Conference Paper

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

DOI: 10.1109/ICIP.2010.5652119 Conference: Proceedings of the International Conference on Image Processing, ICIP 2010, September 26-29, Hong Kong, China
Source: DBLP


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.

1 Follower
86 Reads
  • Source
    • "They extend this work to flame detection in infrared videos [14]. Kolesov et al. [8] propose to combine Optimal Mass Transport (OMT) optical flow and color as features for fire detection. The pixel-wise decision is based on a single-hidden-layer neural network. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a new Video Fire Detection (VFD) system for surveillance applications in fire and security industries. The system consists of three modules: pixel-level processing to identify potential fire blobs, blob-based spatial-temporal feature extraction, and a Support Vector Machine (SVM) classifier. The proposed novel spatial-temporal features include a spatial-temporal structural feature and a spatial-temporal contour dynamics feature. The spatial-temporal structural features are extracted from an accumulated motion mask (AMM) and an accumulated intensity template (AIT), capturing the concentric ring structure of fire intensity. The spatial-temporal dynamics features are based on the Fourier descriptor of contours in space and time, capturing the dynamic properties of fire. These global blob-based features are more robust and effective in rejecting false alarms and nuisance sources than pixel-wise features. In addition, extraction of the spatial-temporal features is very efficient, and no tracking of blobs or contours is needed. We also present a new multi-spectrum fire video database for algorithm testing. We evaluate the effectiveness of the proposed features on fire detection on the video database and obtain very promising results.
    Applications of Computer Vision (WACV), 2013 IEEE Workshop on; 01/2013
    • "However, the assumption that smoke usually drifts upwards makes this model ineffective in a scenario where strong wind is present. Other research efforts have extracted motion features of smoke using optical flow (Kolesov et al. 2010; Yu et al. 2010); the results have been mixed. Recognizing the fact that the color of smoke is usually grayish, Chen et al (2006) extracted chromatic features of smoke according to a set of decision rules. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Existing video-based smoke detection methods often rely on the visual features extracted directly from the original frames. In the case of light smoke, the background is still visible and it deteriorates the quality of the features. This paper presents an approach to separating the smoke com- ponent from the background such that visual features can be extracted from the smoke component for reliable smoke detection. Specifically, an image is assumed to be a linear blending of a smoke component and a background image. Given a video frame and its background, the estimation of the blending parameter and the actual smoke component can be formulated as an optimization problem. Three methods based on different models for the smoke component are proposed to solve the optimization problem. Experimental results on synthesized and real video data have shown that the proposed approach can effectively separate the smoke component and the smoke detection performance is significantly improved by using the visual features extracted from the smoke com- ponent.
    International Journal of Computer Vision 01/2013; 105(3). DOI:10.1007/s11263-013-0656-6 · 3.81 Impact Factor
  • Source
    • "Yuan [1] proposed an accumulative motion model to capture motion characteristics of smoke. Other research efforts have extracted motion features of smoke using optical flow computation [2], [3]. Recognizing the fact that the color of smoke is usually grayish, Chen et al. [4] extracted chromatic features of smoke according to a set of decision rules. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In the state-of-the-art video-based smoke detection methods, the representation of smoke mainly depends on the visual information in the current image frame. In the case of light smoke, the original background can be still seen and may deteriorate the characterization of smoke. The core idea of this paper is to demonstrate the superiority of using smoke component for smoke detection. In order to obtain smoke component, a blended image model is constructed, which basically is a linear combination of background and smoke components. Smoke opacity which represents a weighting of the smoke component is also defined. Based on this model, an optimization problem is posed. An algorithm is devised to solve for smoke opacity and smoke component, given an input image and the background. The resulting smoke opacity and smoke component are then used to perform the smoke detection task. The experimental results on both synthesized and real image data verify the effectiveness of the proposed method.
    Multimedia and Expo (ICME), 2012 IEEE International Conference on; 01/2012
Show more