@incollection{fdi:010084153,
  title = {{F}usion of hyperspectral imaging and {L}i{DAR} for forest monitoring},
  author = {{T}usa, {E}. and {L}aybros, {A}. and {M}onnet, {J}.{M}. and {D}alla {M}ura, {M}. and {B}arr{\'e}, {J}.{B}. and {V}incent, {G}r{\'e}goire and {D}alponte, {M}. and {F}{\'e}ret, {J}.{B}. and {C}hanussot, {J}.},
  editor = {},
  language = {{ENG}},
  abstract = {{E}ffective strategies for forest characterization and monitoring are important to support sustainable management. {R}ecent advances in remote sensing, like hyperspectral and {L}i{DAR} sensors, provide valuable information to describe forests at stand, plot, and tree level. {H}yperspectral imaging contains meaningful reflectance attributes of plants or spectral traits, while {L}i{DAR} data offer alternatives for analyzing structural properties of canopy. {T}he fusion of these two data sources can improve forest characterization. {T}he method to use for the data fusion should be chosen according to the variables to predict. {T}his work presents a literature review on the integration of hyperspectral imaging and {L}i{DAR} data by considering applications related to forest monitoring. {A}lthough different authors propose a variety of taxonomies for data fusion, we classified our reviewed methods according to three levels of fusion: low level or observation level, medium level or feature level, and high level or decision level. {T}his review examines the relationship between the three levels of fusion and the methods used in each considered approach.},
  keywords = {{FRANCE} ; {ITALIE} ; {GUYANE} {FRANCAISE}},
  booktitle = {{D}ata handling in science and technology},
  numero = {32},
  pages = {281--303},
  address = {{A}msterdam ({NLD}) ; {O}xford ({GBR}) ; {C}ambridge},
  publisher = {{E}lsevier},
  series = {{D}ata {H}andling in {S}cience and {T}echnology},
  year = {2020},
  DOI = {10.1016/{B}978-0-444-63977-6.00013-4},
  ISBN = {978-0-444-63977-6},
  URL = {https://www.documentation.ird.fr/hor/fdi:010084153},
}