This review is focused on video flame and smoke based fire detection algorithms for both indoor and outdoor environments. It analyzes and discusses them in a taxonomical manner for the last two decades. These are mainly based on handcraft features with or without classifiers and deep learning approaches. The separate treatment is provided for detecting flames and smoke. Their static and dynamic characteristics are elaborated for the handcraft feature approach. The blending of the obtained features from these characteristics is the focus of most of the research and these concepts are analyzed critically. A fusion of both visible and thermal images leading to multi-fusion and multimodal approaches have conversed. It is a step towards obtaining accurate detection results and how the handcraft feature approach tackles the problems of flame and smoke detection, as well as their weaknesses are discussed which are still not solved. Some of these weaknesses can be tackled by developing a technology based on artificial intelligence named deep-learning. Its taxonomical literature study with a focus on the flame and smoke detection is presented. The strengths and weaknesses of this approach are discussed with possible solutions. The latest trend in literature which focuses on the hybrid approach utilizing both handcraft feature, and deep learning approaches is discussed. This approach aims to minimize the weaknesses still present in the current systems.

Video Flame and Smoke Based Fire Detection Algorithms: A Literature Review

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.

/pdf/entropy-functional-based-online-adaptive-decision-fusion-47cr8100to.pdf

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

A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [−1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower.

/pdf/wildfire-detection-using-lms-based-active-learning-4thwho5big.pdf

Wildfire detection using LMS based active learning

With the rapid development of information technology, natural disaster prevention is growing as a new research field dealing with surveil- lance systems. To forecast and prevent the damage caused by natural disasters, the development of systems to analyze natural disasters using remote sensing geographic information systems (GIS), and vision sensors has been receiving widespread interest over the last decade. This paper provides an up-to-date review of five different types of natural disasters and their corresponding warning systems using computer vision and pattern recognition techniques such as wildfire smoke and flame detection, water level detection for flood prevention, coastal zone monitor- ing, and landslide detection. Finally, we conclude with some thoughts about future research directions. © 2012 Society of Photo-Optical Instrumentation

https://www.spiedigitallibrary.org/journals/optical-engineering/volume-51/issue-7/070901/Survey-of-computer-vision-based-natural-disaster-warning-systems/10.1117/1.OE.51.7.070901.pdf

Survey of computer vision–based natural disaster warning systems

This paper presents the next step in the evolution of multi-sensor wireless network systems in the early automatic detection of forest fires. This network allows remote monitoring of each of the locations as well as communication between each of the sensors and with the control stations. The result is an increased coverage area, with quicker and safer responses. To determine the presence of a forest wildfire, the system employs decision fusion in thermal imaging, which can exploit various expected characteristics of a real fire, including short-term persistence and long-term increases over time. Results from testing in the laboratory and in a real environment are presented to authenticate and verify the accuracy of the operation of the proposed system. The system performance is gauged by the number of alarms and the time to the first alarm (corresponding to a real fire), for different probability of false alarm (PFA). The necessity of including decision fusion is thereby demonstrated.

/pdf/multisensor-network-system-for-wildfire-detection-using-3wri6i2jjx.pdf

Multisensor Network System for Wildfire Detection Using Infrared Image Processing

This paper describes an scheme for automatic forest surveillance. A complete system for forest fire detection is firstly presented although we focus on infrared image processing. The proposed scheme based on infrared image processing performs early detection of any fire threat. With the aim of determining the presence or absence of fire, the proposed algorithms performs the fusion of different detectors which exploit different expected characteristics of a real fire, like persistence and increase. Theoretical results and practical simulations are presented to corroborate the control of the system related with probability of false alarm (PFA). Probability of detection (PD) dependence on signal to noise ration (SNR) is also evaluated.

Infrared image processing and its application to forest fire surveillance

A microphone array can be employed to localize dominant acoustic sources in a given noisy environment. This capability is successfully used in good signal to noise ratio (SNR) conditions but its accuracy decreases considerably in the presence of other background noise sources. In order to counteract this effect, a novel approach that combines the information provided by a Gaussian energy detector (GED) with the approved localization method SRP-PHAT is presented in this paper. To evaluate the presented technique, several acoustic sources (speech and impulsive sounds) were considered in a variety of different scenarios to demonstrate the robustness and the accuracy of the system proposed.

J. Moragues

Papers

Infrared image processing and its application to forest fire surveillance

Background noise suppression for acoustic localization by means of an adaptive energy detection approach