Recent Advances on 2D and 3D Change Detection in Urban Environments from Remote Sensing Data - Computational Approaches for Urban Environments - page 240

Table 10.4 (continued)
Clustering, Bayesian
classifier

Aiazzi et al. ( 2013 ), Celik
( 2010 ), Ghosh et al. ( 2011 ),
and Salmon et al. ( 2011 )

Spectral mixture analysis
(Gaussian, etc. ),
unmixing

Yetgin ( 2012 ) Michishita et al. ( 2012 )

Active contours, level sets Bazi et al. ( 2010 )andHao

et al. ( 2014 )

Celik and Ma ( 2011 )

Support vector machines,
neural networks, learning

Bovolo et al. ( 2008 ) Bovolo et al. ( 2010 ), Chini et al.

( 2008 ), Camps-Valls et al.
( 2008 ), Habib et al. ( 2009 ),
PacificiandDelFrate( 2010 ),
Demir et al. ( 2012 ), Pagot and
Pesaresi ( 2008 ), Taneja et al.
( 2013 ), and Volpi et al. ( 2013 )

MRFs Ghosh et al. ( 2013 ), Moser

and Serpico ( 2009 ), Moser
et al. ( 2011 ), and Wang et al.
( 2013 )

Fernandez-Prieto and Marconcini
( 2011 )

Data fusion Du et al. ( 2012 ), Moser and

Serpico ( 2009 ), Ma et al.
( 2012 ), Gong et al. ( 2012 ),
andDuetal.( 2013 )

Post-classification
comparison

Del Frate et al. ( 2008 ), Dewan
and Yamaguchi ( 2009 ), Abd
El-Kawy et al. ( 2011 ), Knudby
et al. ( 2010 ), Sexton et al. ( 2013 )

Methods

Employed techniques Unsupervised Supervised

Object-based Bouziani et al. ( 2010 ) Berberoglu and Akin ( 2009 ),

Brunner et al. ( 2010 ), Doxani
et al. ( 2012 ), Gamanya et al.
( 2009 ),Hebeletal.( 2013 ), Huo
et al. ( 2010 ), Lu et al. ( 2011b ),
Xian and Homer ( 2010 ), and
Zhou et al. ( 2009 )

Data mining Boulila et al. ( 2011 ), Dos Santos

Silva et al. ( 2008 ), Schneider
( 2012 ), and Vieira et al. ( 2012 )

they were mainly based on. The majority of recent studies is based on standard direct
comparisons, data transformations, data fusion, multiscale analysis, and clustering.
Most of the recent unsupervised methods are, also, pixel-based approaches and
focus on the pixel-by-pixel analysis of the multispectral multitemporal data.
More specifically, they calculate after a certain computation (like a transfor-
mation, a spectral analysis, etc. ) the magnitude of change vectors and apply a
thresholding technique in order to detect possible changes.