Title :
A Nagao-Matsuyama approach to high-resolution satellite image classification
Author :
Baraldi, A. ; Parmiggiani, F.
Author_Institution :
IMGA-CNR, Modena, Italy
fDate :
7/1/1994 12:00:00 AM
Abstract :
A knowledge-based, hierarchical, unsupervised classification scheme for high-resolution multispectral satellite (HRMS) images is described. This scheme, which finds its conceptual bases in the work of Nagao and Matsuyama for structural analysis of aerial photographs, introduces a new filtering algorithm which is able to preserve fine linear structures of the image. An example of the application of this classification scheme to a Landsat Thematic Mapper multispectral image is presented
Keywords :
edge detection; feature extraction; geophysical techniques; geophysics computing; image recognition; knowledge based systems; optical information processing; remote sensing; Landsat Thematic Mapper multispectral image; Nagao Matsuyama approach; feature extraction; filtering algorithm; fine linear structure; geophysical measurement technique; hierarchical unsupervised classification; high-resolution; knowledge-based; land surface; multispectral method; optical imaging; remote sensing; satellite image classification; visible infrared IR; Algorithm design and analysis; Filtering algorithms; Focusing; Human resource management; Image analysis; Image classification; Image sensors; Remote sensing; Satellite broadcasting; Spatial resolution;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
