000190927 001__ 190927
000190927 005__ 20180913062155.0
000190927 020__ $$a978-1-4799-0211-8
000190927 02470 $$2ISI$$a000325634500014
000190927 037__ $$aCONF
000190927 245__ $$aClassification of urban multi-angular image sequences by aligning their manifolds
000190927 269__ $$a2013
000190927 260__ $$aNew York$$bIeee$$c2013
000190927 300__ $$a4
000190927 336__ $$aConference Papers
000190927 520__ $$aWhen dealing with multi-angular image sequences, problems of reflectance changes due either to illumination and acquisition geometry, or to interactions with the atmosphere, naturally arise. These phenomena interplay with the scene and lead to a modification of the measured radiance: for example, according to the angle of acquisition, tall objects may be seen from top or from the side and different light scatterings may affect the surfaces. This results in shifts in the acquired radiance, that make the problem of multi-angular classification harder and might lead to catastrophic results, since surfaces with the same reflectance return significantly different signals. In this paper, rather than performing atmospheric or bi-directional reflection distribution function (BRDF) correction, a non-linear manifold learning approach is used to align data structures. This method maximizes the similarity between the different acquisitions by deforming their manifold, thus enhancing the transferability of classification models among the images of the sequence.
000190927 700__ $$aTrolliet, Maxime
000190927 700__ $$0245927$$aTuia, Devis$$g150680
000190927 700__ $$aVolpi, Michele
000190927 7112_ $$aJoint Urban Remote Sensing Event (JURSE)
000190927 773__ $$q53-56$$t2013 Joint Urban Remote Sensing Event (Jurse)
000190927 909C0 $$0252045$$pLASIG$$xU10244
000190927 909CO $$ooai:infoscience.tind.io:190927$$pconf$$pENAC
000190927 917Z8 $$x104573
000190927 937__ $$aEPFL-CONF-190927
000190927 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000190927 980__ $$aCONF