Wildfire detection using LMS based active learning

B. Ugur Toreyin; A. Enis Cetin

doi:10.1109/ICASSP.2009.4959870

Wildfire detection using LMS based active learning

B. Ugur Toreyin^*, A. Enis Cetin

^*Corresponding author for this work

Bilkent University

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

40 Citations (Scopus)

Abstract

A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower.

Original language	English
Title of host publication	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009
Pages	1461-1464
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2009.4959870
Publication status	Published - 2009
Externally published	Yes
Event	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China Duration: 19 Apr 2009 → 24 Apr 2009

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
Country/Territory	Taiwan, Province of China
City	Taipei
Period	19/04/09 → 24/04/09

Keywords

Active learning
Least mean square methods
Wildfire detection

Access to Document

10.1109/ICASSP.2009.4959870

Cite this

Ugur Toreyin, B., & Enis Cetin, A. (2009). Wildfire detection using LMS based active learning. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009 (pp. 1461-1464). Article 4959870 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2009.4959870

@inproceedings{df6f7de5c4f144d39c1e4a953966400a,

title = "Wildfire detection using LMS based active learning",

abstract = "A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower.",

keywords = "Active learning, Least mean square methods, Wildfire detection",

author = "{Ugur Toreyin}, B. and {Enis Cetin}, A.",

year = "2009",

doi = "10.1109/ICASSP.2009.4959870",

language = "English",

isbn = "9781424423545",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "1461--1464",

booktitle = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009",

note = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 ; Conference date: 19-04-2009 Through 24-04-2009",

}

Ugur Toreyin, B & Enis Cetin, A 2009, Wildfire detection using LMS based active learning. in 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009., 4959870, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1461-1464, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, Taiwan, Province of China, 19/04/09. https://doi.org/10.1109/ICASSP.2009.4959870

Wildfire detection using LMS based active learning. / Ugur Toreyin, B.; Enis Cetin, A.
2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009. 2009. p. 1461-1464 4959870 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

TY - GEN

T1 - Wildfire detection using LMS based active learning

AU - Ugur Toreyin, B.

AU - Enis Cetin, A.

PY - 2009

Y1 - 2009

N2 - A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower.

AB - A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower.

KW - Active learning

KW - Least mean square methods

KW - Wildfire detection

UR - http://www.scopus.com/inward/record.url?scp=70349203841&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4959870

DO - 10.1109/ICASSP.2009.4959870

M3 - Conference contribution

AN - SCOPUS:70349203841

SN - 9781424423545

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1461

EP - 1464

BT - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009

T2 - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009

Y2 - 19 April 2009 through 24 April 2009

ER -

Wildfire detection using LMS based active learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this