Fractal concept to the classification of crop and forest type in IRS data

Author

Jeyarani, K. ; Hebbar, K. Jayaram

Author_Institution

Comput. Process. Group, Nat. Remote Sensing Agency, Hyderabad, India

Volume

1

fYear

1996

fDate

27-31 May 1996

Firstpage

784

Abstract

The objective of the paper is to assess the use of fractal dimension as a discriminator in Indian Remote Sensing Satellite (IRS) images for different forest and crop patterns. In this study, a kernel of pre-defined size has been moved on a single band image and the corresponding fractal dimension is found using the triangular prism surface area method. The measured dimension is used as a classification factor and applied over the kernel. A preliminary study is performed using IRS LISS II Band-4 data. The results are motivating and significant improvement has been obtained in this procedure for the case of a homogeneous pattern

Keywords

agriculture; forestry; fractals; image classification; remote sensing; IRS LISS II Band-4 data; IRS data; Indian Remote Sensing Satellite images; classification; crop; discriminator; forest type; fractal dimension; kernel; triangular prism surface area method; Clouds; Crops; Fractals; Remote sensing; Rough surfaces; Satellites; Signal analysis; Spatial resolution; Surface fitting; Surface roughness;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1996. IGARSS '96. 'Remote Sensing for a Sustainable Future.', International

Conference_Location

Lincoln, NE

Print_ISBN

0-7803-3068-4

Type

conf

DOI

10.1109/IGARSS.1996.516474

Filename

516474