Adaptive hierarchical contexts for object recognition with conditional mixture of trees

Billy Peralta, Pablo Espinace, Alvaro Soto

Producción científica: Contribución a los distintos tipos de conferenciaArtículorevisión exhaustiva

2 Citas (Scopus)

Resumen

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-occurrences and spatial constraints, has been successfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relationships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.

Idioma originalInglés
DOI
EstadoPublicada - 1 ene. 2012
Evento2012 23rd British Machine Vision Conference, BMVC 2012 - Guildford, Surrey, Reino Unido
Duración: 3 sep. 20127 sep. 2012

Conferencia

Conferencia2012 23rd British Machine Vision Conference, BMVC 2012
País/TerritorioReino Unido
CiudadGuildford, Surrey
Período3/09/127/09/12

Áreas temáticas de ASJC Scopus

  • Visión artificial y reconocimiento de patrones

Huella

Profundice en los temas de investigación de 'Adaptive hierarchical contexts for object recognition with conditional mixture of trees'. En conjunto forman una huella única.

Citar esto