Detection of small objects from high-resolution panchromatic satellite imagery based on supervised image segmentation

Author

Segl, Karl ; Kaufmann, Hermann

Author_Institution

Div. Kinematics & Dynamics of the Earth, GeoForschungsZentrum Potsdam, Germany

Volume

39

Issue

9

fYear

2001

fDate

9/1/2001 12:00:00 AM

Firstpage

2080

Lastpage

2083

Abstract

A new concept for the detection of small objects from modular optoelectronic multispectral scanner (MOMS-02) high spatial resolution panchromatic satellite imagery is presented. The authors combine supervised shape classification with unsupervised image segmentation in an iterative procedure which allows a target-oriented search for specific object shapes

Keywords

feature extraction; geophysical signal processing; geophysical techniques; image processing; image segmentation; multidimensional signal processing; remote sensing; terrain mapping; IR imaging; feature extraction; geophysical measurement technique; high-resolution panchromatic image; image processing; iterative procedure; land surface; multispectral remote sensing; optical imaging; satellite image; shape; small object; small object detection; supervised image segmentation; target-oriented search; terrain mapping; visible region; Brightness; Feature extraction; Image edge detection; Image resolution; Image segmentation; Object detection; Remote sensing; Satellites; Shape; Spatial resolution;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.951105

Filename

951105