Object-oriented segmentation of remote sensing image based on texture analysis

DOI

10.2991/rsete.2013.185How to use a DOI?

Keywords

Texture feature, High-resolution, Object-oriented, Image segmentation

Abstract

High-spatial-resolution remote sensing image contains rich texture information and high variability of spectral information, but the rich details greatly increase the difficulty of segmentation. For this reason, this paper proposes a new method of high-spatial-resolution remote sensing image segmentation based on texture features. First, texture features of high-spatial-resolution remote sensing image were extracted by grey level co-occurrence probability (GLCP) method. Then the texture and spectral features are separately used for segmentation in eCognition. By using the texture features to segment the image, the segmentation is more accurate and smoother and has less broken region. The advantage of the method based on texture features is evaluated by comparison of traditional method based on spectral information. It shows that the new method is more reliable and comprehensive in reflecting the ground objects in the image.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wang Yanhong
AU  - Cheng Bo
AU  - Wang Guizhou
AU  - You Shucheng
PY  - 2013/08
DA  - 2013/08
TI  - Object-oriented segmentation of remote sensing image based on texture analysis
BT  - Proceedings of the 2013 the International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE 2013)
PB  - Atlantis Press
SP  - 763
EP  - 766
SN  - 1951-6851
UR  - https://doi.org/10.2991/rsete.2013.185
DO  - 10.2991/rsete.2013.185
ID  - Yanhong2013/08
ER  -