quan and Wang, Han and Gu, Ke and Wei, Mengting and Wong, Lai Kuan and Wang, Mingxing (2023) Vision-Based PM$_{2.5}$ Concentration Estimation With Natural Scene Statistical Analysis. IEEE Transactions on Artificial Intelligence. pp. 1-11. ISSN 2691-4581

Text 4.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

As the primary pollutant in China's urban atmosphere, PM 2.5 poses a great threat to the health of residents and ecological stability. Efficient and effective PM 2.5 concentration monitoring is essential. Nonetheless, the popular devices for PM 2.5 monitoring are developed based on two standards: the micro-oscillation balance method and the β -ray method, which have high purchase and maintenance costs and slow calculation rates. To this end, we put forward a real-time and reliable vision-based estimation algorithm of PM 2.5 concentration. To be specific, the proposed method first develops two natural scene statistical analysis-based visual priors to measure saturation and structural information losses caused by the ‘haze’ formed by PM 2.5 . Moreover, we develop a lightweight deep belief network (DBN)-deep neural network (DNN)-based PM 2.5 concentration estimation model, which learns the mapping from the designed visual priors to PM 2.5 concentrations. Experiments confirm the superiority of our vision-based PM 2.5 concentration estimation method by comparison with state-of-the-art photo-based PM 2.5 monitoring methods.

Item Type:	Article
Uncontrolled Keywords:	Monitoring, Estimation, Visualization, Loss measurement, Atmospheric measurements, Entropy, Artificial intelligence
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	07 Dec 2023 04:10
Last Modified:	07 Dec 2023 04:10
URII:	http://shdl.mmu.edu.my/id/eprint/11948

Downloads

Edit (login required)