Best Merge Region-Growing Segmentation with Intergrated Nonadjacent Region Object Aggregation

Abstract : Best merge region growing normally produces seg- mentations with closed connected region objects. Recognizing that spectrally similar objects often appear in spatially separate loca- tions, we present an approach for tightly integrating best merge region growing with nonadjacent region object aggregation, which we call hierarchical segmentation or HSeg. However, the original implementation of nonadjacent region object aggregation in HSeg required excessive computing time even for moderately sized im- ages because of the required intercomparison of each region with all other regions. This problem was previously addressed by a recursive approximation of HSeg, called RHSeg. In this paper, we introduce a refined implementation of nonadjacent region object aggregation in HSeg that reduces the computational requirements of HSeg without resorting to the recursive approximation. In this refinement, HSeg's region intercomparisons among nonadjacent regions are limited to regions of a dynamically determined mini- mum size. We show that this refined version of HSeg can process moderately sized images in about the same amount of time as RHSeg incorporating the original HSeg. Nonetheless, RHSeg is still required for processing very large images due to its lower computer memory requirements and amenability to parallel pro- cessing. We then note a limitation of RHSeg with the original HSeg for high spatial resolution images and show how incorpo- rating the refined HSeg into RHSeg overcomes this limitation. The quality of the image segmentations produced by the refined HSeg is then compared with other available best merge segmentation approaches. Finally, we comment on the unique nature of the hierarchical segmentations produced by HSeg.
Type de document :
Article dans une revue
IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2012, 50 (11), pp.4454-4467. 〈10.1109/TGRS.2012.2190079〉
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00737067
Contributeur : Yuliya Tarabalka <>
Soumis le : lundi 1 octobre 2012 - 11:22:56
Dernière modification le : samedi 27 janvier 2018 - 01:30:41
Document(s) archivé(s) le : mercredi 2 janvier 2013 - 05:00:09

Fichier

2012_Tilton.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

James Tilton, Yuliya Tarabalka, Paul Montesano, Emanuel Gofman. Best Merge Region-Growing Segmentation with Intergrated Nonadjacent Region Object Aggregation. IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2012, 50 (11), pp.4454-4467. 〈10.1109/TGRS.2012.2190079〉. 〈hal-00737067〉

Partager

Métriques

Consultations de la notice

268

Téléchargements de fichiers

1083