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

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

doi:10.1109/COASE.2006.326953

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

National Chiao Tung University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-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 language	English
Title of host publication	2006 IEEE International Conference on Automation Science and Engineering, CASE
Pages	620-625
Number of pages	6
DOIs	https://doi.org/10.1109/COASE.2006.326953
State	Published - 1 Dec 2007
Event	2006 IEEE International Conference on Automation Science and Engineering, CASE - Shanghai, China Duration: 8 Oct 2006 → 10 Oct 2006

Publication series

Name	2006 IEEE International Conference on Automation Science and Engineering, CASE

Conference

Conference	2006 IEEE International Conference on Automation Science and Engineering, CASE
Country	China
City	Shanghai
Period	8/10/06 → 10/10/06

Keywords

Characteristic view
Gaussian mixture model
Probabilistic modeling
Scene cognition

Access to Document

10.1109/COASE.2006.326953

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

@inproceedings{67590da75abc42a4ad666c5e3844a524,

title = "Vision-based indoor scene cognition using a spatial probabilistic modeling method",

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.",

keywords = "Characteristic view, Gaussian mixture model, Probabilistic modeling, Scene cognition",

author = "Jwu-Sheng Hu and Su, {Tzung Min} and Huang, {Heng Chia} and Lin, {Pei Ching}",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/COASE.2006.326953",

language = "English",

isbn = "1424403103",

series = "2006 IEEE International Conference on Automation Science and Engineering, CASE",

pages = "620--625",

booktitle = "2006 IEEE International Conference on Automation Science and Engineering, CASE",

note = "null ; Conference date: 08-10-2006 Through 10-10-2006",

}

Hu, J-S, Su, TM, Huang, HC & Lin, PC 2007, Vision-based indoor scene cognition using a spatial probabilistic modeling method. in 2006 IEEE International Conference on Automation Science and Engineering, CASE., 4120419, 2006 IEEE International Conference on Automation Science and Engineering, CASE, pp. 620-625, 2006 IEEE International Conference on Automation Science and Engineering, CASE, Shanghai, China, 8/10/06. https://doi.org/10.1109/COASE.2006.326953

Vision-based indoor scene cognition using a spatial probabilistic modeling method. / Hu, Jwu-Sheng; Su, Tzung Min; Huang, Heng Chia; Lin, Pei Ching.

2006 IEEE International Conference on Automation Science and Engineering, CASE. 2007. p. 620-625 4120419 (2006 IEEE International Conference on Automation Science and Engineering, CASE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vision-based indoor scene cognition using a spatial probabilistic modeling method

AU - Hu, Jwu-Sheng

AU - Su, Tzung Min

AU - Huang, Heng Chia

AU - Lin, Pei Ching

PY - 2007/12/1

Y1 - 2007/12/1

N2 - 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.

AB - 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.

KW - Characteristic view

KW - Gaussian mixture model

KW - Probabilistic modeling

KW - Scene cognition

UR - http://www.scopus.com/inward/record.url?scp=45149102261&partnerID=8YFLogxK

U2 - 10.1109/COASE.2006.326953

DO - 10.1109/COASE.2006.326953

M3 - Conference contribution

SN - 1424403103

SN - 9781424403103

T3 - 2006 IEEE International Conference on Automation Science and Engineering, CASE

SP - 620

EP - 625

BT - 2006 IEEE International Conference on Automation Science and Engineering, CASE

Y2 - 8 October 2006 through 10 October 2006

ER -