Osman Günay

Entropy-Functional-Based Online Adaptive Decision Fusion Framework With Application to Wildfire Detection in Video

In this paper, an entropy-functional-based online adaptive decision fusion (EADF) framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several subalgorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular subalgorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing entropic projections onto convex sets describing subalgorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system was developed to evaluate the performance of the decision fusion algorithm. In this case, image data arrive sequentially, and the oracle is the security guard of the forest lookout tower, verifying the decision of the combined algorithm. The simulation results are presented.

Projections onto convex sets (POCS) based optimization by lifting

Summary form only given. A new optimization technique based on the projections onto convex space (POCS) framework for solving convex and some non-convex optimization problems are presented. The dimension of the minimization problem is lifted by one and sets corresponding to the cost function are defined. If the cost function is a convex function in RN the corresponding set which is the epigraph of the cost function is also a convex set in RN+1. The iterative optimization approach starts with an arbitrary initial estimate in RN+1 and an orthogonal projection is performed onto one of the sets in a sequential manner at each step of the optimization problem. The method provides globally optimal solutions in total-variation, filtered variation, l1, and entropic cost functions. It is also experimentally observed that cost functions based on lp; p <; 1 may be handled by using the supporting hyperplane concept. The new POCS based method can be used in image deblurring, restoration and compressive sensing problems.

Flame detection method in video using covariance descriptors

Video fire detection system which uses a spatio-temporal covariance matrix of video data is proposed. This system divides the video into spatio-temporal blocks and computes covariance features extracted from these blocks to detect fire. Feature vectors taking advantage of both the spatial and the temporal characteristics of flame colored regions are classified using an SVM classifier which is trained and tested using video data containing flames and flame colored objects. Experimental results are presented.

Online Adaptive Decision Fusion Framework Based on Entropic Projections onto Convex Sets with Application to Wildfire Detection in Video

In this paper, an online adaptive decision fusion framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several sub-algorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular sub-algorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing orthogonal projections onto convex sets describing sub-algorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system is developed to evaluate the performance of the algorithm in handling the problems where data arrives sequentially. In this case, the oracle is the security guard of the forest lookout tower verifying the decision of the combined algorithm. Simulation results are presented.

Flame detection for video-based early fire warning for the protection of cultural heritage

Cultural heritage and archaeological sites are exposed to the risk of fire and early warning is the only way to avoid losses and damages. The use of terrestrial systems, typically based on video cameras, is currently the most promising solution for advanced automatic wildfire surveillance and monitoring. Video cameras are sensitive in visible spectra and can be used either for flame or smoke detection. This paper presents and compares three video-based flame detection techniques, which were developed within the FIRESENSE EU research project.

Energy efficient cosine similarity measures according to a convex cost function

We propose a new family of vector similarity measures. Each measure is associated with a convex cost function. Given two vectors, we determine the surface normals of the convex function at the vectors. The angle between the two surface normals is the similarity measure. Convex cost function can be the negative entropy function, total variation (TV) function and filtered variation function constructed from wavelets. The convex cost functions need not to be differentiable everywhere. In general, we need to compute the gradient of the cost function to compute the surface normals. If the gradient does not exist at a given vector, it is possible to use the sub-gradients and the normal producing the smallest angle between the two vectors is used to compute the similarity measure. The proposed measures are compared experimentally to other nonlinear similarity measures and the ordinary cosine similarity measure. The TV-based vector product is more energy efficient than the ordinary inner product because it does not require any multiplications.

Wavelet based flame detection using differential PIR sensors

In this paper, a flame detection system using a differential Pyro-electric Infrared (PIR) sensor is proposed. A differential PIR sensor is only sensitive to sudden temperature variations within its viewing range and it produces a time-varying signal. The wavelet transform of the differential PIR sensor signal is used for feature extraction and feature vectors are fed to Markov models trained with uncontrolled fire flames and walking person. The model yielding the highest probability is chosen. Results suggest that the system can be used in spacious rooms for uncontrolled fire flame detection.

Real-time dynamic texture recognition using random sampling and dimension reduction

In this paper, we propose a real-time dynamic texture recognition method using projections onto random hyperplanes and deep neural network filters. We divide dynamic texture videos into spatio-temporal blocks and extract features using local binary patterns (LBP). We reduce the computational cost of the exhaustive LBP method by using randomly sampled subset of pixels in a given spatio-temporal block. We use random hyperplanes and deep neural network filters to reduce the dimensionality of the final feature vectors. We test the performance of the proposed method in a dynamic texture database. We also propose an application of the proposed method to real-time detection of flames in infrared videos. We observe that the approach based on random hyperplanes produces the best results.

Multisensor Fire Analysis

To avoid large-scale fire and smoke damage, timely and accurate fire detection is essential. The sooner the fire is detected, the better the chances are for survival. However, not only is early detection crucial, but it is also important to have a clear understanding of the fire development and the location. Where did the fire start? What is the size of the fire? What is the direction of smoke propagation? How is the fire growing? The answer to each of these questions plays an important part in safety analysis and firefighting/mitigation, and is essential in assessing the risk of escalation. Nevertheless, the majority of video fire detection (VFD) approaches just ring the bell and are not able to model fire evolution (ie, information about the fire circumstances is rarely available). The research in this chapter focuses on both problems and presents several multimodal/multisensor analysis techniques that have proven to be useful in fast and accurate analysis of valuable fire characteristics (eg, flame and smoke spreading) with video and other types of volume sensors. These characteristics, in turn, can be used for fire-spread forecasting.

Infrared Sensor-Based Flame Detection

In this chapter, a pyroelectric infrared (PIR) sensor-based flame detection system is described using a Markovian decision algorithm. The chapter is based on the paper in [ 1 ]. A differential PIR sensor is only sensitive to sudden temperature variations within its viewing range and it produces a time-varying signal. The wavelet transform of the PIR sensor signal is used for feature extraction from the sensor signal and wavelet parameters are fed to a set of Markov models corresponding to the flame flicker process of an uncontrolled fire, ordinary activity of human beings, and other objects. The final decision is reached based on the model yielding the highest probability among others. Comparative results show that the system can be used for fire detection in large rooms.