Fire Detection Research Articles

임베디드 플랫폼을 위한 화재 조기 감지 시스템: 오경보 최소화를 위한 딥러닝 접근 방식

임베디드 플랫폼을 위한 화재 조기 감지 시스템: 오경보 최소화를 위한 딥러닝 접근 방식

A Multi-Sensor Fire Detection Method based on Trend Predictive BiLSTM Networks

A Multi-Sensor Fire Detection Method based on Trend Predictive BiLSTM Networks

An Explainable AI-Based Modified YOLOv8 Model for Efficient Fire Detection

Early fire detection is the key to saving lives and limiting property damage. Advanced technology can detect fires in high-risk zones with minimal human presence before they escalate beyond control. This study focuses on providing a more advanced model structure based on the YOLOv8 architecture to enhance early recognition of fire. Although YOLOv8 is excellent at real-time object detection, it can still be better adjusted to the nuances of fire detection. We achieved this advancement by incorporating an additional context-to-flow layer, enabling the YOLOv8 model to more effectively capture both local and global contextual information. The context-to-flow layer enhances the model’s ability to recognize complex patterns like smoke and flames, leading to more effective feature extraction. This extra layer helps the model better detect fires and smoke by improving its ability to focus on fine-grained details and minor variation, which is crucial in challenging environments with low visibility, dynamic fire behavior, and complex backgrounds. Our proposed model achieved a 2.9% greater precision rate, 4.7% more recall rate, and 4% more F1-score in comparison to the YOLOv8 default model. This study discovered that the architecture modification increases information flow and improves fire detection at all fire sizes, from tiny sparks to massive flames. We also included explainable AI strategies to explain the model’s decision-making, thus adding more transparency and improving trust in its predictions. Ultimately, this enhanced system demonstrates remarkable efficacy and accuracy, which allows additional improvements in autonomous fire detection systems.

Numerical study on smoke temperature distribution in naturally ventilated inclined tunnels: Effects of tunnel width and tunnel slope

Inclined tunnel fires exhibit unique characteristics compared to horizontal tunnel fires as a result of the stack effect. Nevertheless, there is still a lack of consensus among previous scholars regarding the smoke temperature distribution in inclined tunnel fires. This work conducts a numerical investigation on the smoke back-layering length upstream of the fire source and the temperature decay downstream of the fire source in naturally ventilated inclined tunnels with varying widths and slopes. Results indicate that as the tunnel slope increases from 0° to 8°, the smoke back-layering length first decreases and then continues at a constant value of 1.47H4/3/W1/3, while the effect of tunnel width is negligible. The decay factor in the one-dimensional flow stage (x/H≥4) exhibits two distinct patterns related to tunnel width: it initially remains constant and then drops when the tunnel is wide, whereas it monotonically drops when the tunnel is narrow. Two empirical models are developed to identify the segmented characteristics and verified through the relevant data from existing literature with similar fire scenarios. This work offers a method for estimating the smoke temperature distribution in inclined tunnels, providing crucial insights for fire prevention, smoke detection, and safety strategies in tunnel engineering.

Deep Learning Approach for Wildland Fire Recognition Using RGB and Thermal Infrared Aerial Image

Wildfires cause severe consequences, including property loss, threats to human life, damage to natural resources, biodiversity, and economic impacts. Consequently, numerous wildland fire detection systems were developed over the years to identify fires at an early stage and prevent their damage to both the environment and human lives. Recently, deep learning methods were employed for recognizing wildfires, showing interesting results. However, numerous challenges are still present, including background complexity and small wildfire and smoke areas. To address these challenging limitations, two deep learning models, namely CT-Fire and DC-Fire, were adopted to recognize wildfires using both visible and infrared aerial images. Infrared images detect temperature gradients, showing areas of high heat and indicating active flames. RGB images provide the visual context to identify smoke and forest fires. Using both visible and infrared images provides a diversified data for learning deep learning models. The diverse characteristics of wildfires and smoke enable these models to learn a complete visual representation of wildland fires and smoke scenarios. Testing results showed that CT-Fire and DC-Fire achieved higher performance compared to baseline wildfire recognition methods using a large dataset, which includes RGB and infrared aerial images. CT-Fire and DC-Fire also showed the reliability of deep learning models in identifying and recognizing patterns and features related to wildland smoke and fires and surpassing challenges, including background complexity, which can include vegetation, weather conditions, and diverse terrain, detecting small wildfire areas, and wildland fires and smoke variety in terms of size, intensity, and shape. CT-Fire and DC-Fire also reached faster processing speeds, enabling their use for early detection of smoke and forest fires in both night and day conditions.

Magnetic detection of anthropogenic fires at Xiaodong Rockshelter, Southwest China

The Xiaodong Rockshelter, located on the southwest edge of Yunnan Province, is known as Southeast Asia's oldest (>43.5 ka) and northernmost Hoabinhian technocomplex site. The rockshelter preserves a rich record of animals, plants, and lithic artifacts excavated from sediments with a thickness of 4.6 m. New dating reported here indicates that the stratigraphic sequence spans from 65 ka to 15 ka. Several layers in the sedimentary sequence show evidence of fire, representative of the earliest evidence of fire by Hoabinhian population in a tropical-subtropical area. Here, we use magnetic methods coupled with mineral analysis to differentiate natural material from anthropogenically fired sediment. Archaeological fire events are characterized by higher magnetic concentrations and coarser magnetic grains compared to natural sediments. Significant magnetic enhancements were caused by the transformation of paramagnetic iron-bearing silicates into ferrimagnetic, spherical-shaped magnetite with increasing temperatures. Notably, a pronounced magnetic enhancement was observed between 1.8 and 2.5 m, spanning between 42 and 34 ka, indicating intense and concentrated heating, with estimated firing temperatures reaching ca. 400 °C. Additionally, three thin layers exhibiting magnetic enhancement were detected at depths of 3.65 m, 4.45 m, and 4.55 m, dating to ca. 55.6 ka, 62.3 ka and 64.8 ka respectively. This suggests three short-term fired ash deposits with minimal vertical magnetic enhancement, indicative of fire temperatures at ca. 350 °C. The magnetic method proves effective in detecting anthropogenic fire in archaeological sediments and potentially estimating ancient fire temperatures.

A Review on Fire and Smoke Detection With Intelligent Control for Enhanced Safety Using Machine Learning (ML) and Internet of Things (IoT)

A Review on Fire and Smoke Detection With Intelligent Control for Enhanced Safety Using Machine Learning (ML) and Internet of Things (IoT)

LPG Gas Leak Detection System and LPG Fire Classification Based on Internet of Things and Artificial Intelligence with Telegram Bot as a Monitoring Tool

LPG gas leaks pose a serious threat in industrial kitchens as they can cause costly fires, both in terms of material and safety. To improve safety, an accurate detection system is required. This research focuses on developing an LPG gas leak detection system and LPG fire classification with Internet of Things and Artificial Intelligence technology. Supported by Telegram Bot as an emergency notification monitoring tool, this system uses MQ-2 sensors to detect LPG gas leaks and ESP32-Cam to classify LPG fires along with Pretrained-model technology such as Cascade Fire Detection on OpenCV Cloud Server. As the output of this system, the use of PWM control and automation oversees regulating the Exhaust Fan according to the detected leakage. FreeRTOS is also used for system task efficiency, and Port Forwarding with Ngrok Local Server allows public access to the ESP32-Cam. System testing was conducted by Black-Box testing, then evaluating the performance of the MQ-2 sensor against 400 ppm and 1500 ppm thresholds for LPG testing distances in open kitchens and closed kitchens, as well as analyzing system response and delay via HTTP protocol. The results demonstrated the system's success in detecting gas leaks, classifying LPG fires and facilitating emergency communication.

GPAC-YOLOv8: lightweight target detection for fire scenarios

Abstract Due to the large number of parameters in the deep network model, it is difficult for existing fire detection methods to adapt to limited hardware configurations. In addition, detecting targets in the early stages of a fire is challenging owing to their small size. Therefore, this study presents a novel fire and smoke detection framework called GPAC-YOLOv8, which is based on the YOLOv8 architecture. Firstly, the integration of the ghost module and the Polarized Self-Attention attention mechanism into the backbone culminates in the CGP module, which is designed to improve computational efficiency while maintaining accuracy. Next, an innovative feature fusion module, AC-Neck, is developed through the application of the adaptive spatial feature fusion strategy and the lightweight content-aware reassembly of features upsampling mechanism, aiming to optimize feature map fusion and increase small target detection efficiency. Finally, a Focal-WIoU loss function, augmented with a dual weighting mechanism, is formulated to precisely delineate the aspect ratios of the predicted bounding boxes, thereby strengthening the generalization capacity of the model. Experimental results, derived from the application of the proposed GEAC-YOLOv8 method to a specially constructed dataset, show significant improvements in detection speed while maintaining detection accuracy compared to conventional methods. Thus, the GPAC-YOLOv8 framework demonstrably improves the effectiveness of object detection in fire and smoke scenarios.

Prioritizing the Right to Environment: Enhancing Forest Fire Detection and Prevention Through Satellite Data and Machine Learning Algorithms for Early Warning Systems

Prioritizing the Right to Environment: Enhancing Forest Fire Detection and Prevention Through Satellite Data and Machine Learning Algorithms for Early Warning Systems

FireDA: A Domain Adaptation-Based Method for Forest Fire Recognition with Limited Labeled Scenarios

Vision-based forest fire detection systems have significantly advanced through Deep Learning (DL) applications. However, DL-based models typically require large-scale labeled datasets for effective training, where the quality of data annotation is crucial to their performance. To address challenges related to the quality and quantity of labeling, a domain adaptation-based approach called FireDA is proposed for forest fire recognition in scenarios with limited labels. Domain adaptation, a subfield of transfer learning, facilitates the transfer of knowledge from a labeled source domain to an unlabeled target domain. The construction of the source domain FBD is initiated, which includes three common fire scenarios: forest (F), brightness (B), and darkness (D), utilizing publicly available labeled data. Subsequently, a novel algorithm called Neighborhood Aggregation-based 2-Stage Domain Adaptation (NA2SDA) is proposed. This method integrates feature distribution alignment with target domain Proxy Classification Loss (PCL), leveraging a neighborhood aggregation mechanism and a memory bank designed for the unlabeled samples in the target domain. This mechanism calibrates the source classifier and generates more accurate pseudo-labels for the unlabeled sample. Consequently, based on these pseudo-labels, the Local Maximum Mean Discrepancy (LMMD) and the Proxy Classification Loss (PCL) are computed. To validate the efficacy of the proposed method, the publicly available forest fire dataset, FLAME, is employed as the target domain for constructing a transfer learning task. The results demonstrate that our method achieves performance comparable to the supervised Convolutional Neural Network (CNN)-based state-of-the-art (SOTA) method, without requiring access to labels from the FLAME training set. Therefore, our study presents a viable solution for forest fire recognition in scenarios with limited labeling and establishes a high-accuracy benchmark for future research.

Dehazing Algorithm Integration with YOLO-v10 for Ship Fire Detection

Ship fire detection presents significant challenges in computer vision-based approaches due to factors such as the considerable distances from which ships must be detected and the unique conditions of the maritime environment. The presence of water vapor and high humidity further complicates the detection and classification tasks for deep learning models, as these factors can obscure visual clarity and introduce noise into the data. In this research, we explain the development of a custom ship fire dataset, a YOLO (You Only Look Once)-v10 model with a fine-tuning combination of dehazing algorithms. Our approach integrates the power of deep learning with sophisticated image processing to deliver comprehensive solutions for ship fire detection. The results demonstrate the efficacy of using YOLO-v10 in conjunction with a dehazing algorithm, highlighting significant improvements in detection accuracy and reliability. Experimental results show that the YOLO-v10-based developed ship fire detection model outperforms several YOLO and other detection models in precision (97.7%), recall (98%), and mAP@0.50 score (89.7%) achievements. However, the model reached a relatively lower score in terms of F1 score in comparison with YOLO-v8 and ship-fire-net model performances. In addition, the dehazing approach significantly improves the model’s detection performance in a haze environment.

Real-Time Fire Classification Models Based on Deep Learning for Building an Intelligent Multi-Sensor System

Fire detection systems are critical for mitigating the damage caused by fires, which can result in significant annual property losses and fatalities. This paper presents a deep learning-based fire classification model for an intelligent multi-sensor system aimed at early and reliable fire detection. The model processes data from multiple sensors that detect various parameters, such as temperature, humidity, and gas concentrations. Several deep learning architectures were evaluated, including LSTM, GRU, Bi-LSTM, LSTM-FCN, InceptionTime, and Transformer. The models were trained on data collected from controlled fire scenarios and validated for classification accuracy, loss, and real-time performance. The results indicated that the LSTM-based models (particularly Bi-LSTM and LSTM) could achieve high classification accuracy and low false alarm rates, demonstrating their effectiveness for real-time fire detection. The findings highlight the potential of advanced deep-learning models to enhance the reliability of sensor-based fire detection systems.

Digital Measures to Decipher Forest Fires a Comparative Study of the Moroccan and American Experiences

Objectives: The study analyzed the digital measures in forest fire management in Morocco and the United States, comparing of the fire management methods in each country. The goal was to enhance the policies and strategies used in Morocco and to further integrate the Moroccan approach with the American experience. Methods: The study relied on the descriptive-analytical approach to describe the digital measures adopted in both Morocco and the United States for extinguishing forest fires. The comparative approach was also used to compare the experiences of both countries in combating forest fires and explore how Morocco can benefit from American expertise. Results: The study results indicate that both Morocco and the United States use digital technology for early detection of forest fires. However, Morocco faces challenges such as funding shortages, inadequate technical infrastructure, and the need for firefighter training. Meanwhile, the U.S. employs advanced technologies, including satellites, drones, and ground-based thermal sensors, and benefits from integrated information management systems and artificial intelligence. Despite this, the U.S. also encounters challenges related to coordinating efforts among different agencies. In comparison, the U.S. has significantly higher levels of funding and technical support, allowing for the use of more advanced technologies. Therefore, Morocco could benefit from the American experience in several ways, including improving technical infrastructure, training firefighting teams, using integrated information management systems, and exchanging expertise and knowledge.. Conclusions: These results reflect the importance of digital technology in enhancing the effectiveness of forest fire response and highlight Morocco's potential to benefit from the United States' experience to address this environmental issue more effectively.

A flexible perception method of thin smoke based on patch total bounded variation for buildings.

Early fire warning is critical to the safety and stability of power systems. However, current methods encounter challenges in capturing subtle features, limiting their effectiveness in providing timely alerts for potential fire hazards. To overcome this drawback, a novel detection algorithm for thin smoke was proposed to enhance early fire detection capabilities. The core is that the Patch-TBV feature was proposed first, and the total bounded variation (TBV) was computed at the patch level. This approach is rooted in the understanding that traditional methods struggle to detect minute variations in image characteristics, particularly in scenarios where the features are dispersed or subtle. By computing TBV at a more localized level, the algorithm proposed gains a finer granularity in assessing image quality, enabling it to capture subtle variations that might indicate the presence of smoke or early signs of a fire. Another key aspect that sets our algorithm apart is the incorporation of subtle variation magnification. This technique serves to magnify subtle features within the image, leveraging the computed TBV values. This magnification strategy is pivotal for improving the algorithm's precision in detecting subtle variations, especially in environments where smoke concentrations may be minimal or dispersed. To evaluate the algorithm's performance in real-world scenarios, a comprehensive dataset, named TIP, comprising 3,120 images was constructed. The dataset covers diverse conditions and potential challenges that might be encountered in practical applications. Experimental results confirm the robustness and effectiveness of the proposed algorithm, showcasing its ability to provide accurate and timely fire warnings in various contexts. In conclusion, our research not only identifies the limitations of existing methods in capturing subtle features for early fire detection but also proposes a sophisticated algorithm, integrating Patch-TBV and micro-variation amplification, to address these challenges. The algorithm's effectiveness and robustness are substantiated through extensive testing, demonstrating its potential as a valuable tool for enhancing fire safety in power systems and similar environments.

Ultra-lightweight convolution-transformer network for early fire smoke detection

BackgroundForests are invaluable resources, and fire is a natural process that is considered an integral part of the forest ecosystem. Although fire offers several ecological benefits, its frequent occurrence in different parts of the world has raised concerns in the recent past. Covering millions of hectares of forest land, these fire incidents have resulted in the loss of human lives, wild habitats, civil infrastructure, and severe damage to the environment. Around 90% of wildland fires have been caused by humans intentionally or unintentionally. Early detection of fire close to human settlements and wildlife centuries can help mitigate fire hazards. Numerous artificial intelligence-based solutions have been proposed in the past decade that prioritize the detection of fire smoke, as it can be caught through remote sensing and provide an early sign of wildland fire. However, most of these methods are either computationally intensive or suffer from a high false alarm rate. In this paper, a lightweight deep neural network model is proposed for fire smoke detection in images captured by satellites or other remote sensing sources.ResultsWith only 0.6 million parameters and 0.4 billion floating point operations per second, the hybrid network of convolutional and vision transformer blocks efficiently detects smoke in normal and foggy environmental conditions. It outperforms seven state-of-the-art methods on four datasets, including a self-collected dataset from the “Moderate Resolution Imaging Spectroradiometer” satellite imagery. The model achieves an accuracy of more than 99% on three datasets and 93.90% on the fourth dataset. The t-distributed stochastic neighbor embedding of extracted features by the proposed model demonstrates its superior feature learning capabilities. It is remarkable that even a tiny occurrence of smoke covering just 2% of the satellite image area is efficiently detected by the model.ConclusionsWith low memory and computational demands, the proposed model works exceedingly well, making it suitable for deployment in resource constrained devices for forest surveillance and early fire smoke detection.

LD-YOLO: A Lightweight Dynamic Forest Fire and Smoke Detection Model with Dysample and Spatial Context Awareness Module

The threat of forest fires to human life and property causes significant damage to human society. Early signs, such as small fires and smoke, are often difficult to detect. As a consequence, early detection of smoke and fires is crucial. Traditional forest fire detection models have shortcomings, including low detection accuracy and efficiency. The YOLOv8 model exhibits robust capabilities in detecting forest fires and smoke. However, it struggles to balance accuracy, model complexity, and detection speed. This paper proposes LD-YOLO, a lightweight dynamic model based on the YOLOv8, to detect forest fires and smoke. Firstly, GhostConv is introduced to generate more smoke feature maps in forest fires through low-cost linear transformations, while maintaining high accuracy and reducing model parameters. Secondly, we propose C2f-Ghost-DynamicConv as an effective tool for increasing feature extraction and representing smoke from forest fires. This method aims to optimize the use of computing resources. Thirdly, we introduce DySample to address the loss of fine-grained detail in initial forest fire images. A point-based sampling method is utilized to enhance the resolution of small-target fire images without imposing an additional computational burden. Fourthly, the Spatial Context Awareness Module (SCAM) is introduced to address insufficient feature representation and background interference. Also, a lightweight self-attention detection head (SADH) is designed to capture global forest fire and smoke features. Lastly, Shape-IoU, which emphasizes the importance of boundaries’ shape and scale, is used to improve smoke detection in forest fires. The experimental results show that LD-YOLO realizes an mAP0.5 of 86.3% on a custom forest fire dataset, which is 4.2% better than the original model, with 36.79% fewer parameters, 48.24% lower FLOPs, and 15.99% higher FPS. Therefore, LD-YOLO indicates forest fires and smoke with high accuracy, fast detection speed, and a low model complexity. This is crucial to the timely detection of forest fires.

FIRE DETECTION USING AI

Fires are one of the biggest challenges in the world right now, due to the global warming that the planet is currently suffering from. We all know what fires are and what they are capable of causing great damage, whether to humans, animals, or other forms of life. Fires spreading increasingly around the world due to increasing global warming, it has become imperative to develop an intelligent system that detects fires early, using modern technology. Therefore, we used one of the artificial intelligence techniques, which is machine learning, which is one of the popular methods now. Professionals have done a lot of research, experiments, and coding software to detect fires using machine learning. Image processing is a type of processing in which the input image is transformed into another image as output with certain techniques applied to it. In this concept, we will create a fire detecting device using a USB or system camera and a application and apply the concepts of IoT and Image Processing to get real time fire detection results. When the device is switched on, it continuously monitors the area Infront of camera for fires. This is done by using HAAR Cascade Classifier Algorithm. Once detected the system could be hooked up with either fire extinguishers to make them work independently or it could just set an alarm or send a notification to the users mobile device via GSM. The after processing possibilities are endless.

Analysis of Innovation Trends in Energy Storage Safety Technology based on Patent Data

Against the backdrop of energy transition and the large-scale development of renewable energy, the significance of energy storage technology has become increasingly prominent. Based on the data of invention patents, this paper analyzes the innovation situation of global energy storage safety technology, providing a reference basis for future patent research and industrial planning in the field of energy storage safety. Through the global and Chinese patent application volumes, the research comparatively analyzes the application situations of the main source countries and main applicants of patents, and analyzes the innovation situation of energy storage safety technology by combining research methods such as technical structure comparison and value degree comparison. The study finds that global energy storage safety innovation is in a relatively active period. China takes the leading position in the total amount of patent applications, but the proportion of patents with high value is low, and it still lags behind South Korea and the United States. Currently, the main research directions in this field worldwide mainly include battery monitoring and status monitoring, battery protection, fire detection and alarm, fire extinguishing systems, and battery pack structure design.

Efficient attention-based networks for fire and smoke detection

Efficient attention-based networks for fire and smoke detection