Technology and Methodology |
|
|
|
|
|
THEOBJECT-ORIENTEDHYPERSPECTRALIMAGECLASSIFICATIONBASEDONMULTIPLE FEATURESDURINGINFORMATIONFUSION |
GUIDe-zhu 1,LIGang 1,2HANGCheng-cheng 1 |
1.CollegeofEnvironmentandSpatialInformatics,ChinaUniversityofMiningandTechnology,Xuzhou221008,China; 2.XuzhouLandResourcesBureau,Xuzhou221006,China |
|
|
Abstract
Becauseofthehighdatadimensionalityofhyperspectraldata,itisverydifficultforconventionalmeth
odstoobtainsatisfactoryresultsinthestudyofimageclassificationformaterialsontheground.Intheprocessof
featureimagesextractionbasedoninformationfusion,anewmethodisputforward,whichcombinesimage
multifeatureinformationfusionwithvariousclassificationalgorithmstomakeobjectorientedhyperspectralimage
classification.Experimentsshowthatimagedatadimensionsarereducedandclassificationaccuracyisimproved.
|
Keywords
Structures from remote sensing
Hydrocarbon anomaly
Comprehensive prediction
|
|
Issue Date: 24 July 2009
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|