Abstract

In order to study the method for identifying the oil film using the multispectral data,the authors obtained the imagery of Zhoushan waters by using the marine aircraft- borne multi- spectral oil spill detector,and also acquired the reflectance spectra of the water and oil film by means of FieldSpec spectroradiometer. The image characteristics and spectral response characteristics were analyzed so as to detect the distribution of the relative thickness using the decision tree classifier. The overall accuracy is 93. 7%,which shows that the classification method based on the spectral characteristics could effectively recognize the thick thin sheen oil film and extract the information of marine oil pollution,thus sufficiently satisfying the requirements for monitoring marine oil spill.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call