Integration of spot and SAR fractal images for terrain cover classification

NCU Institutional Repository > 研究中心 > 太空及遙測研究中心 > 期刊論文 > Item 987654321/27681

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/27681

题名:	Integration of spot and SAR fractal images for terrain cover classification
作者:	Tzeng,YC;Chen,KS
贡献者:	太空及遙測研究中心
关键词:	LEARNING NEURAL-NETWORK;NATURAL SCENES;SEGMENTATION;GEOMETRY
日期:	1997
上传时间:	2010-06-29 18:52:05 (UTC+8)
出版者:	中央大學
摘要:	This paper presents the terrain cover classification from combining SPOT with SAR fractal images. Due to its special geometric characteristics, SAR image needs special geometry ratification before the process of overlaying with other types of imagery is proper and feasible. In this study, we intend to develop and verify a simple model to compensate for the elevation effect in the SAR image. Besides, operations of radiometric calibrations are necessary to perform three-term corrections including elevation antenna gain pattern, local incident angle variations, and range spreading compensation. The important finding is that fractal information significantly improves the discrimination capability of the heterogeneous area such as in urban regions, while it slightly degrades accuracy for homogeneous areas, such as open water. The overall classification performance can make to results that are much superior to those in production by use of SPOT image only. The integration of SAR fractal image and SPOT data for terrain cover classification proves to be effective and efficient.
關聯:	JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS
显示于类别:	[太空及遙測研究中心] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	442	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing