Paper Info
Title
Object extraction from high resolution SAR images using a birth and death dynamics
Abstract
We present a new approach to extract predefined objects, such as trees and oil tanks instance, from high resolution SARA images. We consider a stochastic approch based on an object process also called marked point process. The objects process trees or oil tanks which are modeled by disks in the images. We first define a Gibbs density that takes into account both prior information and the data. The energy We define is composed of two terms, one is a prior penallzing overlaps between objects, and the other is a data term, which mneasures the suitabillity of an object the SAR images. The problem is then reduced to an energy minimization problem. We sample the process to extract the configuration of objects minimizing the enegy by extract the configuration of objects minimizing the energy by a fast birth-and-death dynamics, leading to the total number of objects (trees or oil tanks in our case.) This approach is much faster than manual counts and does not need any preprocessing or supervision of a user.
Year
DOI
Venue
2009
10.1109/ICIP.2009.5413907
Image Processing
Keywords
Field
DocType
marked point process,objects process tree,data term,death dynamic,oil tank,new approach,high resolution sar image,energy minimization problem,object process,object extraction,oil tanks instance,prior information,predefined object,feature extraction,synthetic aperture radar,gold,energy minimization,decision support systems,high resolution,radar imaging
Computer vision,Object detection,Radar imaging,Pattern recognition,Synthetic aperture radar,Computer science,Birth–death process,Feature extraction,Preprocessor,Artificial intelligence,Image resolution,Energy minimization
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-5655-0
978-1-4244-5655-0
1
PageRank 
References 
Authors
0.42
7
3
Name
Order
Citations
PageRank
Fatih Arslan110.42
Xavier Descombes269379.43
Josiane Zerubia32032232.91