Hierarchical segmentation of multiresolution remote sensing images

The extraction of urban patterns from very high spatial resolution optical images presents challenges related to the size, the accuracy and the complexity of the data. In order to efficiently carry out this task, a multiresolution hierarchical approach is proposed. It enables to progressively segment several images (of increasing resolutions) of a same scene, based on low level criteria. The process, based on binary partition trees, is partially performed in an interactive fashion, and then automatically completed. Experiments on urban images datasets provide encouraging results which may be further used for detection and classification purpose .

Keywords

remote sensing urban analysis partition-trees interactive/automated segmentation multiresolution multisource images hierarchical segmentation

Domains

Image Processing [eess.IV] Machine Learning [cs.LG] Geography

Fichier principal

Kurtz_ISMM_2011.pdf (12.61 Mo)

Kurtz ISMM 2011 Slides.pdf (18.81 Mo)

Origin	Files produced by the author(s)

Nicolas Passat : Connect in order to contact the contributor

https://hal.univ-reims.fr/hal-01718349

Submitted on : Tuesday, February 27, 2018-12:18:53 PM

Last modification on : Thursday, February 29, 2024-8:58:04 AM

Dates and versions

hal-01718349 , version 1 (27-02-2018)

Identifiers

HAL Id : hal-01718349 , version 1
DOI : 10.1007/978-3-642-21569-8_30

Cite

Camille Kurtz, Nicolas Passat, Anne Puissant, Pierre Gançarski. Hierarchical segmentation of multiresolution remote sensing images. International Symposium on Mathematical Morphology (ISMM), 2011, Intra, Lake Maggiore, Italy. pp.343-354, ⟨10.1007/978-3-642-21569-8_30⟩. ⟨hal-01718349⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CNRS URCA SITE-ALSACE

716 View

199 Download