Automatic recognition of coastal and oceanic environmental events with orbital radars

被引:5
作者
Bentz, Cristina Maria [1 ]
Politano, Alexandre Tadeu [1 ]
Favilla Ebecken, Nelson Francisco [2 ]
机构
[1] Petrobras SA, Ctr Res & Dev, Rio De Janeiro, Brazil
[2] Fed Univ Rio de Janeiro COPPE, Rio De Janeiro, Brazil
来源
IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET | 2007年
关键词
synthetic aperture radar; oil spill; ocean features detection; classification; machine learning;
D O I
10.1109/IGARSS.2007.4422946
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
An automatic classification procedure was developed able to identify different oceanic events, detectable in orbital radar images. The procedure was customized to be used in the southeastern Brazilian coast, since the classification training and test used examples extracted from 402 RADARSAT-1 images acquired in this region. Different sets of spectral, geometric and contextual (meteo-oceanographic and location) features of selected low backscatter patches were evaluated. Machine learning procedures (neural networks, decision trees and support vector machines) were used to induce classifiers to differentiate between seven classes, belonging to two categories. The classification procedure involves two steps: first the features area classified in one of two categories - oil spill or meteo-oceanographic phenomena. In the second step, the identification of tree classes of oil spills and four classes of meteo-oceanographic phenomena is done. The oil spill related classes are associated to operational exploration and production spills, ship releases and others. The meteo-oceanographic phenomena include biogenic oils and/or upwellings, algae blooms, low wind areas and rain cells. The models induced by support vector machines and neural networks achieved good results, allowing the operational implementation of the proposed procedures.
引用
收藏
页码:914 / 916
页数:3
相关论文
共 8 条
[1]  
Baatz M., 2003, ECOGNITION USER GUID
[2]  
BENTTZ CM, 2006, THESIS U FEDERAL RIO
[3]  
Clemente-Colón P, 2000, J HOPKINS APL TECH D, V21, P116
[4]   Neural networks for oil spill detection using ERS-SAR data [J].
Del Frate, F ;
Petrocchi, A ;
Lichtenegger, J ;
Calabresi, G .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2000, 38 (05) :2282-2287
[5]   Satellite SAR oil spill detection using wind history information [J].
Espedal, HA ;
Wahl, T .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1999, 20 (01) :49-65
[6]  
ESPINDOLA RP, 2005, DATA MINING, V6, P25
[7]   Machine learning for the detection of oil spills in satellite radar images [J].
Kubat, M ;
Holte, RC ;
Matwin, S .
MACHINE LEARNING, 1998, 30 (2-3) :195-215
[8]  
SOLBERG AHS, 1999, IEEE T GEOSCIENCE RE, V37