Contextual approach for oil spill detection in SAR images using image fusion and markov random fields


Por: López L., Moctezuma M., Parmiggiani F.

Publicada: 1 ene 2006
Resumen:
This paper presents a study for oil spill detection. The scheme incorporates contextual information using multiconexity analysis. The image is modeled as a discrete Markov Random Field (MRF). Each pixel can be classified in two classes: {oil, not-oil}. To determine the class we optimized the a posteriori energy function by means of simulated annealing. The segmentation result contains different levels of information. In order to improve the detection, we propose a data fusion stage. To realize the data fusion we use a contextual algorithm. The result obtained is binary and shows in detail the oil spill in the analysis zone. © 2006 IEEE.

Filiaciones:
López L.:
 National University of Mexico, DIE-UNAM, Ciudad Universitaria, Apdo. Postal 70-256, Coyoacan, C.P. 04510, Mexico D.F

Moctezuma M.:
 National University of Mexico, DIE-UNAM, Ciudad Universitaria, Apdo. Postal 70-256, Coyoacan, C.P. 04510, Mexico D.F

Parmiggiani F.:
 ISAO-CNR, Via P. Gobetti 101-40129, Bologna, Italy
ISSN: 15483746
Editorial
Inst Nacional de Astrofisica, Optica y Electronica, Puebla, Mex. Distributed by Western Period, Estados Unidos America
Tipo de documento: Conference Paper
Volumen: 2 Número:
Páginas: 137-139
WOS Id: 000249557100029