000088582 001__ 88582
000088582 005__ 20210902121706.0
000088582 0247_ $$2doi$$a10.3390/rs12030534
000088582 0248_ $$2sideral$$a117324
000088582 037__ $$aART-2020-117324
000088582 041__ $$aeng
000088582 100__ $$0(orcid)0000-0002-7057-4283$$aAlcolea, Adrián$$uUniversidad de Zaragoza
000088582 245__ $$aInference in supervised spectral classifiers for on-board hyperspectral imaging: An overview
000088582 260__ $$c2020
000088582 5060_ $$aAccess copy available to the general public$$fUnrestricted
000088582 5203_ $$aMachine learning techniques are widely used for pixel-wise classification of hyperspectral images. These methods can achieve high accuracy, but most of them are computationally intensive models. This poses a problem for their implementation in low-power and embedded systems intended for on-board processing, in which energy consumption and model size are as important as accuracy. With a focus on embedded anci on-board systems (in which only the inference step is performed after an off-line training process), in this paper we provide a comprehensive overview of the inference properties of the most relevant techniques for hyperspectral image classification. For this purpose, we compare the size of the trained models and the operations required during the inference step (which are directly related to the hardware and energy requirements). Our goal is to search for appropriate trade-offs between on-board implementation (such as model size anci energy consumption) anci classification accuracy.
000088582 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T58-17R$$9info:eu-repo/grantAgreement/ES/MEC/FPU15-02090$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2016-76635-C2-1-R
000088582 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000088582 590__ $$a4.848$$b2020
000088582 591__ $$aGEOSCIENCES, MULTIDISCIPLINARY$$b27 / 198 = 0.136$$c2020$$dQ1$$eT1
000088582 591__ $$aIMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY$$b8 / 29 = 0.276$$c2020$$dQ2$$eT1
000088582 591__ $$aREMOTE SENSING$$b10 / 32 = 0.312$$c2020$$dQ2$$eT1
000088582 591__ $$aENVIRONMENTAL SCIENCES$$b76 / 273 = 0.278$$c2020$$dQ2$$eT1
000088582 592__ $$a1.284$$b2020
000088582 593__ $$aEarth and Planetary Sciences (miscellaneous)$$c2020$$dQ1
000088582 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000088582 700__ $$aPaoletti, Mercedes E.
000088582 700__ $$aHaut, Juan M.
000088582 700__ $$0(orcid)0000-0002-7532-2720$$aResano, Javier$$uUniversidad de Zaragoza
000088582 700__ $$aPlaza, Antonio
000088582 7102_ $$15007$$2035$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Arquit.Tecnología Comput.
000088582 773__ $$g12, 3 (2020), 534 [29 pp.]$$pRemote sens. (Basel)$$tRemote Sensing$$x2072-4292
000088582 8564_ $$s1237935$$uhttps://zaguan.unizar.es/record/88582/files/texto_completo.pdf$$yVersión publicada
000088582 8564_ $$s492651$$uhttps://zaguan.unizar.es/record/88582/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000088582 909CO $$ooai:zaguan.unizar.es:88582$$particulos$$pdriver
000088582 951__ $$a2021-09-02-09:16:58
000088582 980__ $$aARTICLE