Centre de documentation
scientifique

Dépouillements

Spectral-angle-based Laplacian Eigenmaps for non linear dimensionality reduction of hyperspectral imagery / L. Yan in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 9 (September 2014)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 80 n° 9 (September 2014) . - pp 849 - 861 Titre : Spectral-angle-based Laplacian Eigenmaps for non linear dimensionality reduction of hyperspectral imagery Type de document : Article/Communication Auteurs : L. Yan, Auteur ; X. Niu, Auteur Année de publication : 2014 Article en page(s) : pp 849 - 861 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] angle d'incidence [Termes IGN] classification Spectral angle mapper [Termes IGN] détection de cible [Termes IGN] distance euclidienne [Termes IGN] image hyperspectrale [Termes IGN] réduction [Termes IGN] réflectance spectrale [Termes IGN] végétation Résumé : In traditional manifold learning of hyperspectral imagery, distances among pixels are defined in terms of Euclidean distance, which is not necessarilly the best choice because of its sensitivity to variations in spectrum magnitudes. Selecting Laplacian Eignemaps (LE) as the test method, this paper studies the effects of distance metric selection in LE and proposes a spectral-angle-based LE method (LE-SA)to be compared against the traditional LE-based on Euclidean distance (LE-ED). Le-SA and LA-ED were applied to two airborne hyperspectral data sets and the dimensionlity-reduced data were quantitatively evalueted. Experimental results demonstrated that LE-SA is able to suppress the variations within the same type of features, such as variations in vegetation and those in illuminations due to shade orientations, and maintain a higher level of overall separability among different features than LE-ED. Further, the potential usage of a single LA-SA or LE-ED band for target detection is discussed. Numéro de notice : A2014-598 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.80.9.849 En ligne : https://doi.org/10.14358/PERS.80.9.849 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74888 [article]

Generating pit-free canopy height models from airborne lidar / Anahita Khosravipour in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 9 (September 2014)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 80 n° 9 (September 2014) . - pp 863 - 872 Titre : Generating pit-free canopy height models from airborne lidar Type de document : Article/Communication Auteurs : Anahita Khosravipour, Auteur ; Andrew K. Skidmore, Auteur ; Martin Isenburg, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp 863 - 872 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] canopée [Termes IGN] détection de cible [Termes IGN] données lidar [Termes IGN] hauteur des arbres [Termes IGN] modélisation [Termes IGN] semis de points Résumé : (Auteur)Canopy height models (CHMs) derived from lidar data have been applied to extract forest inventory parameters. However, variations in modeled height cause data pits, which form a challenging problem as they disrupt CHM smoothness, negatively affecting tree detection and subsequent biophysical measurements. These pits appear where laser beams penetrate deeply into a tree crown, hitting a lower branch or ground before producing the first return. In this study, we develop a new algorithm that generates a pit-free CHM raster, by using subsets of the lidar points to close pits. The algorithm operate robustly on high-density lidar data as well as on a thinned lidar dataset. The evaluation involves detecting the finding to those achieved by using a Gaussian smoothed CHM. The results show that our pit-free CHMs derived from high-and low-density lidar data significantly improve the accuracy of tree detection. Numéro de notice : A2014-599 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.14358/PERS.80.9.863 En ligne : https://doi.org/10.14358/PERS.80.9.863 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74889 [article]