Return to search

Context-Based Vision System for Place and Object Recognition

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 contextual priors for object recognition (e.g., table, chair, car, computer). 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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6711
Date19 March 2003
CreatorsTorralba, Antonio, Murphy, Kevin P., Freeman, William T., Rubin, Mark A.
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format9 p., 7141251 bytes, 2104025 bytes, application/postscript, application/pdf
RelationAIM-2003-005

Page generated in 0.0015 seconds