Oil Spill Four-Class Classification Using UAVSAR Polarimetric Data
- PDF / 4,059,872 Bytes
- 11 Pages / 595 x 842 pts (A4) Page_size
- 87 Downloads / 405 Views
Available online at http://link.springer.com
Article pISSN 1738-5261 eISSN 2005-7172
Oil Spill Four-Class Classification Using UAVSAR Polarimetric Data Behnam Hassani, Mahmod Reza Sahebi*, and Reza Mohammadi Asiyabi Faculty of Geodesy and Geomatics Engineering, Department of Photogrammetry and Remote Sensing, K.N. Toosi University of Technology, Tehran 19967, Iran Received 14 December 2019; Revised 30 April 2020; Accepted 21 May 2020 © KSO, KIOST and Springer 2020
Abstract − Oil pollution of oceans from various sources is a devastating environmental problem and immediate detection of oil spills is crucial. Remote sensing techniques have provided an unprecedented opportunity for early oil spill detection and classification with an easy, quick, and cheap approach. Moreover, Fully Polarimetric Synthetic Aperture Radar (PolSAR) data with unique capabilities and informative features is an immense data source for oil spill detection on large scales. The objective of the present study is to utilize PolSAR data not only for oil spill detection, but also to classify the detected oil spill in the ocean into four classes: thick oil, thin oil, oil/water mixture, and clear water. In this study, numerous polarimetric decomposition parameters and texture features are extracted from the PolSAR image. A two-phase feature selection method, manually selection based on oil and water surface backscattering behavior and an optimization algorithm, has been employed on the extracted features to select the optimum feature set. The selected feature set has been used to classify the PolSAR image into oil and water classes. Moreover, the high sensitivity and discriminative power of the validation PolSAR dataset, UAVSAR L-band quad-pol data, is exploited by classifying the image into four classes. Remarkable acquired classification accuracies of 90.21% and 85.41% and Kappa coefficient of 0.8052 and 0.7905 for two-class and four-class classifications, respectively, demonstrate the robustness and high potential of the proposed methodology for oil spill detection and classification. Keywords − remote sensing, UAVSAR, PolSAR, classification, oil spill detection, Gulf of Mexico
1. Introduction Mineral or petroleum oil pollution is one of the major environmental problems in the seas and oceans which can be traced back to various sources. Many oil spill catastrophes *Corresponding author. E-mail: [email protected]
are the result of unexpected incidents such as ship crashes or accidents at oil rigs. In addition, oil might pollute the ocean because of some common ship operations such as oil tank washing or because of minor problems such as oil tank leakage. Moreover, some offshore oil platforms and oil pipelines under the sea can cause oil pollution in the oceans (Alpers et al. 2017). Generally, oil pollution from various sources is an important and consequential environmental problem which threatens the marine ecosystem, water quality, birds’ life, human food chain, marine infrastructure, etc. Deliberate or accidental oil spills at sea can cause
Data Loading...
