Context-based vision system for place and object recognition
A. Torralba, K. Murphy, W. Freeman, and M. Rubin. Computer Vision, 2003. Proceedings. Ninth IEEE International Conference
on, page 273--280 vol.1. (2003)
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.
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., tables are more likely in an office
than a street). We present a low-dimensional global image representation
that provides relevant information for place recognition and categorization,
and show 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 realtime feedback
to the user.
%0 Conference Paper
%1 Torralba2003a
%A Torralba, A.
%A Murphy, K.P.
%A Freeman, W.T.
%A Rubin, M.A.
%B Computer Vision, 2003. Proceedings. Ninth IEEE International Conference
on
%D 2003
%K categorization, context-based detection, feedback global image low-dimensional mobile object place realtime recognition, representation, robot robots, system, vision vision,
%P 273--280 vol.1
%T Context-based vision system for place and object recognition
%X 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.
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., tables are more likely in an office
than a street). We present a low-dimensional global image representation
that provides relevant information for place recognition and categorization,
and show 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 realtime feedback
to the user.
@inproceedings{Torralba2003a,
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.
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., tables are more likely in an office
than a street). We present a low-dimensional global image representation
that provides relevant information for place recognition and categorization,
and show 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 realtime feedback
to the user.},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Torralba, A. and Murphy, K.P. and Freeman, W.T. and Rubin, M.A.},
biburl = {https://www.bibsonomy.org/bibtex/2f4a1572359d023e62266f26317676433/mozaher},
booktitle = {Computer Vision, 2003. Proceedings. Ninth IEEE International Conference
on},
file = {01238354.pdf:Torralba2003a.pdf:PDF},
interhash = {0eda4d11357d0af06c72a0bfe0d80959},
intrahash = {f4a1572359d023e62266f26317676433},
keywords = {categorization, context-based detection, feedback global image low-dimensional mobile object place realtime recognition, representation, robot robots, system, vision vision,},
owner = {Mozaher},
pages = {273--280 vol.1},
timestamp = {2009-09-12T19:19:43.000+0200},
title = {Context-based vision system for place and object recognition},
year = 2003
}