Smoke detection in video using wavelets and support vector machines
TL;DR: A novel method for smoke characterization using wavelets and support vector machines is proposed and the results are impressive with limited false alarms.
About: This article is published in Fire Safety Journal.The article was published on 2009-11-01. It has received 181 citations till now. The article focuses on the topics: Video processing.
Citations
More filters
TL;DR: This is a review article describing the recent developments in Video based Fire Detection (VFD), which may help reduce the detection time compared to the currently available sensors in both indoors and outdoors.
220 citations
Cites background or methods from "Smoke detection in video using wave..."
...As in any video processing method, morphological operations, subblocking and clean-up post-processing such as median-filtering are used as an integral part of any VFD system [21,22,25,20,26,33, 36,59]....
[...]
...As it is well known, flames flicker in uncontrolled fires, therefore flicker detection [24,18,12,13,27,28,30] in video and waveletdomain signal energy analysis [21,14,20,26,31,39] can be used to distinguish ordinary objects from fire....
[...]
...Yuan [22], 2008 RGB X X X Borges [23], 2008 RGB X Qi [24], 2009 RGB/HSV X X X Yasmin [25], 2009 RGB/HSI X X X Gubbi [26], 2009 X X X A ....
[...]
TL;DR: A novel deep normalization and convolutional neural network (DNCNN) with 14 layers to implement automatic feature extraction and classification and to reduce overfitting caused by imbalanced and insufficient training samples is proposed.
Abstract: It is a challenging task to recognize smoke from images due to large variance of smoke color, texture, and shapes. There are smoke detection methods that have been proposed, but most of them are based on hand-crafted features. To improve the performance of smoke detection, we propose a novel deep normalization and convolutional neural network (DNCNN) with 14 layers to implement automatic feature extraction and classification. In DNCNN, traditional convolutional layers are replaced with normalization and convolutional layers to accelerate the training process and boost the performance of smoke detection. To reduce overfitting caused by imbalanced and insufficient training samples, we generate more training samples from original training data sets by using a variety of data enhancement techniques. Experimental results show that our method achieved very low false alarm rates below 0.60% with detection rates above 96.37% on our smoke data sets.
198 citations
Cites methods from "Smoke detection in video using wave..."
...[3] proposed a video smoke detection method by handcrafting features, which consists of geometric mean, standard deviation, skewness, kurtosis, arithmetic mean and entropy over every subband of wavelet transformed images....
[...]
TL;DR: This review outlines the state of the art in direct, semi-automated and automated fire detection from both manned and unmanned aerial platforms and discusses the operational constraints and opportunities provided by these sensor systems.
Abstract: For decades detection and monitoring of forest and other wildland fires has relied heavily on aircraft (and satellites). Technical advances and improved affordability of both sensors and sensor platforms promise to revolutionize the way aircraft detect, monitor and help suppress wildfires. Sensor systems like hyperspectral cameras, image intensifiers and thermal cameras that have previously been limited in use due to cost or technology considerations are now becoming widely available and affordable. Similarly, new airborne sensor platforms, particularly small, unmanned aircraft or drones, are enabling new applications for airborne fire sensing. In this review we outline the state of the art in direct, semi-automated and automated fire detection from both manned and unmanned aerial platforms. We discuss the operational constraints and opportunities provided by these sensor systems including a discussion of the objective evaluation of these systems in a realistic context.
177 citations
Cites background from "Smoke detection in video using wave..."
...Objects seen through smoke are lower contrast and less distinct and the reduced energy or contrast of edges has been used a feature in video smoke detection algorithms [34,41]....
[...]
TL;DR: Wang et al. as mentioned in this paper proposed a video-based smoke detection method by using a histogram sequence of pyramids, which involves four steps: first, through multi-scale analysis, a 3-level image pyramid is constructed.
173 citations
TL;DR: A new deep dual-channel neural network (DCNN) for smoke detection that has attained a very high detection rate that exceeds 99.5% on average, superior to state-of-the-art relevant competitors.
Abstract: Smoke detection plays an important role in industrial safety warning systems and fire prevention. Due to the complicated changes in the shape, texture, and color of smoke, identifying the smoke from a given image still remains a substantial challenge, and this has accordingly aroused a considerable amount of research attention recently. To address the problem, we devise a new deep dual-channel neural network (DCNN) for smoke detection. In contrast to popular deep convolutional networks (e.g., Alex-Net, VGG-Net, Res-Net, and Dense-Net and the DNCNN that is specifically devoted to detecting smoke), our proposed end-to-end network is mainly composed of dual channels of deep subnetworks. In the first subnetwork, we sequentially connect multiple convolutional layers and max-pooling layers. Then, we selectively append the batch normalization layer to each convolutional layer for overfitting reduction and training acceleration. The first subnetwork is shown to be good at extracting the detailed information of smoke, such as texture. In the second subnetwork, in addition to the convolutional, batch normalization, and max-pooling layers, we further introduce two important components. One is the skip connection for avoiding the vanishing gradient and improving the feature propagation. The other is the global average pooling for reducing the number of parameters and mitigating the overfitting issue. The second subnetwork can capture the base information of smoke, such as contours. We finally deploy a concatenation operation to combine the aforementioned two deep subnetworks to complement each other. Based on the augmented data obtained by rotating the training images, our proposed DCNN can promptly and stably converge to the perfect performance. Experimental results conducted on the publicly available smoke detection database verify that the proposed DCNN has attained a very high detection rate that exceeds 99.5% on average, superior to state-of-the-art relevant competitors. Furthermore, our DCNN only employs approximately one-third of the parameters needed by the comparatively tested deep neural networks. The source code of DCNN will be released at https://kegu.netlify.com/ .
128 citations
Cites methods from "Smoke detection in video using wave..."
...In [2], by introducing wavelet decompositions and a support vector machine (SVM), Gubbi et al....
[...]
References
More filters
01 Jan 1998
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Abstract: A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
26,531 citations
"Smoke detection in video using wave..." refers background in this paper
...Support vector machines introduced by Vapnik [26] are a relatively new class of learning machines that have evolved from the concepts of structural risk minimization (SRM) [27] and regularization theory....
[...]
TL;DR: There are several arguments which support the observed high accuracy of SVMs, which are reviewed and numerous examples and proofs of most of the key theorems are given.
Abstract: The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and non-separable data, working through a non-trivial example in detail. We describe a mechanical analogy, and discuss when SVM solutions are unique and when they are global. We describe how support vector training can be practically implemented, and discuss in detail the kernel mapping technique which is used to construct SVM solutions which are nonlinear in the data. We show how Support Vector machines can have very large (even infinite) VC dimension by computing the VC dimension for homogeneous polynomial and Gaussian radial basis function kernels. While very high VC dimension would normally bode ill for generalization performance, and while at present there exists no theory which shows that good generalization performance is guaranteed for SVMs, there are several arguments which support the observed high accuracy of SVMs, which we review. Results of some experiments which were inspired by these arguments are also presented. We give numerous examples and proofs of most of the key theorems. There is new material, and I hope that the reader will find that even old material is cast in a fresh light.
15,696 citations
TL;DR: In this article, a discrete cosine transform (DCT) is defined and an algorithm to compute it using the fast Fourier transform is developed, which can be used in the area of digital processing for the purposes of pattern recognition and Wiener filtering.
Abstract: A discrete cosine transform (DCT) is defined and an algorithm to compute it using the fast Fourier transform is developed. It is shown that the discrete cosine transform can be used in the area of digital processing for the purposes of pattern recognition and Wiener filtering. Its performance is compared with that of a class of orthogonal transforms and is found to compare closely to that of the Karhunen-Loeve transform, which is known to be optimal. The performances of the Karhunen-Loeve and discrete cosine transforms are also found to compare closely with respect to the rate-distortion criterion.
4,481 citations
Book•
15 Aug 1990TL;DR: This paper presents two Dimensional DCT Algorithms and their relations to the Karhunen-Loeve Transform, and some applications of the DCT, which demonstrate the ability of these algorithms to solve the discrete cosine transform problem.
Abstract: Discrete Cosine Transform. Definitions and General Properties. DCT and Its Relations to the Karhunen-Loeve Transform. Fast Algorithms for DCT-II. Two Dimensional DCT Algorithms. Performance of the DCT. Applications of the DCT. Appendices. References. Index.
2,039 citations
TL;DR: This paper presents an overview of image processing and analysis tools used in traffic applications and relates these tools with complete systems developed for specific traffic applications, and categorizes processing methods based on the intrinsic organization of their input data and the domain of processing.
606 citations
"Smoke detection in video using wave..." refers background in this paper
...These systems are economically viable as CCD cameras are already available for traffic monitoring [4] and surveillance [5] applications....
[...]