Retrieval of Remote Sensing Images with Pattern Spectra Descriptors - Archive ouverte HAL Access content directly
Journal Articles ISPRS International Journal of Geo-Information Year : 2016

Retrieval of Remote Sensing Images with Pattern Spectra Descriptors

Abstract

The rapidly increasing volume of visual Earth Observation data calls for effective content based image retrieval solutions, specifically tailored for their high spatial resolution and heterogeneous content. In this paper, we address this issue with a novel local implementation of the well-known morphological descriptors called pattern spectra. They are computationally efficient histogram-like structures describing the global distribution of arbitrarily defined attributes of connected image components. Besides employing pattern spectra for the first time in this context, our main contribution lies in their dense calculation, at a local scale, thus enabling their combination with sophisticated visual vocabulary strategies. The Merced Landuse/Landcover dataset has been used for comparing the proposed strategy against alternative global and local content description methods, where the introduced approach is shown to yield promising performances.
Fichier principal
Vignette du fichier
ISPR_IJGI_16.pdf (1.22 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01397883 , version 1 (15-12-2016)

Identifiers

Cite

Petra Bosilj, Erchan Aptoula, Sébastien Lefèvre, Ewa Kijak. Retrieval of Remote Sensing Images with Pattern Spectra Descriptors. ISPRS International Journal of Geo-Information, 2016, Special Issue "Mathematical Morphology in Geoinformatics", ⟨10.3390/ijgi5120228⟩. ⟨hal-01397883⟩
298 View
172 Download

Altmetric

Share

Gmail Facebook X LinkedIn More