Fire Detection in Video Using LMS Based Active Learning

• Published in: Fire technology Vol. 46; no. 3; pp. 551 - 577
• Main Authors: GÜNAY, Osman, TASDEMIR, Kasim, TÖREYIN, B. Uğur, ENIS CETIN, A
• Format: Journal Article
• Language: English
• Published: Boston Boston : Springer US 01.07.2010; Springer US; Springer; Springer Nature B.V
• Subjects: Active learning; Algorithms; Applied sciences; Boundaries; Building technical equipments; Buildings; Buildings. Public works; Cameras; Characterization and Evaluation of Materials; Civil Engineering; Classical Mechanics; Decision Fusion; Decision making models; Detection alarms; Detection. Firefighting. Smoke control. Evacuation; Engineering; Exact sciences and technology; fire detection; Fire protection; Fires; Least-mean-square methods; Markov chains; On-line learning; Physics; Spatial analysis; Surveillance; Video; Wavelet transforms; Decision Fusion; Least-mean-square methods; Fire detection; Active learning; On-line learning; Video technique; Markov model; Algorithm; Learning; Flame detection; Experimental result; Least squares method; Wavelet base; Decision fusion; Method study
• ISSN: 0015-2684; 1572-8099
• DOI: 10.1007/s10694-009-0106-8

In this paper, a video based algorithm for fire and flame detection is developed. In addition to ordinary motion and color clues, flame flicker is distinguished from motion of flame colored moving objects using Markov models. Irregular nature of flame boundaries is detected by performing temporal wavelet analysis using Hidden Markov Models as well. Color variations in fire is detected by computing the spatial wavelet transform of moving fire-colored regions. Boundary of flames are represented in wavelet domain and irregular nature of the boundaries of fire regions is also used as an indication of the flame flicker. Decisions from sub-algorithms are linearly combined using an adaptive active fusion method. The main detection algorithm is composed of four sub-algorithms (i) detection of fire colored moving objects, (ii) temporal, and (iii) spatial wavelet analysis for flicker detection and (iv) contour analysis of fire colored region boundaries. Each algorithm yields a continuous decision value as a real number in the range [−1, 1] at every image frame of a video sequence. Decision values from sub-algorithms are fused using an adaptive algorithm in which weights are updated using the least mean square (LMS) method in the training (learning) stage.