Multi-image segmentation: A collaborative approach based on binary partition trees

• Main Authors: Francky Randrianasoa, Jimmy, Kurtz, Camille, Desjardin, Eric, Passat, Nicolas
• Other Authors: Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804 (CRESTIC), Université de Reims Champagne-Ardenne (URCA), Laboratoire d'Informatique Paris Descartes (LIPADE - EA 2517), Université Paris Descartes - Paris 5 (UPD5), ANR-10-BLAN-0205,KIDICO,Intégration des connaissances pour la convolution discrète, la segmentation et la reconstruction d'informations dans les images digitales(2010), ANR-12-MONU-0001,Coclico,COllaboration, CLassification, Incrémentalité et COnnaissances(2012)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2015
• Subjects: morphological hierarchies; multi-image; collaborative strategies; binary partition tree; remote sensing; segmentation fusion; col- laborative strategies; [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]; [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]; Iceland
• Online Access: https://hal.univ-reims.fr/hal-01695074; https://hal.univ-reims.fr/hal-01695074/document; https://hal.univ-reims.fr/hal-01695074/file/Randrianasoa_ISMM_2015.pdf; https://doi.org/10.1007/978-3-319-18720-4_22

International audience Image segmentation is generally performed in a "one image, one algorithm" paradigm. However, it is sometimes required to consider several images of a same scene, or to carry out several (or several occurrences of a same) algorithm(s) to fully capture relevant information. To solve the induced segmentation fusion issues, various strategies have been already investigated for allowing a consensus between several segmentation outputs. This article proposes a contribution to segmentation fusion, with a specific focus on the "n images" part of the paradigm. Its main originality is to act on the segmentation research space, i.e., to work at an earlier stage than standard segmentation fusion approaches. To this end, an algorithmic framework is developed to build a binary partition tree in a collaborative fashion, from several images, thus allowing to obtain a unified hierarchical segmentation space. This framework is, in particular, designed to embed consensus policies inherited from the machine learning domain. Application examples proposed in remote sensing emphasise the potential usefulness of our approach for satellite image processing.