Conventional Fire Detection Research Articles

Fabric-based intelligent fire-warning and flame-retardant coating: A review of advances, challenges and prospects

Fabric-based fire-warning and flame-retardant coatings could achieve dual functions of active warning response and passive fire retardancy. In contrast to conventional fire detection systems that necessitate installation at designated locations, the contact surface between the coating sensing material and the flame is substantially augmented. Therefore, it possesses crucial application value in enhancing the warning efficiency and fire safety performance of flammable substrates. This review primarily delved into the flame retardancy and fire warning of fabric coating materials. It thoroughly examined the current research status of fabric-based flame-retardant coatings and analyzed the fire-warning mechanisms of voltage-based and resistance-based coatings. Furthermore, this comprehensive review elucidated the research and current applications of various coatings based on sensing materials such as graphene oxide, carbon nanotubes, and MXene in the fire warning and flame resistance. Additionally, it is worth noting that the current functionality of fabric-based coatings is relatively limited, necessitating the incorporation of multi-functionality to adapt to various usage scenarios. In addition, it is necessary to develop large-scale coating preparation technique to achieve commercial production and combine artificial intelligence technology to achieve higher-level fire warning and flame-resistant application. Finally, the future development trend of the fabric-based coating was prospected.

Enhancing fire safety through IoT-enabled flame detection systems: A cost-effective and scalable approach

The Internet of Things (IoT), which connects and automates numerous systems and gadgets, has completely changed how we live and work. One such application of IoT technology is in fire detection systems, which can help prevent and mitigate the devastating effects of fires on different types of facilities. The research presents a n IoT architecture for a fire detection system using small, low-cost cameras to collect surveillance feeds from large buildings. The data is uploaded to the cloud, where a Machine Learning algorithm detects fires in digital images. The proposed architecture consists of cameras, cloud, and clients, using an inexpensive camera for surveillance feeds and a convolutional neural network for image classification based on large datasets. However, the architecture's cloud component processes surveillance feeds and runs a Machine Learning (ML) model, utilizing computing resources for real-time data processing and continuous training for improved accuracy. Clients can subscribe to the data from the cloud and receive alerts in real-time when the ML model detects a fire in the surveillance feeds. There are significant benefits in comparing the proposed design to conventional fire detection systems. First and foremost, it is economical since the cameras used are compact, affordable, and simple to install around the building without the need for elaborate wiring or infrastructure. Secondly, it is scalable, as the cloud provides the necessary computing resources and storage capacity to handle large amounts of data, making it possible to monitor large structures with many cameras.

Acoustic Wave Based Forest Fire Extinguisher and Detection Using Machine Learning

Worldwide, forest fires are a serious hazard to people, property, and the environment, needing creative approaches to early detection and prompt control. In order to establish an intelligent forest fire control system, this research introduces a cutting-edge methodology that blends conventional fire detection techniques with machine learning and cutting-edge technology. To find fires in a forest, we use flame sensors. The flame sensor informs a microcontroller when a fire is found. We offer a revolutionary form of fire suppression using Sonic Fire Extinguisher technology, which puts out flames by emitting high-frequency sound waves, as opposed to traditional fire suppression methods that use water or carbon dioxide. This strategy offers a safer and more environmentally friendly fire suppression technique. The technology incorporates machine learning to improve the speed and accuracy of fire detection. A SD card for sound file storage is included with the ARDUINO UNO microcontroller. In addition, the microcontroller is wired up with an amplifier and speaker. The microcontroller uses machine learning techniques to analyses the characteristics of the fire, such as size and intensity, and chooses the best sound wave frequency for suppression when the flame sensor detects a fire. This device can put out fires more effectively than conventional techniques and can adjust to various fire circumstances. The device can tailor the produced sound waves for effective fire suppression by fusing real-time data from the flame sensor with machine learning insights. This novel strategy improves the safety from forest fires while simultaneously minimizing the negative ecological effects of fire management activities. A promising approach to protecting priceless natural resources, people's lives, and property from the destructive impacts of forest fires is the combination of machine learning and Sonic Fire Extinguisher technology. This research Endeavour marks a significant advancement in the practice of finding fires and extinguishment, allowing a more environmentally responsible and sustainable method of managing forest fires.

A wavelet-based real-time fire detection algorithm with multi-modeling framework

This paper presents a wavelet-based real-time automated fire detection algorithm that takes into consideration the multi-resolution property of the wavelet transforms. Unlike conventional fire detection algorithms, which fail to capture temporal dependency within the fire sensor signals, the proposed wavelet-based features characterize temporal dynamics of chemical sensor signals generated from various types of fire, such as flaming, heating and smoldering fires. We propose a new feature selection technique based on types of fire to select the best features that can effectively discriminate between normal and various fire conditions. Then, a real-time fire detection algorithm with a multi-modeling framework is developed to effectively utilize the selected features and construct multiple fire detectors that are sensitive in monitoring various kinds of fires without prior knowledge. In addition, we develop a novel multi-sensor fusion system that incorporates various chemical sensors and collects an accurate and reliable fire dataset from different real-life fire scenarios in order to validate the performance of the proposed and existing fire detection algorithms. The experimental results with real-life and public fire data show that the proposed algorithm outperforms others with early detection time with a reasonable false alarm rate regardless of the type of fire.

Industrial Fire Detector Using Colour Detection and Tracking

Conventional fire detection systems use physical sensors to detect fire. Chemical properties of particles in the air are acquired by sensors and are used by conventional fire detection systems to raise an alarm. However, this can also cause false alarms; for example, a person smoking in a room may trigger a typical fire alarm system. In order to manage false alarms of conventional fire detection systems, a computer vision-based fire detection algorithm is proposed in this paper. The proposed fire detection algorithm consists of two main parts: fire color modeling and motion detection. The algorithm can be used in parallel with conventional fire detection systems to reduce false alarms. It can also be deployed as a stand-alone system to detect fire by using video frames acquired through a video acquisition system.

A Prefatory Approach Towards Monitoring and Detection of Fire Outbreak Using Artificial Neural Network

Fire incidents had always been a primary concern in domestic and industrial properties, buildings, sites and offices. The end results of fire outbreaks can be exceedingly devastating and usually amount to serious losses of lives and properties. They also consist of alarm circuits and some manual call points often referred to as detection zones. Recent researches on fire related systems which are adaptations of the conventional fire systems, have dwelt comprehensively on technologies that can provide possible fire detection services by the integration of sensors that are capable of reacting to certain fire based parameters such as rise in temperature/heat, accumulation of pressure, smoke and other combustible elements etc.. The perceived setback of these sensors is that they need considerable time for responding as they require product of fire (e.g., smoke, temperature etc.) to reach the sensors. However, as computing power increases, and its effect is felt across most spheres of human existence, artificial intelligence based systems have been in the fore front of the discourse due to its ability to adequately minimize or exclude human involvement in most emergency or delicate activities. Therefore, implementing a computer vision-based fire monitoring and detection system using low cost surveillance cameras and artificial neural network is proposed and will sufficiently enhance the ability to monitor, detect and generally manage fire outbreaks in deployed buildings. The proposed system seek to significantly provide a more precise and accurate tool for the detection of fire situations and sufficiently eliminate the tendency for false fire alarms since it will be dependent on convolutional neural network trained with captured frames of video images of fire in order to accurately tell a fire situation. The primary purpose of this study is to develop an intelligent system for monitoring and detection of fire outbreak using computer vision and artificial neural network. Other objectives include: to develop a suitable neural network upon which the model will be trained and to implement the model using python programming language..The technology adopted in this study is expected to perform better unlike the conventional fire detection and alarm systems which are heavily reliant on sensors that are only effective with proximity and location of use.

Improved Real-Time Fire Warning System Based on Advanced Technologies for Visually Impaired People.

Early fire detection and notification techniques provide fire prevention and safety information to blind and visually impaired (BVI) people within a short period of time in emergency situations when fires occur in indoor environments. Given its direct impact on human safety and the environment, fire detection is a difficult but crucial problem. To prevent injuries and property damage, advanced technology requires appropriate methods for detecting fires as quickly as possible. In this study, to reduce the loss of human lives and property damage, we introduce the development of the vision-based early flame recognition and notification approach using artificial intelligence for assisting BVI people. The proposed fire alarm control system for indoor buildings can provide accurate information on fire scenes. In our proposed method, all the processes performed manually were automated, and the performance efficiency and quality of fire classification were improved. To perform real-time monitoring and enhance the detection accuracy of indoor fire disasters, the proposed system uses the YOLOv5m model, which is an updated version of the traditional YOLOv5. The experimental results show that the proposed system successfully detected and notified the occurrence of catastrophic fires with high speed and accuracy at any time of day or night, regardless of the shape or size of the fire. Finally, we compared the competitiveness level of our method with that of other conventional fire-detection methods to confirm the seamless classification results achieved using performance evaluation matrices.

Computer Vision Based Fire Detection System Using OpenCV - A Case Study

Conventional fire detection system was based mechanical sensor for fire detection. The smoke particles in the surrounding detected by sensors in the traditional fire detection system. However, this can also lead to false alarms. For example, a person smoking in a room of can activate a general fire alarm system. In addition, these systems are expensive and ineffective if the fire is far away from the detector. An alternatives fire detection system such as system based on computer vision and Image/video Processing technology to manage false alarms from conventional fire detection. One of the most cost-effective ways is to use surveillance cameras to detect fires and alert affected parties. In the following proposed system proposes a technique which will be monitor the outburst of a fire anywhere within the camera range using a surveillance camera. In this Paper, fire alarm system will be developed to efficiently detect fires and protect lives and property from fire hazards. This research describes a fire detection system that uses color and motion models derived from video sequences. The proposed approach identifies color changes and mobility in common areas to identify fires and can therefore be used both in real time and in datasets.

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.

Industry safety measurement using multi-sensing robot with IIoT

The conventional fire detection systems are predisposed to generate false alarms. In this paper, we discuss the design and implementation of an effective and cost-effective fire detection system using Wireless Sensor Network (WSN) and Global System for Mobile (GSM) communication to detect fires effectively and eliminate false alarms. The system uses smoke and temperature sensors to activate or cease operation. A Smart Message Service (SMS) capability was introduced in fire alarms system to alert inhabitants on fire conditions. The main purpose of this paper was to design and implement a fire detection system that works effectively. The results reveal that the system fulfills the specifications.

IoT-Based Fire Safety System Using MQTT Communication Protocol

Fire can be made useful for various purposes. However, uncontrollable fire may result in property damage and human death. The major factor of fire deaths is due to excessive smoke inhalation. Therefore, early detection of fire is crucial in fire detection systems. The conventional fire detection system does not come with a false alarm prevention system. Besides, the system is unable to tell the exact location of the fire. In this project, an Internet of Things (IoT) based fire safety system is developed to overcome these problems. The proposed system consists of three major parts which are the detector, processing unit and surveillance. The detector unit is an integration of ESP32, carbon monoxide sensor, ionization smoke detector, buzzer, temperature and humidity sensor. As the processing unit, Raspberry Pi is used to run the Node-RED application, which processes the data and performs monitoring. The communication between the detector and processing unit is based on the Message Queuing Telemetry Transport (MQTT) protocol. A surveillance unit is where a camera is installed to monitor the condition of the surrounding. The response of the system is based upon the sensor’s values or the user’s response. Once the fire breakout is confirmed, the system will immediately sound the alarm, and Global Positioning System (GPS) coordinates and floor plan of the accommodation will send to the nearby fire station. The floor plan is developed to track the exact location of the fire. Experiments are carried out on the proposed fire safety system, and encouraging results are produced.

Continuous Wavelet Transform Based Gene Optimized Fuzzy C-Means Clustering For Forest Fire Detection

Fire detection is an important aspect of disaster preparedness, to reduce loss of lives and property damage. Conventionally, many techniques have been designed so far, to discover the forest fires through input videos. But, clustering performance of conventional fire detection techniques was not sufficient. To overcome the above limitations, Continuous Wavelet Transform Based Gene Optimized Fuzzy C-Means Clustering (CWT-GOFCC) technique is proposed. The proposed CWT-GOFCC technique takes number of video files from FIRESENSE database as input and converts those input videos into a number of frames. Next, it defines the number of clusters and centroids and consequently initializes the gene populations with number of video frames. After that, CWT-GOFCC technique evaluates fuzzy membership with the assistance of fitness function for all input video frames based on spatial correlation between the fire flame colors. By using this fitness function, the technique groups the video frames into pre-fire stage or fire stage or critical fire stage with enhanced accuracy. From that, this technique accurately clusters all the video frames into related clusters with lower time consumption. The simulation of the technique is conducted using metrics such as fire detection accuracy, fire detection time and false positive rate with respect to different numbers of video frames. The simulation result depicts that the technique is able to improve the accuracy and also reduce the time of forest fire detection in video file when compared to state-of-the-art works

Fire Detection in Video Stream by Using Simple Artificial Neural Network

This paper deals with the preliminary research of the fire detection in a video stream. Early fire detection can save lives and properties from huge losses and damages. Therefore the surveillance of the areas is necessary. Early fire discovery with high accuracy, i.e. a low number of false positive or false negative cases, is essential in any environment, especially in places with the high motion of people. The traditional fire detection sensors have some drawbacks: they need separate systems and infrastructure to be implemented, to use sensors in the case of the industrial environment with open fire technologies is often impossible, and others. The fire detection in a video stream is one of the possible and feasible solutions suitable for replacement or supplement of conventional fire detection sensors without a need for installation a huge infrastructure. The paper provides the state of the art in the fire detection. The following part of the paper proposes the new system of feature extraction and describes the feedforward neural network which was used for the training and testing of the proposed idea. The promising results are presented with over 93% accuracy on a selected dataset of movies which consist of more and highly varied instances than published by other researchers involved in the fire detection field. The structure of the neural networks promises higher computational speed than currently implemented deep learning systems.

Development of Fire Detection Algorithm at Its Early Stage Using Fire Colour and Shape Information

Fire can be defined as a state in which substances combined chemically with oxygen from the air and give out heat, smoke and flame. Most of the conventional fire detection techniques such as smoke, fire and heat detectors respectively have a problem of travelling delay and also give a high false alarm. The algorithm begins by loading the selected video clip from the database developed to identify the present or absence of fire in a frame. In this approach, background subtraction was employed. If the result of subtraction is less than the set threshold, the difference is ignored and the next frame is taken. However, if the difference is equal to or greater than the set threshold then it subjected to colour and shape test. This is done by using combined RGB colour model and shape signature. The proposed technique was very effective in detecting fire compared to those technique using only motion or colour clues.

Development of gas fire detection system using tunable diode laser absorption spectroscopy

The conventional fire detection methods mainly produce an alarm through detecting the changes in smoke concentration, flame radiation, heat and other physical parameters in the environment, but are unable to provide an early warning of a fire emergency. We have designed a gas fire detection system with a high detection sensitivity and high selectivity using the tunable semiconductor diode laser as a light source and combining wavelength modulation and harmonic detection technology. This system can invert the second harmonic signal obtained to obtain the concentration of carbon monoxide gas (a fire characteristic gas) so as to provide an early warning of fire. We reduce the system offset noise and the background noise generated due to the laser interference by deducting the system background spectrum lines from the second harmonic signal. This can also eliminate the interference of other gas spectral lines to a large extent. We detected the concentration of the carbon monoxide gas generated in smoldering sandalwood fire and open beech wood fire with the homemade fire simulator, and tested the lowest detectable limit of system. The test results show that the lowest detectable limit can reach 5×10-6; the system can maintain stable operation for a long period of time and can automatically trigger a water mist fire extinguishing system, which can fully meet the needs of early fire warning.

Noise Elimination Method in Automatic Fire Detection Equipment in Accordance with the Communication Distance

This research focused on the communication noise level depending on the distance for conventional fire detection systems (RS-485 codetransmitter) in comparison to the newly developed optical cable automatic fire detection system (optical communication code-transmitter. The noise levels of the RS-485 code-transmitter were respectively 10, 200, 1200, and 2400 mV for the communication distances of 0, 1, 40, and 80 m and showed a correlation between the increase of the communication noise with the increase of the communication distance. However, the optical communication code-transmitter did not show any sign of communication noise at these four different distances. Therefore, the newly developed optical communication system is an ideal system to avoid false alarms in automatic fire detection system.

움직임 정보와 칼라정보 분석을 통한 화재검출 알고리즘

In this paper, we propose a fire detection algorithm based on motion information and color information analysis. Conventional fire detection algorithms have as main problem the difficulty to detect fire due to external light, intensity, background image complexity, and little fire diffusion. So we propose a fire detection algorithm that accurate and fast. First, it analyzes the motion information in video data and then set the first candidate. Second, it determines this domain after analyzing the color and the domain. This algorithm assures a fast fire detection and a high accuracy compared with conventional fire detection algorithms. Our algorithm will be useful to real-time fire detection in real world.

Benchmarking of wildland fire colour segmentation algorithms

Recently, computer vision-based methods have started to replace conventional sensor-based fire detection technologies. In general, visible band image sequences are used to automatically detect suspicious fire events in indoor or outdoor environments. There are several methods which aim to achieve automatic fire detection on visible band images, however, it is difficult to identify which method is the best performing as there is no fire image dataset which can be used to test the different methods. This study presents a benchmarking of state of the art wildland fire colour segmentation algorithms using a new fire dataset introduced for the first time. The dataset contains images of wildland fire in different contexts (fuel, background, luminosity, smoke etc.). All images of the dataset are characterised according to the principal colour of the fire, the luminosity, and the presence of smoke in the fire area. With this characterisation, it has been possible to determine on which kind of images each algorithm is efficient. Also a new probabilistic fire segmentation algorithm is introduced and compared to the other techniques. Benchmarking is performed in order to assess performances of 12 algorithms that can be used for the segmentation of wildland fire images.

Ego-Motion 보정기법을 적용한 쿼드로터의 화재 감지 알고리즘

A conventional fire detection has been developed based on images captured from a fixed camera. However, It is difficult to apply current algorithms to a flying Quad-rotor to detect fire. To solve this problem, we propose that the fire detection algorithm can be modified for Quad-rotor using Ego-motion compensation. The proposed fire detection algorithm consists of color detection, motion detection, and fire determination using a randomness test. Color detection and randomness test are adapted similarly from an existing algorithm. However, Ego-motion compensation is adapted on motion detection for compensating the degree of Quad-rotor's motion using Planar Projective Transformation based on Optical Flow, RANSAC Algorithm, and Homography. By adapting Ego-motion compensation on the motion detection step, it has been proven that the proposed algorithm has been able to detect fires 83% of the time in hovering mode.

화염의 칼라와 움직임을 이용한 화재감지

본 논문에서는 비디오 영상에서 화염의 칼라와 움직임 특징을 이용한 새로운 화재 감지 방법을 제안한다. 색차로부터 휘도를 효율적으로 분리하기 위하여 RGB 칼라를 YCbCr 성분으로 변환한다. 제안한 방법은 인접 영상들 간의 휘도의 차를 누적하여 화염의 움직임 영역을 검출하고, 화염의 색을 이용하여 화염 후보 영역을 생성한다. 최종적으로, 화염 후보 영역의 면적에 대한 시간적 변화를 이용하여 화염 영역을 결정한다. 실험 결과를 통하여 제안한 방법이 기존의 비디오 영상에서의 화재 감지 방법보다 화재 영역의 분류에 우수한 성능을 나타내는 것을 확인하였다. In this paper, we propose a new fire detection method using moving features and colors of flames in video sequences. It uses YCbCr color space to separate the luminance from the chrominance components more effectively than RGB color space. In the proposed method, moving regions of flames are detected by cumulating the difference of luminance between two consecutive images and generate candidate flame regions by using the color of flames. Finally, it decides whether the candidate flame regions are flames or not by using their temporal changes of the areas. Experimental results show that the proposed method performs better in segmenting fire regions compared with the conventional fire detection method in video sequences.