Smoke Detection Research Articles

Fire and Smoke Detection Using Fine-Tuned YOLOv8 and YOLOv7 Deep Models

Viewed as a significant natural disaster, wildfires present a serious threat to human communities, wildlife, and forest ecosystems. The frequency of wildfire occurrences has increased recently, with the impacts of global warming and human interaction with the environment playing pivotal roles. Addressing this challenge necessitates the ability of firefighters to promptly identify fires based on early signs of smoke, allowing them to intervene and prevent further spread. In this work, we adapted and optimized recent deep learning object detection, namely YOLOv8 and YOLOv7 models, for the detection of smoke and fire. Our approach involved utilizing a dataset comprising over 11,000 images for smoke and fires. The YOLOv8 models successfully identified fire and smoke, achieving a mAP:50 of 92.6%, a precision score of 83.7%, and a recall of 95.2%. The results were compared with a YOLOv6 with large model, Faster-RCNN, and DEtection TRansformer. The obtained scores confirm the potential of the proposed models for wide application and promotion in the fire safety industry.

Forest Fire Smoke Detection Based on Multiple Color Spaces Deep Feature Fusion

The drastic increase of forest fire occurrence, which in recent years has posed severe threat and damage worldwide to the natural environment and human society, necessitates smoke detection of the early forest fire. First, a semantic segmentation method based on multiple color spaces feature fusion is put forward for forest fire smoke detection. Considering that smoke images in different color spaces may contain varied and distinctive smoke features which are beneficial for improving the detection ability of a model, the proposed model integrates the function of multi-scale and multi-type self-adaptive weighted feature fusion with attention augmentation to extract the enriched and complementary fused features of smoke, utilizing smoke images from multi-color spaces as inputs. Second, the model is trained and evaluated on part of the FIgLib dataset containing high-quality smoke images from watchtowers in the forests, incorporating various smoke types and complex background conditions, with a satisfactory smoke segmentation result for forest fire detection. Finally, the optimal color space combination and the fusion strategy for the model is determined through elaborate and extensive experiments with a superior segmentation result of 86.14 IoU of smoke obtained.

Improving Computer Vision-Based Wildfire Smoke Detection by Combining SE-ResNet with SVM

Wildfire is one of the most critical natural disasters that poses a serious threat to human lives as well as ecosystems. One issue hindering a high accuracy of computer vision-based wildfire detection is the potential for water mists and clouds to be marked as wildfire smoke due to the similar appearance in images, leading to an unacceptable high false alarm rate in real-world wildfire early warning cases. This paper proposes a novel hybrid wildfire smoke detection approach by combining the multi-layer ResNet architecture with SVM to extract the smoke image dynamic and static characteristics, respectively. The ResNet model is improved via the SE attention mechanism and fully convolutional network as SE-ResNet. A fusion decision procedure is proposed for wildfire early warning. The proposed detection method was tested on open datasets and achieved an accuracy of 98.99%. The comparisons with AlexNet, VGG-16, GoogleNet, SE-ResNet-50 and SVM further illustrate the improvements.

Video smoke detection method based on cell root–branch structure

Video smoke detection method based on cell root–branch structure

YOLO-EPF: Multi-scale smoke detection with enhanced pool former and multiple receptive fields

Smoke identification in photos has long been difficult because of the intricate variations in smoke's texture, color, and shape. This article suggests a Transformer network and YOLOv5-based smoke detector to solve this problem. In particular, we suggest using the Enhanced Pool Former (EPF) structure to improve the expression ability of smoke features by obtaining greater global information. Additionally, to improve the recognition capacity of slight smoke, we strive to prevent the loss of information by increasing the number of detecting heads and introducing more feature fusion. We do this by using the NWDLoss to compensate for the sensitivity of IoU to the position difference of small objects. In addition, we develop the Multiple Receptive Fields (MRF) module to improve the ability to extract features from smoke at different scales. Our solution outperforms current methods on our custom dataset for AP and AP50, making it well-suited for smoke detection.

Am-241 in the urban air – Monitoring and simulation results

Concentration of 241Am was identified and analyzed during seven weeks between April and June 2021 in central Poland, using ASS500 monitoring station. The results changed from 0.305 to 4.241 µBq/m3. The lack of other, associate artificial isotopes on filters and no presence of isotope on other stations in Poland indicate on local emission. Processing of electrical waste, especially isotopic smoke detectors, has been investigated as a possible reason of the 241Am release into the atmosphere, probably in high temperature phase of metal separation. The possible circumstances of distribution of the radioactive 241Am isotope in the urban air in central Poland have been investigated and described.

Early fire detection technology based on improved transformers in aircraft cargo compartments

The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety. The current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared light. This often results in a high false alarm rate in complex air transportation environments. The traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire information. This paper proposes a multi-technology collaborative fire detection method based on an improved transformers model. Dual-wavelength optical sensors, flue gas analyzers, and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection accuracy. The improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective, which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN (recurrent neural network) and CNN (convolutional neural network). Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information, respectively, which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention mechanism. Finally, the output results of the two models are fused through the gate mechanism. The research results show that, compared with the traditional single-feature detection technology, the multi-technology collaborative fire detection method can better capture fire information. Compared with the traditional deep learning model, the multivariate fire prediction model constructed by the improved Transformer can better detect fires, and the accuracy rate is 0.995.

THE DEVELOPMENT OF AUTOMATIC CIGARETTE SMOKE DETECTION SYSTEM USING TA12-100 AND MQ-135 SENSORS

Indonesia is ranked 3rd with the highest number of active smokers in the world after India and China. Cigarettes contain more than 4000 chemical compounds that are harmful to active smokers and passive smokers. The large number of active smokers in Indonesia also has an impact on passive smokers where passive smokers also inhale cigarette smoke. The purpose of this research is to build an automatic cigarette smoke detector to support air hygiene control, protect passive smokers, and save electricity used. The stages in designing this research include analysis of product specifications, assembly, programming, and trials. This study was designed using Arduino UNO as the microcontroller, the MQ-135 sensor as a tool to detect cigarette smoke, the TA12-100 sensor to calculate electrical power consumption, the relay as an automatic switch, and the exhaust fan as a smoke neutralizer. The results of this study are that the MQ-135 sensor can detect cigarette smoke properly with the Relay as an automatic switch that functions to turn on the exhaust fan automatically. Based on the test results on the TA12-100 sensor, the consumption of electrical energy with an automatic mechanism is more efficient than the consumption of electrical energy in a manual way, with a difference of 0.0000385 kWH and Rp. 0.05205. Future research could focus on developing a more complex system for overall air cleanliness control, rather than just focusing on cigarette smoke detection.

Incendiary: Fire setting behaviors in youth

A 12‐year‐old boy presented for psychiatric assessment with a chief complaint of “fire setting.” The patient was reluctant to speak, however, his caregiver stated that he had set a fire in the basement of his home while the rest of the family were asleep. They were alerted due to the smoke alarm going off and were able to hurriedly contain the situation. The patient had a history of physical and emotional abuse from parents and was residing with his legal guardian, his maternal aunt.

Evaluation of Available Safety Egress Time (ASET) in Performance-Based Design (PBD) Using CFAST

In South Korea, the need to link fire and evacuation simulations to compare the available safety egress time (ASET) and required safety egress time (RSET) in real time when implementing performance-based design in buildings is increasing. Accordingly, the Consolidated Model of Fire Growth and Smoke Transport (CFAST) has been discussed as an alternative to the fire dynamics simulator, which requires high computational costs, sufficient experience in fire dynamics numerical calculations, and various input parameters and faces limitations in integration with evacuation simulations. A method for establishing a reasonable computational domain to predict the activation times of smoke and heat detectors has been proposed. This study examined the validity of using CFAST to predict factors relevant to the ASET evaluation. The results showed that CFAST, which solved empirical correlations based on heat release rates, predicted high gas temperatures similarly. Moreover, the applicability of the visibility distance calculation method using smoke concentration outputs from CFAST was examined. The results suggest that despite the limitations of the zone model, CFAST can produce reasonable ASET results. These results are expected to enhance the usability of CFAST in terms of understanding general fire engineering technology and simple fire dynamics trends.

Application of additive manufacturing in developing smoke and flame detectors for a habitable microgravity environment

Application of additive manufacturing in developing smoke and flame detectors for a habitable microgravity environment

FFYOLO: A Lightweight Forest Fire Detection Model Based on YOLOv8

Forest is an important resource for human survival, and forest fires are a serious threat to forest protection. Therefore, the early detection of fire and smoke is particularly important. Based on the manually set feature extraction method, the detection accuracy of the machine learning forest fire detection method is limited, and it is unable to deal with complex scenes. Meanwhile, most deep learning methods are difficult to deploy due to high computational costs. To address these issues, this paper proposes a lightweight forest fire detection model based on YOLOv8 (FFYOLO). Firstly, in order to better extract the features of fire and smoke, a channel prior dilatation attention module (CPDA) is proposed. Secondly, the mixed-classification detection head (MCDH), a new detection head, is designed. Furthermore, MPDIoU is introduced to enhance the regression and classification accuracy of the model. Then, in the Neck section, a lightweight GSConv module is applied to reduce parameters while maintaining model accuracy. Finally, the knowledge distillation strategy is used during training stage to enhance the generalization ability of the model and reduce the false detection. Experimental outcomes demonstrate that, in comparison to the original model, FFYOLO realizes an mAP0.5 of 88.8% on a custom forest fire dataset, which is 3.4% better than the original model, with 25.3% lower parameters and 9.3% higher frames per second (FPS).

Intelligent Methods for Forest Fire Detection Using Unmanned Aerial Vehicles

This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.

A Capacitive Particle-Analyzing Smoke Detector for Very Early Fire Detection.

Smoke detectors face the challenges of increasing accuracy, sensitivity, and high reliability in complex use environments to ensure the timeliness, accuracy, and reliability of very early fire detection. The improvement in and innovation of the principle and algorithm of smoke particle concentration detection provide an opportunity for the performance improvement in the detector. This study is a new refinement of the smoke concentration detection principle based on capacitive detection of cell structures, and detection signals are processed by a multiscale smoke particle concentration detection algorithm to calculate particle concentration. Through experiments, it is found that the detector provides effective detection of smoke particle concentrations ranging from 0 to 10% obs/m; moreover, the detector can detect smoke particles at parts per million (PPM) concentration levels (at 2 and 5 PPM), and the accuracy of the detector can reach at least the 0.5 PPM level. Furthermore, the detector can detect smoke particle concentrations at better than 1 PPM accuracy even in an environment with 6% obs/m oil gas particles, 7% obs/m large dust interference particles, or 8% obs/m small dust interference particles.

PREDICTING FIRE ALARMS USING MULTI SENSOR DATA: A BINARY CLASSIFICATION APPROACH

Fires pose significant threats to human life, property, and the environment. Early detection of fire incidents is crucial to prevent extensive damage and to ensure the safety of occupants. Traditional fire alarm systems typically rely on a single type of sensor, such as smoke detectors or heat sensors, to detect specific fire indicators. These systems operate based on predefined thresholds and triggers. However, they can be prone to false alarms triggered by non-fire-related events (e.g., cooking fumes or dust) and may not provide early warning signs in certain scenarios. To address these limitations, researchers and engineers have turned to advanced technologies, such as multi-sensor data analysis and machine learning algorithms, to develop more reliable and efficient fire alarm prediction systems. On the other hand, the need for a more robust and accurate fire alarm prediction system stems from the shortcomings of traditional methods. False alarms not only lead to wasted resources but also desensitize occupants, potentially leading them to ignore genuine alarms. Additionally, a delayed response to a fire incident can result in severe consequences, making it essential to develop an intelligent system that can effectively and timely predict fire events. Therefore, this work presents the utilization of multi-sensor data and binary classification to develop a more reliable fire alarm prediction system. The experiments are conducted using a dataset collected from various sensor inputs, including air temperature, humidity, CO2 concentration, molecular hydrogen, ethanol gas, and air pressure etc. Then applied binary classification algorithm to learn patterns from the data and classify fire-related events accurately. The results showed promising improvements in prediction accuracy, reduced false alarm rates, and early detection of fire incidents.

Study on the Response Characteristics of Smoke Detectors Based on the ISO 7240-7 Smoldering Cotton Fire

In this study, a smoldering cotton fire test was conducted in accordance with ISO 7240-7 to analyze the smoke/aerosols and combustion products that occur during a cotton fire that are crucial flammable components of multi-unit dwellings. The results of the smoldering cotton fire experiment comparing ODM and ASD based on the concentration standard of 15 %/m, which are the operating concentrations of the fire detection of type-2 smoke detectors, indicated a delay of approximately 2∼4 min in the ASD fire detection time. In addition, in the case of the smoldering fire, the CO concentrations appeared to be 37 ppm and 62 ppm at the ASD<sub>1,2</sub> fire detector operating concentrations, resulting in high concentrations of combustion gas. Furthermore, in the case of a smoldering fire rather than a flame fire, despite a large amount of smoke/aerosol and gas owing to incomplete combustion because of the lack of buoyancy, it did not flow into the smoke detector chamber and was not distributed on the ceiling; this required a long time to detect the fire. Accordingly, smoke detector operation tests for various smoke/aerosols must be conducted in Korea to meet the international standards of firefighting technology.

Review of the Implementation of Minimum Services for Loading Vehicles on Ships on the Bolok – Rote Route, East Nusa Tenggara Province

The Minimum Service Standards for Ferry Transport are the minimum requirements that must be met by ferry transport companies in providing services to service users. Minimum Service Standards (SPM) inspection process so that when the ship operates it does not cause problems. However, in its implementation the Minimum Service Standards have not been implemented at the Bolok Ferry Port, especially for the Minimum Service Standards for Loading on 4 ships, namely: (1) KMP. Lakaan; (2) KMP. Skipjack II; (3) KMP. Uma Kalada; and (4) KMP. Inerie II on the Bolok – Rote route. The aim of this research is to determine the level or percentage of compliance with the Minimum Service Standards for Loading vehicles on 4 ships on the Bolok – Rote Route. The method used is an observation method in the form of a survey of the distance between vehicles and the level of conformity to Minister of Transportation Regulation Number 62 of 2019 concerning Minimum Service Standards for Ferry Transport. Based on the results of the analysis, it can be seen that on 4 (four) ships in The Bolok – Rote route does not comply with Ministerial Regulation Number 62 of 2019 concerning Minimum Service Standards (SPM) for Ferry Transport, namely: (1) KMP. The conformity rate was 62%; (2) KMP. Cakalang II conformity level of 62%; (3) KMP. Uma Kalada's conformity rate was 65.5%; and (4) KMP. Inerie II conformity rate is 65.5%. Based on the analysis, ship operators can increase the Minimum Service Standards (SPM) for vehicle loading, especially in the following aspects: (1) Safety aspects require improvements to sprinklers and smoke detectors; (2) Security aspects that require providing CCTV on the card deck and regulating the distance between vehicles; and (3) Convenience/affordability aspects include changes to the cardeck height, improvements to lights and fastening to the vehicle when sailing.

An Improved Forest Smoke Detection Model Based on YOLOv8

This study centers on leveraging smoke detection for preemptive forest smoke detection. Owing to the inherent ambiguity and uncertainty in smoke characteristics, existing smoke detection algorithms suffer from reduced detection accuracy, elevated false alarm rates, and occurrences of omissions. To resolve these issues, this paper employs an efficient YOLOv8 network and integrates three novel detection modules for enhancement. These modules comprise the edge feature enhancement module, designed to identify smoke ambiguity features, alongside the multi-feature extraction module and the global feature enhancement module, targeting the detection of smoke uncertainty features. These modifications improve the accuracy of smoke area identification while notably lowering the rate of false alarms and omission phenomenon occurrences. Meanwhile, a large forest smoke dataset is created in this paper, which includes not only smoke images with normal forest backgrounds but also a considerable quantity of smoke images with complex backgrounds to enhance the algorithm’s robustness. The proposed algorithm in this paper achieves an AP of 79.1%, 79.2%, and 93.8% for the self-made dataset, XJTU-RS, and USTC-RF, respectively. These results surpass those obtained by the current state-of-the-art target detection-based and neural network-based improved smoke detection algorithms.

SMWE-GFPNNet: A high-precision and robust method for forest fire smoke detection

Smoke is an early manifestation of forest fire. Accurate identification of smoke from forest fires is crucial for the prevention and control of forest fires, which helps protect the ecological environment and the safety of people. The texture features of smoke are complex and prone to detection omissions. The forest environment is complex, and smoke-like objects in the forest often interfere with smoke recognition. The concentration of smoke at the edge is thin, which easily leads to edge omission. In response to these problems, we propose a high-precision edge focused forest fire smoke detection network. To begin, in response to the problem of detection omission, we present a Swin multidimensional window extractor (SMWE) that enhances information exchange between windows in both horizontal and vertical dimensions to extract global texture features from images with smoke. Then, the guillotine feature pyramid network (GFPN) is suggested, along with a new guillotine convolution method for reducing redundant feature information from a feature fusion perspective, thereby improving the anti-interference ability of the model. Finally, taking into account the thinness and irregularity of the smoke near the borders, a contour adaptive loss function is suggested to minimize the boundary blur caused by down-sampling the feature map in the network. The experimental and application results show that SMWE-GFPNNet accomplishes 80.92 % of the mAP, 90.01 % of the mAP50, and 83.38 % of the mAP75 on the Forest Fire Smoke Complex Background Detection Dataset. Excellent in anti-interference ability and accuracy.

ПРОВЕДЕНИЕ НАТУРНЫХ ИСПЫТАНИЙ СИСТЕМЫ ПОЖАРНОЙ СИГНАЛИЗАЦИИ ПРИ ИМИТАЦИИ ТЕСТОВЫХ ОЧАГОВ ПОЖАРА С ЭВАКУАЦИЕЙ КОНТРОЛЬНОЙ ГРУППЫ

Long-term operation of fire alarm systems, even with routine maintenance, often leads to untimely detection of a fire. Due to the possibility of contamination, dust and, as a consequence, a decrease in the sensitivity of smoke fire detectors, their normal operation
 will be in question. The use of smoke detectors in the process of maintenance that do not simulate the optical density of the environment corresponding to a real fire leads to the fact that in the event of a real fire, the possibility of timely detection of dangerous factors is reduced. The work examines the problem of checking the installed fire alarm system for its effective functioning, as well as the possibility of ensuring safe evacuation when threshold smoke levels are reached. Mathematical modeling of smoke propagation is presented and comparative full-scale tests are carried out. Based on a series of experiments, an effective method has been proposed
 for testing a fire alarm system while simultaneously conducting exercises for the safe evacuation of personnel at a protected facility under conditions of a real decrease in visibility due to the appearance of smoke from a fire.