STUDY ON AN IMAGE ENHANCEMENT FOR SHIP DETECTION USING SYNTHETIC APERTURE RADAR

Title
STUDY ON AN IMAGE ENHANCEMENT FOR SHIP DETECTION USING SYNTHETIC APERTURE RADAR
Author(s)
정재훈; 양찬수
KIOST Author(s)
Yang, Chan Su(양찬수)
Alternative Author(s)
정재훈; 양찬수
Publication Year
2015-04-24
Abstract
This paper addresses a procedure of an image enhancement for detecting ship in synthetic aperture radar (SAR) imagery. For experiments, RADARSAT-2 covering Ieodo ocean area of Korea was used. In this paper, power law transformation was applied to the radar brightness of original SAR data. This procedure generates a precision image that provides excellent visibility by compensating non-linear response produced by SAR and brings improvement to ship detection performance at final stage. Median and wiener filters with an optimum window size are applied to reduce speckle noise further over the precision image. Adaptive histogram equalization (AHE) are also considered for SAR contrast enhancement. The results were evaluated in terms of the improvement of signal to noise ratio (SNR) and of ship detectability. The results verified that our method is very effective for identifying and detecting ship, particularly for small ship target.ied to the radar brightness of original SAR data. This procedure generates a precision image that provides excellent visibility by compensating non-linear response produced by SAR and brings improvement to ship detection performance at final stage. Median and wiener filters with an optimum window size are applied to reduce speckle noise further over the precision image. Adaptive histogram equalization (AHE) are also considered for SAR contrast enhancement. The results were evaluated in terms of the improvement of signal to noise ratio (SNR) and of ship detectability. The results verified that our method is very effective for identifying and detecting ship, particularly for small ship target.
URI
https://sciwatch.kiost.ac.kr/handle/2020.kiost/25599
Bibliographic Citation
ISRS, pp.1 - 2, 2015
Publisher
CSPRS
Type
Conference
Language
English
Files in This Item:
There are no files associated with this item.

qrcode

Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse