DocumentCode
410424
Title
Consolidation of a pixel-based classification using neighborhood information
Author
Scheuchl, Bernd ; Cumming, Ian ; Hajnsek, Irena
Author_Institution
Dept. of Electr. & Comput. Eng., British Columbia Univ., Canada
Volume
1
fYear
2003
fDate
21-25 July 2003
Firstpage
449
Abstract
A two-step consolidation process is presented that reduces the effect of speckle in the classification result. The degree of consolidation or smoothing can be adjusted using a classification confidence measure and a threshold for the amount of neighborhood agreement needed. Results from AIRSAR ice data shown are compared to a classification result form pre-filtered data.
Keywords
geophysical signal processing; image classification; radar polarimetry; remote sensing by radar; synthetic aperture radar; terrain mapping; AIRSAR ice data; classification confidence measure; image classification; image consolidation; image speckle; neighborhood information; pixel-based classification; smoothing; Aerospace engineering; Bayesian methods; Covariance matrix; Ice; Measurement standards; Microwave technology; Radar scattering; Sea measurements; Speckle; Synthetic aperture radar;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International
Print_ISBN
0-7803-7929-2
Type
conf
DOI
10.1109/IGARSS.2003.1293805
Filename
1293805
Link To Document