Detection of PM 2.5 Particulates using a Snap-Shot Hyperspectral Imaging Technology
Arvind Mukundan, Nguyen Hong-Thai, Hsiang‐Chen Wang
Abstract
In this paper, visible light hyperspectral imaging technology combined with VGG-16 to estimate PM2.5 concentration in images captured aerially using three different methods; RGB, Principal component Analysis, and 3D-CAE, and their accuracy is compared.
Topics & Concepts
Hyperspectral imagingPrincipal component analysisRGB color modelArtificial intelligenceRemote sensingShot (pellet)Single shotOne shotComputer scienceComputer visionMaterials scienceGeologyOpticsEngineeringPhysicsMechanical engineeringMetallurgyAir Quality Monitoring and ForecastingAir Quality and Health ImpactsCOVID-19 impact on air quality