A New Endmember Preprocessing Method for the Hyperspectral Unmixing of Imagery Containing Marine Oil Spills

Can Cui,Bingxin Liu,Ying Li,Guannan Li

doi:10.3390/ijgi6090286

Can Cui, Bingxin Liu + Show 2 more

Open Access

https://doi.org/10.3390/ijgi6090286

Copy DOI

Abstract

The current methods that use hyperspectral remote sensing imagery to extract and monitor marine oil spills are quite popular. However, the automatic extraction of endmembers from hyperspectral imagery remains a challenge. This paper proposes a data field-spectral preprocessing (DSPP) algorithm for endmember extraction. The method first derives a set of extreme points from the data field of an image. At the same time, it identifies a set of spectrally pure points in the spectral space. Finally, the preprocessing algorithm fuses the data field with the spectral calculation to generate a new subset of endmember candidates for the following endmember extraction. The processing time is greatly shortened by directly using endmember extraction algorithms. The proposed algorithm provides accurate endmember detection, including the detection of anomalous endmembers. Therefore, it has a greater accuracy, stronger noise resistance, and is less time-consuming. Using both synthetic hyperspectral images and real airborne hyperspectral images, we utilized the proposed preprocessing algorithm in combination with several endmember extraction algorithms to compare the proposed algorithm with the existing endmember extraction preprocessing algorithms. The experimental results show that the proposed method can effectively extract marine oil spill data.

Highlights

Oil pollution is one of the most common forms of marine pollution
Based on vertex component analysis (VCA), orthogonal subspace projection (OSP), minimum volume simplex analysis (MVSA), and SISAL, we found that VCA performed much better in terms of its robustness to noise; the VCA endmember extraction algorithm that we applied included a module that estimates noise
A new data field-spectral endmember extraction preprocessing algorithm has been proposed for the identification of marine oil spills

Summary

Introduction

Oil pollution is one of the most common forms of marine pollution. It is estimated that approximately 706 million gallons of oil are spilled into the ocean each year [1]. Marine oil spills have become one of the most serious ocean pollution problems because they can degrade ocean ecosystems and affect both the environment and the economy [3]. To address oil spill pollution and prevent large environmental and economic costs, a rapid and accurate response is necessary. Hyperspectral remote sensing offers good coverage and the continuity of observations, as well as rich spectral and spatial data. It is an efficient way to detect and monitor oil spills over a broad area. Airborne hyperspectral remote sensing is an effective and rapid tool for the remote detection and mapping of oil spills. During the Deepwater Horizon oil spills, hyperspectral remote sensing data were gathered from aerial flights that were undertaken to assess the extent and magnitude of the surface oil [4]

Objectives

Methods

Conclusion