DocumentCode :
2998969
Title :
Contextual approach for oil spill detection in SAR images using image fusion and markov random fields
Author :
Lopezl, Ludwin ; Moctezuma, Miguel ; Parmiggianil, Flavio
Author_Institution :
DIE-UN AM, Nat. Univ. of Mexico, Coyoacan
Volume :
2
fYear :
2006
fDate :
6-9 Aug. 2006
Firstpage :
137
Lastpage :
139
Abstract :
This paper presents a study for oil spill detection. The scheme incorporates contextual information using multi-conexity 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.
Keywords :
Markov processes; disasters; image fusion; image segmentation; oils; radar imaging; random processes; remote sensing by radar; simulated annealing; spaceborne radar; synthetic aperture radar; SAR images; contextual algorithm; data fusion stage; discrete Markov random fields; image fusion; image segmentation; multiconexity analysis; oil spill detection; posteriori energy function; remote sensing; simulated annealing; synthetic aperture radar; Image fusion; Image segmentation; Instruments; Lighting; Markov random fields; Petroleum; Pixel; Remote sensing; Satellites; Synthetic aperture radar;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2006. MWSCAS '06. 49th IEEE International Midwest Symposium on
Conference_Location :
San Juan
ISSN :
1548-3746
Print_ISBN :
1-4244-0172-0
Electronic_ISBN :
1548-3746
Type :
conf
DOI :
10.1109/MWSCAS.2006.382227
Filename :
4267305
Link To Document :
بازگشت