Study on Bohai seaice monitoring based on hyperspectral remote sensing imagery

As an effective method,supervised classification is widely used in seaice remote sensing monitoring field,but different supervised classification methods and bands combinations always result in different classification results and accuracy.In order to improve the precision of the seaice monitoring,this paper used hyperspectral remote sensed imagery,which provides the visible light,near-infrared wavelengths of continuous imaging spectra data,compared seaice extracting accuracy of the different band combinations,analyzed the advantages and disadvantages of seaice monitoring using different bands combinations and different classification methods,and proposed the best bands combination and the most suitable supervised classification method for the seaice monitoring.