Centre de documentation
scientifique

Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer / S. Durbha in Remote sensing of environment, vol 107 n° 1-2 (15 March 2007)  

Public [article]  inRemote sensing of environment > vol 107 n° 1-2 (15 March 2007) . - pp 348 - 361 Titre : Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer Type de document : Article/Communication Auteurs : S. Durbha, Auteur ; R.l. King, Auteur ; N.H. Younan, Auteur Année de publication : 2007 Article en page(s) : pp 348 - 361 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Terra-MISR [Termes IGN] Leaf Area Index [Termes IGN] modèle de transfert radiatif [Termes IGN] problème inverse [Termes IGN] régression Résumé : (Auteur) The retrieval of biophysical variables using canopy reflectance models is hindered by the fact that the inverse problem is ill posed. This is due to the measurement, model errors and the inadequacy between the model and reality, which produces similar reflectances for the different combination of the input parameters into the radiative transfer model. This leads to unstable and often inaccurate inversion results. The ill-posed nature of the inverse problem requires some regularization. Regularization means that one tries to consider only those solutions that are in the proximity of the true value. In order to regularize the model inversion, we propose kernel-based regularization by support vector machines regression (SVR) method. The formulation of the SVR contains meta-parameters C (regularization) and ?-insensitive loss. The SVR generalization performance (estimation accuracy) depends on these two parameters and the kernel parameters. Often the meta-parameters are selected using prior knowledge and/or user expertise. In this paper we adopt methods for the estimation of the meta-parameters from the input data itself instead of relying on any prior information. This paper is focused on the retrieval of leaf area index (LAI) from multiangle imaging spectroradiometer (MISR) data. The proposed methodology was implemented by inverting a 1D canopy reflectance model (PROSAIL) using SVR over MISR data. The results were validated against the LAI retrievals at the Alpilles EOS validation core site. An RMSE of 0.64 was obtained using both near-infrared (NIR) in conjunction with the red band and an RMSE of 0.50 using only the NIR band. Copyright Elsevier Numéro de notice : A2007-057 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2006.09.031 En ligne : https://doi.org/10.1016/j.rse.2006.09.031 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28422 [article]

DTM extraction of Lidar returns via adaptive processing / H.S. Lee in IEEE Transactions on geoscience and remote sensing, vol 41 n° 9 (September 2003)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 41 n° 9 (September 2003) . - pp 2063 - 2069 Titre : DTM extraction of Lidar returns via adaptive processing Type de document : Article/Communication Auteurs : H.S. Lee, Auteur ; N.H. Younan, Auteur Année de publication : 2003 Article en page(s) : pp 2063 - 2069 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] données lidar [Termes IGN] extraction automatique [Termes IGN] forêt [Termes IGN] modèle numérique de terrain [Termes IGN] prévision linéaire [Termes IGN] processus Résumé : (Auteur) Airborne light detection and ranging is emerging as a tool to provide accurate digital terrain models (DTMs) of forest areas, since it can penetrate beneath the canopy. Although traditional techniques, such as linear prediction, have shown to be robust type methods for the extraction of DTMs, they fail to effectively model terrain with steep slopes and large variability. In this paper, a modified linear prediction technique, followed by adaptive processing and refinement, is developed. A comparison with the traditional linear prediction method is provided along with statistical measures to ascertain the validity of the foregoing technique. Numéro de notice : A2003-253 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2003.813849 En ligne : https://doi.org/10.1109/TGRS.2003.813849 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22548 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-03091	RAB	Revue	Centre de documentation	En réserve L003	Disponible