Mostra el registre d'ítem simple
Improved binary partition tree construction for hyperspectral images: application to object detection
dc.contributor.author | Valero, Silvia |
dc.contributor.author | Salembier Clairon, Philippe Jean |
dc.contributor.author | Chanussot, Jocelyn |
dc.contributor.author | Cuadres, Carles |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2012-01-17T19:25:01Z |
dc.date.available | 2012-01-17T19:25:01Z |
dc.date.created | 2011 |
dc.date.issued | 2011 |
dc.identifier.citation | Valero, S. [et al.]. Improved binary partition tree construction for hyperspectral images: application to object detection. A: IEEE International Geoscience and Remote Sensing Symposium. "Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International". Vancouver: IEEE, 2011, p. 2515-2518. |
dc.identifier.isbn | 978-1-4577-1003-2 |
dc.identifier.uri | http://hdl.handle.net/2117/14623 |
dc.description.abstract | This paper discusses hierarchical region-based representation using Binary Partition Tree in the framework of hyperspectral data. Based on region merging techniques, this region-based representation reduces the number of elementary primitives compared to the pixel based representation and allows a more robust filtering, segmentation, classification or information retrieval. The work presented here proposes a strategy for merging hyperspectral regions using a new association measure depending on canonical correlations relating principal coordinates. To demonstrate an example of BPT usefulness, a pruning strategy aiming at object detection is discussed. Experimental results demonstrate the good performances of BPT. |
dc.format.extent | 4 p. |
dc.language.iso | eng |
dc.publisher | IEEE |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo |
dc.subject.lcsh | Image processing --Digital techniques. |
dc.subject.lcsh | Spectroscopic imaging |
dc.title | Improved binary partition tree construction for hyperspectral images: application to object detection |
dc.type | Conference report |
dc.subject.lemac | Imatges -- Processament -- Tècniques digitals |
dc.subject.lemac | Reconeixement de formes (Informàtica) |
dc.contributor.group | Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
dc.identifier.doi | 10.1109/IGARSS.2011.6049723 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6034618 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 9408053 |
dc.description.version | Postprint (published version) |
local.citation.author | Valero, S.; Salembier, P.; Chanussot, J.; Cuadres, C. |
local.citation.contributor | IEEE International Geoscience and Remote Sensing Symposium |
local.citation.pubplace | Vancouver |
local.citation.publicationName | Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International |
local.citation.startingPage | 2515 |
local.citation.endingPage | 2518 |