Selection of the best hybrid spectral similarity measure for characterising marine oil spills from multi-platform hyperspectral datasets
by Deepthi; Deepa Sankar; Tessamma Thomas
International Journal of Computational Science and Engineering (IJCSE), Vol. 26, No. 6, 2023

Abstract: Marine oil pollution causes major economic crises in major industrial sectors like fishing, shipping and tourism. It affects marine life and human even decades after spillage necessitating very quick detection and remediation. Generally, oils are exceedingly difficult to identify from high-resolution images as oil slicks and sea water possess identical spectral characteristics. Therefore a cohesive and synergistic classification method called hybrid spectral similarity measures (HSSM) that discerns the data-rich constituents of hyperspectral images (HSI) is recommended in this paper to classify oil spills. Oil spill HSI procured from spaceborne [earth observation (EO-1) Hyperion] and airborne [airborne visible/infrared imaging spectrometer (AVIRIS)] platforms are employed to discriminate different marine spectral classes. The statistical parameters like overall accuracy (OA), Kappa, ROC/PR curve, AUC/PRAUC, weighted Youden index (J_w), F1score and Noise analysis have identified spectral information divergence-chi square distance (SID-CHI) as the best HSSM promulgating its multi-class, multi-sensor, and multi-platform oil spill classification capability.

Online publication date: Mon, 04-Dec-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Science and Engineering (IJCSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com