Mixing hierarchical contexts for object recognition

Peralta, B; Soto A.

Keywords: model, information, communities, recognition, variation, world, mixture, computer, detection, visual, vision, object, clutter, background, occlusions, pose, Partial, Graphical, Contextual, Co-ocurrences

Abstract

Robust category-level object recognition is currently a major goal for the Computer Vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual information in the form of object co-ocurrences and spatial contraints has been successfully applied to reduce the inherent uncertainty of the visual world. Recently, Choi et al. [5] propose the use of a tree-structured graphical model to capture contextual relations among objects. Under this model there is only one possible fixed contextual relation among subsets of objects. In this work we extent Choi et al. approach by using a mixture model to consider the case that contextual relations among objects depend on scene type. Our experiments highlight the advantages of our proposal, showing that the adaptive specialization of contextual relations improves object recognition and object detection performances. © 2011 Springer-Verlag.

Más información

Título de la Revista: EDUCATING FOR A NEW FUTURE: MAKING SENSE OF TECHNOLOGY-ENHANCED LEARNING ADOPTION, EC-TEL 2022
Volumen: 7042
Editorial: SPRINGER INTERNATIONAL PUBLISHING AG
Fecha de publicación: 2011
Página de inicio: 232
Página final: 239
URL: http://www.scopus.com/inward/record.url?eid=2-s2.0-81855177176&partnerID=q2rCbXpz