Vision-based indoor scene cognition using a spatial probabilistic modeling method

Jwu-Sheng Hu*, Tzung Min Su, Heng Chia Huang, Pei Ching Lin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

This work describes a vision-based approach to recognize scene in the indoor environment. The proposed method represents each scene captured by a Pan-Tilt-Zoom (PTZ) camera with a blob model using spatial probabilistic modeling. Although the details of the scene covered by the camera are lost, this model is efficient in memorizing the scene characteristics and is robust against image distortions. Furthermore, multi-view recognition is studied to increase the precision of scene cognition via a partial knowledge of the scene. The images captured in the same location with different view angles are collected to extract the scene characteristics in order to decrease the memory storage size for each location. The effectiveness of the method is demonstrated by experiments in an unstructured indoor environment.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Automation Science and Engineering, CASE
Pages620-625
Number of pages6
DOIs
StatePublished - 1 Dec 2007
Event2006 IEEE International Conference on Automation Science and Engineering, CASE - Shanghai, China
Duration: 8 Oct 200610 Oct 2006

Publication series

Name2006 IEEE International Conference on Automation Science and Engineering, CASE

Conference

Conference2006 IEEE International Conference on Automation Science and Engineering, CASE
CountryChina
CityShanghai
Period8/10/0610/10/06

Keywords

  • Characteristic view
  • Gaussian mixture model
  • Probabilistic modeling
  • Scene cognition

Fingerprint Dive into the research topics of 'Vision-based indoor scene cognition using a spatial probabilistic modeling method'. Together they form a unique fingerprint.

Cite this