Fire Detection Method Research Articles

A fire detection and localisation method based on keyframes and superpixels for large-space buildings

A fire detection and localisation method based on keyframes and superpixels for large-space buildings

Optimized Deep Learning Model for Fire Semantic Segmentation

Recent convolutional neural networks (CNNs) based deep learning has significantly promoted fire detection. Existing fire detection methods can efficiently recognize and locate the fire. However, the accurate flame boundary and shape information is hard to obtain by them, which makes it difficult to conduct automated fire region analysis, prediction, and early warning. To this end, we propose a fire semantic segmentation method based on Global Position Guidance (GPG) and Multi-path explicit Edge information Interaction (MEI). Specifically, to solve the problem of local segmentation errors in low-level feature space, a top-down global position guidance module is used to restrain the offset of low-level features. Besides, an MEI module is proposed to explicitly extract and utilize the edge information to refine the coarse fire segmentation results. We compare the proposed method with existing advanced semantic segmentation and salient object detection methods. Experimental results demonstrate that the proposed method achieves 94.1%, 93.6%, 94.6%, 95.3%, and 95.9% Intersection over Union (IoU) on five test sets respectively which outperforms the suboptimal method by a large margin. In addition, in terms of accuracy, our approach also achieves the best score.

Development and field deployment of a mid-infrared CO and CO2 dual-gas sensor system for early fire detection and location

In order to realize early fire detection and location, a mid-infrared carbon monoxide (CO) and carbon dioxide (CO2) dual-gas sensor system was developed, which mainly includes a gas pretreatment module, a CO2 sensor module, a CO sensor module, and a laptop monitoring platform. CO2 and CO absorption lines located at 4.26 μm and 4.66 μm, respectively, were selected to ensure good selectivity of the sensor system. A series of experiments were carried out to evaluate the sensor performance. The 10–90% response time of the CO and CO2 sensor modules was measured to be ∼ 30 s at a flow rate of 1 L/min, and the limits of detection (LoD) of CO2 and CO were assessed to be 5.66 parts per million by volume (ppmv) and 0.94 ppmv, respectively, when the averaging time was 0.25 s. According to the correlation between CO2 and CO concentration in the early fire stage, a method of early fire detection was studied and proposed using the normalized concentration ratio between CO and CO2 (C(CO)/C(CO2)) as the key alarm parameter. Based on gas turbulent diffusion (GTD) model combined with particle swarm optimization (PSO) algorithm, a mobile early fire location method was presented. Correlative experiment results verified that the reported sensor system has a good performance for early fire detection and location.

An adaptive Particle Swarm Optimization algorithm for fire source identification of the utility tunnel fire

In order to overcome serious utility tunnel fires and minimize economic loss, it is essential to establish an effective and practical method for finding the fire source. An adaptive Particle Swarm Optimization (PSO) algorithm was proposed for fire source identification of utility tunnel fires, whose inertia weight and learning factors were adjusted dynamically. In comparison with traditional fire detection methods, the proposed algorithm is immune to the specific environment and complicated fire propagation mechanisms, the fire source location can be identified only based on several temperature values. The proposed algorithm was applied in both numerical and experimental scenarios. The results showed that the adaptive algorithm showed greater global searchability in the early exploration, and stronger local searchability in the later exploration compared with the basic one, the improvement ratio of convergence performance could achieve 50%. Additionally, all of the cases demonstrated that the fire source location can be identified by the proposed algorithm with good accuracy. Critically, the spatial temperature distribution of the whole utility tunnel was obtained based on the fire source location and the attenuation coefficient. The reasonable results indicate that the proposed algorithm can provide a reference for fire protection and intervention in the utility tunnel.

Computer Vision Method for Forest Fires Detection Based on RGB Images Obtained by Unmanned Motor Glider

The article proposes a method (algorithm) of forest fire detection by means of RGB images obtained by using an unmanned aerial vehicle (motor glider). It includes several stages associated with background detection and subtraction and recognition of fire areas by means of RGB colour space. The proposed method was tested using images of forest fires. It is proposed to use unmanned aerial vehicles capable to monitor large areas continuously for several hours. The results of calculations are shown, which demonstrate that the proposed method allows us to detect areas of images occupied by forest fires and may be used in automatic forest fire monitoring systems.

An Improvement of the Fire Detection and Classification Method Using YOLOv3 for Surveillance Systems.

Currently, sensor-based systems for fire detection are widely used worldwide. Further research has shown that camera-based fire detection systems achieve much better results than sensor-based methods. In this study, we present a method for real-time high-speed fire detection using deep learning. A new special convolutional neural network was developed to detect fire regions using the existing YOLOv3 algorithm. Due to the fact that our real-time fire detector cameras were built on a Banana Pi M3 board, we adapted the YOLOv3 network to the board level. Firstly, we tested the latest versions of YOLO algorithms to select the appropriate algorithm and used it in our study for fire detection. The default versions of the YOLO approach have very low accuracy after training and testing in fire detection cases. We selected the YOLOv3 network to improve and use it for the successful detection and warning of fire disasters. By modifying the algorithm, we recorded the results of a rapid and high-precision detection of fire, during both day and night, irrespective of the shape and size. Another advantage is that the algorithm is capable of detecting fires that are 1 m long and 0.3 m wide at a distance of 50 m. Experimental results showed that the proposed method successfully detected fire candidate areas and achieved a seamless classification performance compared to other conventional fire detection frameworks.

Fire Detection Methods Based on Various Color Spaces and Gaussian Mixture Models

Fire Detection Methods Based on Various Color Spaces and Gaussian Mixture Models

The design of integrated fire spot monitoring system for industrial plantation forest using enterprise architecture approach

Fire control in industrial plantation areas is often delayed due to late information on the location of fire spots. A quick response is the best chance to contain and eliminate a fire spot. Several methods are used to explore existing problems. First, the interview method is used to obtain information from direct sources involved in the fire spot handling process. Then with the SWOT analysis method, the strengths, weaknesses, opportunities and threats of the current fire spot management system are obtained. Value Chain Analysis is used to see the main activities and supporting activities in designing the fire spots detection system. Finally, the application of the Zachman Framework method can demonstrate the system design from various points of view. From the analysis carried out, it can be seen that each of the fire spot detection methods has its advantages and disadvantages. This study aims to analyze the implementation of a fire spot monitoring and handling system and produces a new Integrated Fire Spot Monitoring System design using the Zachman Framework in industrial plantation companies. A new model is thus created that integrates all existing detection methods. The new model utilizes supporting technology such as messenger technology, satellite, drone, CCTV, and applications on servers that intelligently complement the required data, including spatial information for the closest path to the fire spot. Enterprise Architecture’s implementation uses the Zachman Framework, which supported by SWOT Analysis and Value Chain Analysis, ensuring that all needs can be explored and producing a system design that has comprehensively considered all needs.

Multi-Scale Coal Fire Detection Based on an Improved Active Contour Model from Landsat-8 Satellite and UAV Images

Underground coal fires can increase surface temperature, cause surface cracks and collapse, and release poisonous and harmful gases, which significantly harm the ecological environment and humans. Traditional methods of extracting coal fires, such as global threshold, K-mean and active contour model, usually produce many false alarms. Therefore, this paper proposes an improved active contour model by introducing the distinguishing energies of coal fires and others into the traditional active contour model. Taking Urumqi, Xinjiang, China as the research area, coal fires are detected from Landsat-8 satellite and unmanned aerial vehicle (UAV) data. The results show that the proposed method can eliminate many false alarms compared with some traditional methods, and achieve detection of small-area coal fires by referring field survey data. More importantly, the results obtained from UAV data can help identify not only burning coal fires but also potential underground coal fires. This paper provides an efficient method for high-precision coal fire detection and strong technical support for reducing environmental pollution and coal energy use.

When Convolutional Neural Networks Meet Remote Sensing Data for Fire Detection

In this paper, we present a novel end-to-end Dual Fire Detection Network (DFD-Net) for the remote sensing data fire detection task. The proposed network architecture consists of two streams in a parallel fashion, a fire estimate stream is used to detect fire pixels, and a cloud-water stream is built to exclude cloud and water regions. Moreover, the pixel and band attention modules adapted to characteristics of the remote sensing data are proposed. Experimental results on our prepared Himawari-8 data fire detection dataset with ground truth labels demonstrate that the proposed algorithm outperforms existed fire detection methods in various metrics.

Research on Mountain Fire Detection method of UAV based on Mathematical Modeling method

For the first question, we establish two main models for SSA drones and repeater drones respectively. For repeater drones, we establish a grid search model, aiming at terrain, repeater range limits and other restrictions, by gradually removing the grid points, work out the optimal position and quantity of the repeater drones. For SSA drones, we also use the grid search model, considering the flight parameters of SAA drones, to find the position of the charging station (EOC) and fully meet the charging needs of SSA drones. Considering the impact of the size of fire, we divide the size of the fire into three levels, which correspond to different SSA drones demand quantities, and referred to the VRPTW algorithm to solve the TSP problem with different node requirements. Finally, we use genetic algorithm to optimize.

METHODS FOR DETECTING FIRES IN ECOSYSTEMS USING LOW-RESOLUTION SPACE IMAGES

The paper presents the methods for fire identification using low-resolution space images obtained from Terra Modis and NOAA satellites. There are lots of algorithms to identify potentially "fire pixels" (PF). They are based on the assessment of temperature in spectral ranges from 3.5–4 to 10.5–11.5 microns. One of the problematic aspects in the Fire Detection Method using low-resolution space images is "Cloud and Water Masking". To identify "fire pixels", it is important to exclude from the analysis fragments of images that are covered with clouds and occupied by water objects. Identification of pixels in which one or more fires are actively burning at the time of passing over the Earth is the basis of the algorithm for detecting potentially "fire pixels". The algorithm requires a significant increase in radiation in the range of 4 micrometers, as well as on the observed radiation in the range of 11 micrometers. The algorithm investigates each pixel in a scene that is assigned one of the following classes as a result: lack of data, cloud, water, potentially fire or uncertain. The pixels that lack actual data are immediately classified as "missing data (NULL)" and excluded from further consideration. Cloud and water pixels, defined by the cloud masking technique and water objects, belong to cloud and water classes, respectively. The fire detection algorithm investigates only those pixels of the Earth's surface that are classified as potentially fire or uncertain. The method was implemented using the Visual Programming Tool PowerBuilder in the data processing system of Erdas Imaging. As a result of the use of the identification method, fires in the Chornobyl exclusion zone, steppe fires and fires at gas wells were detected. Using the method of satellite fire identification is essential for the prompt detection of fires for remote forests or steppes that are poorly controlled by ground monitoring methods.

Monitoring 2019 Forest Fires in Southeastern Australia with GNSS Technique

From late 2019 to early 2020, forest fires in southeastern Australia caused huge economic losses and huge environmental pollution. Monitoring forest fires has become increasingly important. A new method of fire detection using the difference between global navigation satellite system (GNSS)-derived precipitable water vapor and radiosonde-derived precipitable water vapor (ΔPWV) is proposed. To study the feasibility of the new method, the relationship is studied between particulate matter 10 (PM10) (2.5 to 10 microns particulate matter) and ΔPWV based on Global Positioning System (GPS) data, radiosonde data, and PM10 data from 1 June 2019 to 1 June 2020 in southeastern Australia. The results show that before the forest fire, ΔPWV and PM10 were smaller and less fluctuating. When the forest fire happened, ΔPWV and PM10 were increasing. Then after the forest fire, PM10 became small with relatively smooth fluctuations, but ΔPWV was larger and more fluctuating. Correlation between the 15-day moving standard deviation (STD) time series of ΔPWV and PM10 after the fire was significantly higher than that before the fire. This study shows that ΔPWV is effective in monitoring forest fires based on GNSS technique before and during forest fires in climates with more uniform precipitation, and using ΔPWV to detect forest fires based on GNSS needs to be further investigated in climates with more precipitation and severe climate change.

Advances Toward the Next Generation Fire Detection: Deep LSTM Variational Autoencoder for Improved Sensitivity and Reliability

Fire detection is a critical component of a building safety monitoring system and remains an important research area with weighty practical relevance. Significant advances have occurred in recent years in building automation, and the operation of buildings has become more complex and requires ever more effective monitoring systems. In this work, we develop a novel fire detection method using deep Long-Short Term Memory (LSTM) neural networks and variational autoencoder (VAE) to meet these increasingly stringent requirements and outperform existing fire detection methods. To evaluate the effectiveness of our method, we develop high-fidelity simulations, and we use datasets from real-world fire and non-fire experiments provided by NIST. We compare and discuss the performance of our proposed fire detection with alternative methods, including the standard LSTM, cumulative sum control chart (CUSUM), exponentially weighted moving average (EWMA), and two currently used fixed-temperature heat detectors. The results using the simulation-based and the real-world experiments are complementary, and they indicate that the LSTM-VAE robustly outperforms the other detection methods with, for example, statistically significant shorter alarm time lags, no missed detection, and no false alarms. The results also identify shortcomings of other detection methods and indicate a clear ranking among them (LSTM-VAE $\mathrm {\succ }EWMA\succ LSTM\mathrm {\succ }CUSUM$ ).

Temporal sequence method for fire spot detection using Himawari-8 geostationary meteorological satellite

Temporal sequence method for fire spot detection using Himawari-8 geostationary meteorological satellite

An improved YOLOv3-tiny method for fire detection in the construction industry

To prevent fire accidents on construction site and improve the accuracy of fire detection, an improved YOLOv3-tiny method (I-YOLOv3-tiny) is proposed in this paper. Although the YOLOv3-tiny has a fast detection speed and low equipment requirement, the accuracy is relatively low on fire detection. The improvement of the I-YOLOv3-tiny method is followed by three steps. Firstly, the feature extraction of fire images is enhanced by optimizing the network structure. Secondly, a multi-scale fusion is used to improve the detection effect of fire targets. Finally, the anchor boxes that are suitable for fire data sets are selected by k-means clustering. The results show that I-YOLOv3-tiny has an increased percentage of 4 on the mAP, the Recall rate has an increased percentage of 4, and AVG IOU has an increased percentage of 6. The proposed model meets the real-time performance of fire detection. This study is of theoretical and practical significance on fire safety management and accident prevention in the construction industry.

Применение средств видеонаблюдения для обнаружения пожара

Introduction. The fire safety of the protected object is determined by the possibility of reliable fire detection. Insufficiently effective operation of the fire alarm system can lead to the death of people, unacceptable material and other damage. The video surveillance system, being one of the main links of the engineering security system, monitors emergency situations in real time and, in particular, a breakout of fire at the protected object. Goals and objectives. The purpose of the article is to analyze the state and trends in the development of video surveillance equipment aimed at improving the fire safety of protected objects. Tasks include regulatory justification of the use of video surveillance in fire alarm systems, review of methods of fire detection by video surveillance and improving their effectiveness under the influence of interfering factors, as well as evaluation of the effectiveness of video surveillance in fire protection systems. Methods. The methods of the system analysis and probability theory are used. Results and discussion. The requirements of regulatory documents for detectors with a video detection channel for their effective operation in fire alarm systems are considered. The main directions of development of means and methods of application of video surveillance in fire protection systems are defined. It is shown that reducing the risk of non-detection of fire to an acceptable level can be achieved by increasing the probability of effective operation of the fire alarm system, as well as by increasing the positive impact of the video surveillance system, which is a part of the complex security system of the object. Conclusions. Video surveillance significantly increases the efficiency of fire detection. It allows you to get a visual picture of the state of the protected object, which has such a high information content that no other security means can provide. The use of video surveillance equipment in fire alarm systems, as well as their integration with industrial and fire automation systems is one of the main reserves for increasing the fire safety of facilities. Keywords: video surveillance, fire detector with video detection channel, fire alarm, video analytics, fire protection

Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks

Fire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In the first stage, fire candidates are detected by using their salient features, such as their color, flickering frequency, and brightness. In the second stage, a pretrained CNN model is used to extract the 2D features of flames that are the input for the LSTM network. In the last stage, a softmax classifier is utilized to determine whether the flames represent a true fire or a nonfire moving object. The experimental results show that our proposed method can achieve competitive performance compared with other state-of-the-art methods and is suitable for real-world applications.

Research on Improved YOLOv3 Fire Detection Based on Enlarged Feature Map Resolution and Cluster Analysis

Fire detection can effectively prevent the occurrence of fire. For the current fire detection methods, traditional image processing techniques such as grayscale image processing and feature extraction processing have poor anti-interference ability, weak generalization ability, and the detection results are more sensitive to data fluctuations. At present, based on the concept of deep learning, the proposed convolutional neural network processing of extracted image features has been widely used. On this basis, an improved YOLOv3 fire detection algorithm is proposed in this paper: The K-Means++ algorithm is used for clustering analysis to obtain the corresponding anchor boxes dimension, which reduces the error detection rate caused by the bounding boxes not matching the label; secondly, the resolution of the feature image is improved and the receptive field is enlarged; the image data are sharpened and the contrast is enhanced to make the data features more prominent. The experimental results show that the detection precision of the method is 97.7%, the recall rate is 98.5%, and the fps is 19, effectively solving the problem of high error detection rate and high missing rate of traditional image processing and general CNN networks for suspected flame objects.

A Novel Fire Identification Algorithm Based on Improved Color Segmentation and Enhanced Feature Data

In order to improve the accuracy of fire identification based on video in the Internet-of-Things environment, this article proposes a new fire identification algorithm by merging fire segmentation and multifeature fusion of fire. First, according to the relationship between R and Y channels, the improved YCbCr models are established for initial fire segmentation under reflection and nonreflection conditions, respectively. Simultaneously, the reflection and nonreflection conditions are judged by comparing the areas obtained by the two improved YCbCr models. Second, an improved region growing algorithm is proposed for fine fire segmentation by making use of the relationship between the seed point and its adjacent points. The seed points are determined using the weighted average of centroid coordinates of each segmented image. Finally, the quantitative indicators of fire identification are given according to the variation coefficient of fire area, the dispersion of centroid, and the circularity. Extensive experiments were conducted, and the experimental results demonstrate that the proposed fire detection method considerably outperforms the traditional methods on average in terms of three performance indexes: precision, recall, and $F1$ -score. Specifically, compared with the deep learning method, the precision of the proposed method is slightly higher. Although the recall of the proposed method is slightly lower than the deep learning method, its computation complexity is low.