@article{fdi:010082187,
  title = {{F}ast unsupervised multi-scale characterization of urban landscapes based on earth observation data},
  author = {{T}eillet, {C}laire and {P}illot, {B}enjamin and {C}atry, {T}hibault and {D}emagistri, {L}aurent and {L}yszczarz, {D}. and {L}ang, {M}. and {C}outeron, {P}ierre and {B}arbier, {N}icolas and {K}ouassi, {A}. {A}. and {G}unther, {Q}. and {D}essay, {N}adine},
  editor = {},
  language = {{ENG}},
  abstract = {{M}ost remote sensing studies of urban areas focus on a single scale, using supervised methodologies and very few analyses focus on the "neighborhood" scale. {T}he lack of multi-scale analysis, together with the scarcity of training and validation datasets in many countries lead us to propose a single fast unsupervised method for the characterization of urban areas. {W}ith the {FOTOTEX} algorithm, this paper introduces a texture-based method to characterize urban areas at three nested scales: macro-scale (urban footprint), meso-scale ("neighbourhoods") and micro-scale (objects). {FOTOTEX} combines a {F}ast {F}ourier {T}ransform and a {P}rincipal {C}omponent {A}nalysis to convert texture into frequency signal. {S}everal parameters were tested over {S}entinel-2 and {P}leiades imagery on {B}ouake and {B}rasilia. {R}esults showed that a single {S}entinel-2 image better assesses the urban footprint than the global products. {P}leiades images allowed discriminating neighbourhoods and urban objects using texture, which is correlated with metrics such as building density, built-up and vegetation proportions. {T}he best configurations for each scale of analysis were determined and recommendations provided to users. {T}he open {FOTOTEX} algorithm demonstrated a strong potential to characterize the three nested scales of urban areas, especially when training and validation data are scarce, and computing resources limited.},
  keywords = {remote sensing ; multi-scale ; unsupervised ; urban landscapes ; texture},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {13},
  numero = {12},
  pages = {2398 [26 ]},
  year = {2021},
  DOI = {10.3390/rs13122398},
  URL = {https://www.documentation.ird.fr/hor/fdi:010082187},
}