Context-Based Vision System for Place and Object Recognition

DMCA

Context-Based Vision System for Place and Object Recognition (2003)

Cached

Download Links

Other Repositories/Bibliography

CiteULike
DBLP

by Antonio Torralba , Kevin P. Murphy , William T. Freeman , Mark Rubin

Citations:

317 - 9 self

BibTeX

@INPROCEEDINGS{Torralba03context-basedvision,
    author = {Antonio Torralba and Kevin P. Murphy and William T. Freeman and Mark Rubin},
    title = {Context-Based Vision System for Place and Object Recognition},
    booktitle = {},
    year = {2003},
    pages = {273--280}
}

OpenURL

Abstract

While navigating in an environment, a vision system has' to be able to recognize where it is' and what the main objects' in the scene are. In this paper we present a context-based vision system for place and object recognition. The goal is' to identify familiar locations' (e.g., office 610, conference room 941, Main Street), to categorize new environments' (office, corridor, street) and to use that information to provide contextualpriors for object recognition (e.g., table, chair, car, computeD. We present a low-dimensional global image representation that provides relevant information for place recognition and categorization, and how such contextual information introduces strong priors' that simplify object recognition. We have trained the system to recognize over 60 locations (indoors' and outdoors') and to suggest the presence and locations' of more than 20 different object types. The algorithm has been integrated into a mobile system that provides real-time feedback to the user. 1This work was sponsored by the Air Force under Air Force Contract F19628-00-C-0002. Opinions, interpretations, conclusions, and recommendations are those of the author and are not necessarily endorsed by the U.S. Government.

Keyphrases

object recognition context-based vision system real-time feedback main object air force contract f19628-00-c-0002 familiar location air force new environment u.s. government mobile system contextual information introduces strong prior main street low-dimensional global image representation relevant information conference room place recognition vision system different object type

DMCA