SAR IMAGE SIMULATION WITH APPLICATION TO TARGET RECOGNITION

NCUIR > Research Center > Center for Space and Remote Sensing Research > journal & Dissertation > Item 987654321/50641

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/50641

Title:	SAR IMAGE SIMULATION WITH APPLICATION TO TARGET RECOGNITION
Authors:	Chang,YL;Chiang,CY;Chen,KS
Contributors:	太空及遙測研究中心
Keywords:	LEARNING NEURAL-NETWORK;LOCAL STATISTICS;CLASSIFICATION;CLUTTER;RCS
Date:	2011
Issue Date:	2012-03-27 17:49:45 (UTC+8)
Publisher:	國立中央大學
Abstract:	This paper presents a novel synthetic aperture radar (SAR) image simulation approach to target recognition, which consists of two frameworks, referred to as the satellite SAR images simulation and the target recognition and identification. The images simulation makes use of the sensor and target geo-location relative to the Earth, movement of SAR sensor, SAR system parameters, radiometric and geometric characteristics of the target, and target radar cross section (RCS), orbital parameters estimation, SAR echo signal generation and image focusing to build SAR image database. A hybrid algorithm that combines the physical optics, physical diffraction theory, and shooting and bouncing rays was used to compute the RCS of complex radar targets. Such database is vital for aided target recognition and identification system Followed by reformulating the projection kernel in an optimization equation form, the target's reflectivity field can be accurately estimated. Accordingly, the target's features can be effectively enhanced and extracted, and the dominant scattering centers are well separated. Experimental results demonstrate that the simulated database developed in this paper is well suited for target recognition. Performance is extensively tested and evaluated from real images by Radarsat-2 and TerraSAR-X. Effectiveness and efficiency of the proposed method are further confirmed.
Relation:	PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER
Appears in Collections:	[Center for Space and Remote Sensing Research ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	688	View/Open

社群 sharing

Loading...