DocumentCode :
3470218
Title :
Door detection via signage context-based Hierarchical Compositional Model
Author :
Chen, Cheng ; Tian, YingLi
Author_Institution :
City Coll., City Univ. of New York, New York, NY, USA
fYear :
2010
fDate :
13-18 June 2010
Firstpage :
1
Lastpage :
6
Abstract :
Door detection by using wearable cameras helps people with severe vision impairment to independently access unknown environments. The goal of this paper is to robustly detect different doors and classify them as office doors, elevators, exits, etc. These tasks are challenging due to the factors: 1) small inter-class variations of different objects such as office doors and elevators, 2) only part of an object is captured due to occlusions or continuous camera moving of a mobile system. To overcome the above challenges, we propose a Hierarchical Compositional Model (HCM) approach which incorporates context information into the model decomposition process of a part-based HCM to handle partially captured objects as well as large intra-class variations in different environments. Our preliminary experimental results demonstrate promising performance on doors detection over a wide range of scales, view points, and occlusions.
Keywords :
computer vision; handicapped aids; object detection; continuous camera movement; door detection; large intraclass variation; model decomposition process; severe vision impairment; signage context based hierarchical compositional model; wearable camera; Cameras; Cities and towns; Context modeling; Deformable models; Elevators; Graphical models; Navigation; Object detection; Power system reliability; Tree graphs;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on
Conference_Location :
San Francisco, CA
ISSN :
2160-7508
Print_ISBN :
978-1-4244-7029-7
Type :
conf
DOI :
10.1109/CVPRW.2010.5543894
Filename :
5543894
Link To Document :
بازگشت