Segmentation of optical remote sensing images for detecting homogeneous regions in space and time.

With the amount of multitemporal and multiresolution images growing exponentially, the number of image segmentation applications is recently increasing and, simultaneously, new challenges arise. Hence, there is a need to explore new segmentation concepts and techniques that make use of the temporal dimension. This paper describes a spatio-temporal segmentation that adapts the traditional region growing technique to detect homogeneous regions in space and time in optical remote sensing images. Tests were conducted by considering the Dynamic Time Warping measure as the homogeneity criterion. Study cases on high temporal resolution for sequences of MODIS and Landsat-8 OLI vegetation indices products provided satisfactory outputs and demonstrated the potential of the spatio-temporal segmentation method.

Bibliographic Details

Main Authors:	COSTA, W. S., FONSECA, L. M. G., KÖRTING, T. S., SIMÕES, M., BENDINI, H. N., SOUZA, R. C. M.
Other Authors:	WANDERSON S. COSTA, INPE; LEILA M. G. FONSECA, INPE; THALES S. KÖRTING, INPE; MARGARETH GONCALVES SIMOES, CNPS; HUGO N. BENDINI, INPE; RICARDO C. M. SOUZA, INPE.
Format:	Anais e Proceedings de eventos biblioteca
Language:	English eng
Published:	2017-12-14
Subjects:	Séries temporais, MODIS., Sensoriamento Remoto., Landsat, Remote sensing.,
Online Access:	http://www.alice.cnptia.embrapa.br/alice/handle/doc/1082573
Tags:	Add Tag No Tags, Be the first to tag this record!