Fire and smoke detection in video with optimal mass transport based optical flow and neural networks

Abstract

Detection of fire and smoke in video is of practical and theoretical interest. In this paper, we propose the use of optimal mass transport (OMT) optical flow as a low-dimensional descriptor of these complex processes. The detection process is posed as a supervised Bayesian classification problem with spatio-temporal neighborhoods of pixels;feature vectors are composed of OMT velocities and R,G,B color channels. The classifier is implemented as a single-hidden-layer neural network. Sample results show probability of pixels belonging to fire or smoke. In particular, the classifier successfully distinguishes between smoke and similarly colored white wall, as well as fire from a similarly colored background.

A Saliency-Based Method for Early Smoke Detection in Video Sequences

“…The saliency map is calculated using Eq. (13). Different window scales are used here; the parameters are …”

“…Thus, the main emphasis of research has shifted to VSD [7][8][9][10][11]. Most VSD schemes have three stages: [12][13][14][15][16]; the first stage is the detection of a candidate smoke region, the second stage is the extraction and analysis of smoke features, and the final stage is verification of the smoke region. The detection of a candidate smoke region greatly affects the detection rate and final detection efficiency of subsequent procedures.…”

Video fire detection – Review

“…Well-known moving object detection algorithms are background (BG) subtraction methods [16,21,18,14,13,17,20,22,27,28,30,34], temporal differencing [19], and optical flow analysis [9,8,29]. They can all be used as part of a VFD system.…”

“…Although dynamic textures are easily observed by human eyes, they are difficult to discern using computer vision methods as the spatial location and extent of dynamic textures can vary with time and they can be partially transparent. Some dynamic texture and pattern analysis methods in video [29,33,35] are closely related to spatial difference analysis.…”

“…Other classification methods include the AdaBoost method [22], neural networks [29,35], Bayesian classifiers [30,32], Markov models [28,33] and rule-based classification [58].…”