A vision-based system for early fire detection

José António Barata Oliveira; DEE Group Author

doi:10.1109/ICSMC.2012.6377815

A vision-based system for early fire detection

José António Barata Oliveira, DEE Group Author

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

10 Citations (Scopus)

Abstract

This paper presents a video-based early fire detection system. Focus is given to the challenges related to the actual deployment of the vision system. Most importantly, background subtraction is performed in a windowed way for improved accuracy, an attentive mechanism is employed to focus a computationally expensive frequency analysis of potential fire regions, interaction with a people detection and tracking system is included so as to enable model-based false alarms rejection, a new colour-based model of fire's appearance as well as a new Wavelet-based model of fire's frequency signature are proposed, and the camera-world mapping is approximated according to a GPS-based learning calibration process. An average success rate of 92.7% at a processing rate of 10 Hz shows the applicability of the model to real-life applications.

Original language	Unknown
Title of host publication	IEEE International Conference on Systems Man and Cybernetics Conference (SMC)
Pages	739-744
ISBN (Electronic)	978-1-4673-1712-2
DOIs	https://doi.org/10.1109/ICSMC.2012.6377815
Publication status	Published - 1 Jan 2012
Event	IEEE International Conference on Systems, Man, and Cybernetics (SMC) - Duration: 1 Jan 2012 → …

Conference

Conference	IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Period	1/01/12 → …

Access to Document

10.1109/ICSMC.2012.6377815

Cite this

Barata Oliveira, J. A., & DEE Group Author (2012). A vision-based system for early fire detection. In IEEE International Conference on Systems Man and Cybernetics Conference (SMC) (pp. 739-744) https://doi.org/10.1109/ICSMC.2012.6377815

@inproceedings{ed028b1067a642cab2b7300d61206df0,

title = "A vision-based system for early fire detection",

abstract = "This paper presents a video-based early fire detection system. Focus is given to the challenges related to the actual deployment of the vision system. Most importantly, background subtraction is performed in a windowed way for improved accuracy, an attentive mechanism is employed to focus a computationally expensive frequency analysis of potential fire regions, interaction with a people detection and tracking system is included so as to enable model-based false alarms rejection, a new colour-based model of fire's appearance as well as a new Wavelet-based model of fire's frequency signature are proposed, and the camera-world mapping is approximated according to a GPS-based learning calibration process. An average success rate of 92.7{\%} at a processing rate of 10 Hz shows the applicability of the model to real-life applications.",

keywords = "Fire detection, computer vision systems, video and image processing",

author = "{Barata Oliveira}, {Jos{\'e} Ant{\'o}nio} and {DEE Group Author}",

year = "2012",

month = "1",

day = "1",

doi = "10.1109/ICSMC.2012.6377815",

language = "Unknown",

isbn = "978-1-4673-1713-9",

pages = "739--744",

booktitle = "IEEE International Conference on Systems Man and Cybernetics Conference (SMC)",

}

TY - GEN

T1 - A vision-based system for early fire detection

AU - Barata Oliveira, José António

AU - DEE Group Author

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper presents a video-based early fire detection system. Focus is given to the challenges related to the actual deployment of the vision system. Most importantly, background subtraction is performed in a windowed way for improved accuracy, an attentive mechanism is employed to focus a computationally expensive frequency analysis of potential fire regions, interaction with a people detection and tracking system is included so as to enable model-based false alarms rejection, a new colour-based model of fire's appearance as well as a new Wavelet-based model of fire's frequency signature are proposed, and the camera-world mapping is approximated according to a GPS-based learning calibration process. An average success rate of 92.7% at a processing rate of 10 Hz shows the applicability of the model to real-life applications.

AB - This paper presents a video-based early fire detection system. Focus is given to the challenges related to the actual deployment of the vision system. Most importantly, background subtraction is performed in a windowed way for improved accuracy, an attentive mechanism is employed to focus a computationally expensive frequency analysis of potential fire regions, interaction with a people detection and tracking system is included so as to enable model-based false alarms rejection, a new colour-based model of fire's appearance as well as a new Wavelet-based model of fire's frequency signature are proposed, and the camera-world mapping is approximated according to a GPS-based learning calibration process. An average success rate of 92.7% at a processing rate of 10 Hz shows the applicability of the model to real-life applications.

KW - Fire detection

KW - computer vision systems

KW - video and image processing

U2 - 10.1109/ICSMC.2012.6377815

DO - 10.1109/ICSMC.2012.6377815

M3 - Conference contribution

SN - 978-1-4673-1713-9

SP - 739

EP - 744

BT - IEEE International Conference on Systems Man and Cybernetics Conference (SMC)

ER -