SAR image segmentation using kernel density estimation on region adjacency graph

Author

Zhang, Daming ; Fu, Maosheng ; Luo, Bin

Author_Institution

Sch. of Comput. Sci. & Technol., Anhui Univ., Hefei, China

fYear

2009

fDate

26-30 Oct. 2009

Firstpage

668

Lastpage

671

Abstract

In this paper, we propose a new synthetic aperture radar (SAR) image segmentation scheme. Firstly, the SAR image is over-segmented using the mean shift (MS) algorithm while the original image discontinuity characteristics are preserved. Secondly, we propose a novel method to estimates the probability density function of each node on region adjacency graph (RAG) using kernel density estimation (KDE) method. This estimation includes the information of similarity and proximity of any pairs of nodes at the same time. Our approach yields superior performance and also is feasible for real-time processing.

Keywords

graph theory; image segmentation; probability; radar imaging; synthetic aperture radar; SAR image segmentation; image discontinuity characteristics; kernel density estimation; mean shift algorithm; probability density function; region adjacency graph; synthetic aperture radar; Clustering algorithms; Image analysis; Image segmentation; Iterative algorithms; Kernel; Partitioning algorithms; Pixel; Probability density function; Speckle; Synthetic aperture radar; Image segmentation; kernel density estimation (KDE); mean shift (MS); region adjacency graph (RAG); synthetic aperture radar (SAR);

fLanguage

English

Publisher

ieee

Conference_Titel

Synthetic Aperture Radar, 2009. APSAR 2009. 2nd Asian-Pacific Conference on

Conference_Location

Xian, Shanxi

Print_ISBN

978-1-4244-2731-4

Electronic_ISBN

978-1-4244-2732-1

Type

conf

DOI

10.1109/APSAR.2009.5374115

Filename

5374115