000842376 001__ 842376
000842376 005__ 20210129232309.0
000842376 0247_ $$2doi$$a10.1109/IGARSS.2017.8127067
000842376 037__ $$aFZJ-2018-00617
000842376 1001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b0$$ufzj
000842376 1112_ $$a2017 IEEE International Geoscience and Remote Sensing Symposium$$cFort Worth, TX$$d2017-07-23 - 2017-07-28$$gIGARSS 2017$$wUSA
000842376 245__ $$aTree-based supervised feature extraction method based on self-dual attribute profiles
000842376 260__ $$bIEEE$$c2017
000842376 300__ $$a775-778
000842376 3367_ $$2ORCID$$aCONFERENCE_PAPER
000842376 3367_ $$033$$2EndNote$$aConference Paper
000842376 3367_ $$2BibTeX$$aINPROCEEDINGS
000842376 3367_ $$2DRIVER$$aconferenceObject
000842376 3367_ $$2DataCite$$aOutput Types/Conference Paper
000842376 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1516351741_26826
000842376 520__ $$aSelf-Dual Attribute Profiles (SDAPs) have proven to be an effective method for extracting spatial features able to improve scene classification of remote sensing images with very high spatial resolution. An SDAP is a multilevel decomposition of an image obtained with a sequence of transformations performed by attribute filters over the Tree of Shapes (ToS). One of the main issues with this technique is the identification of the filter thresholds generating a SDAP composed of features that should be relevant for the classification problem. This paper proposes a tree-based supervised feature extraction strategy, which is based on Fisher's linear discriminant analysis relying on the available class information. The exploitation of the ToS structure in the threshold selection procedure allows one to avoid any prior full image filtering, as in other related techniques. Furthermore, the ToS automates and optimizes the whole process by decreasing the computational time and overcoming the conventional selection procedure based on trial and error attempts. The proposed automatic spatial feature extraction technique has been tested in the classification of a very high resolution image proving its effectiveness with respect to a conventional selection strategy.
000842376 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000842376 588__ $$aDataset connected to CrossRef Conference
000842376 7001_ $$aMura, Mauro Dalla$$b1
000842376 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b2$$ufzj
000842376 7001_ $$0P:(DE-HGF)0$$aBenediktsson, Jon Atli$$b3
000842376 773__ $$a10.1109/IGARSS.2017.8127067
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.pdf$$yRestricted
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.gif?subformat=icon$$xicon$$yRestricted
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.jpg?subformat=icon-1440$$xicon-1440$$yRestricted
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.jpg?subformat=icon-180$$xicon-180$$yRestricted
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.jpg?subformat=icon-640$$xicon-640$$yRestricted
000842376 8564_ $$uhttps://juser.fz-juelich.de/record/842376/files/08127067.pdf?subformat=pdfa$$xpdfa$$yRestricted
000842376 909CO $$ooai:juser.fz-juelich.de:842376$$pVDB
000842376 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b0$$kFZJ
000842376 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b2$$kFZJ
000842376 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000842376 9141_ $$y2017
000842376 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000842376 980__ $$acontrib
000842376 980__ $$aVDB
000842376 980__ $$aI:(DE-Juel1)JSC-20090406
000842376 980__ $$aUNRESTRICTED