DocumentCode :
256155
Title :
Mean-shift Segmentation Parameters Estimator (MSPE): A new tool for Very High Spatial Resolution satellite images
Author :
Benarchid, Omar ; Raissouni, Naoufal
Author_Institution :
RS&AID Lab., Univ. Abdelmalek Essaadi (UAE), Tetuan, Morocco
fYear :
2014
fDate :
14-16 April 2014
Firstpage :
357
Lastpage :
361
Abstract :
In this research we propose a new tool, called Mean-shift Segmentation Parameters Estimator (MSPE), to automate the selection of segmentation parameter values. Our algorithm is based on Mean-shift segmentation. However, this algorithm needs as inputs: i) existing vector database and ii) spectral data to define automatically the segmentation parameter values. The proposed method has been applied on different landscape´s types (Urban, and Rural). The results obtained show accurate results.
Keywords :
geophysical image processing; image segmentation; remote sensing; mean-shift segmentation parameters estimator; segmentation parameter values; spectral data; vector database; very high spatial resolution satellite images; Databases; Image resolution; Image segmentation; Vectors; MSPE; OBIA; Remote Sensing; Segmentation; VHSR;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia Computing and Systems (ICMCS), 2014 International Conference on
Conference_Location :
Marrakech
Print_ISBN :
978-1-4799-3823-0
Type :
conf
DOI :
10.1109/ICMCS.2014.6911184
Filename :
6911184
Link To Document :
بازگشت