loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Shaou-Gang Miaou 1 ; Cheng-Yu Chien 1 ; Fu-Chiau Shih 1 and Chia-Yuan Huang 2

Affiliations: 1 Chung Yuan Christian University, Taiwan ; 2 Industrial Technology Research Institute, Taiwan

ISBN: 978-989-8111-60-9

Keyword(s): Surveillance system, omni-directional camera, PTZ camera, fall detecting.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Motion, Tracking and Stereo Vision ; Video Surveillance and Event Detection

Abstract: We propose a new surveillance system that uses both omni-directional (OD) and Pan/Tilt/Zoom (PTZ) cameras with heterogeneous characteristics and a relatively simple image processing algorithm to achieve the goal of real time surveillance. The system is demonstrated for detecting the occurrence of human’s fall-down event. An OD camera has a 360º viewing angle. It is used here to replace the multiple traditional cameras having limited viewing angles in order to reduce the system cost. A PTZ camera is also used in the system to track the target of interest and verify the occurrence of the event. Various unique features obtained from OD images are used for fall down detection and a multi-classifier approach is used for better recognition performance. Experimental results show that the system is quite robust to sudden changes of walking paths and different directions of falling. During the tracking process, a moving target is captured and its representative coordinates is obtained based on the processing of continuous OD images. The coordinates of the target in the OD camera space will be converted to its corresponding three dimensional (3D) coordinates in a real-world space. This derived information is served as guidance for the automatic control of the PTZ camera to track the moving target as closely as it can. By combining the advantages of two heterogeneous types of cameras, our experimental results show that the proposed system can track the moving target well without the need of a complicated method, showing the feasibility and potential of the system. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.207.136.184

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Miaou S.; Chien C.; Shih F.; Huang C. and (2008). A SMART SURVEILLANCE SYSTEM FOR HUMAN FALL-DOWN DETECTION USING DUAL HETEROGENEOUS CAMERAS.In Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2008) ISBN 978-989-8111-60-9, pages 291-299. DOI: 10.5220/0001933402910299

@conference{sigmap08,
author={Shaou{-}Gang Miaou and Cheng{-}Yu Chien and Fu{-}Chiau Shih and Chia{-}Yuan Huang},
title={A SMART SURVEILLANCE SYSTEM FOR HUMAN FALL-DOWN DETECTION USING DUAL HETEROGENEOUS CAMERAS},
booktitle={Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2008)},
year={2008},
pages={291-299},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001933402910299},
isbn={978-989-8111-60-9},
}

TY - CONF

JO - Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2008)
TI - A SMART SURVEILLANCE SYSTEM FOR HUMAN FALL-DOWN DETECTION USING DUAL HETEROGENEOUS CAMERAS
SN - 978-989-8111-60-9
AU - Miaou, S.
AU - Chien, C.
AU - Shih, F.
AU - Huang, C.
PY - 2008
SP - 291
EP - 299
DO - 10.5220/0001933402910299

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.