Effective Fire Detection Research Articles

Chitosan-based films with excellent flame retardancy and highly sensitive fire response for application in self-powered dual fire alarm systems.

The widespread use of flammable building materials severely threatens residential safety. Additionally, traditional fire-alarm systems may fail in complex fire environments due to power disruptions. It is crucial to enhance the flame retardancy of material while establishing effective fire detection and early warning systems. This study prepared a chitosan/gelatin (CG) and LiBr-modified CG (CG-LiBr) composite film using an environmentally friendly water evaporation method. We coated the CG-LiBr film with polytetrafluoroethylene (PTFE), thus a flame-retardant and conductive PTFE-coated film-based triboelectric nanogenerator (PF-TENG) was developed. Notably, the CG-LiBr film exhibits outstanding alarm capabilities, with response times of 0.41 s at 100 °C and 0.4 s under flame attack. Compared to the initial CG, CG-LiBr shows a 24.4 % increase in char residue and a 62.1 % reduction in peak heat release rate. Furthermore, PF-TENG demonstrates excellent voltage output, achieving up to 60.8 V at a vertical contact-separation frequency of 5 Hz. Integrating CG-LiBr's exceptional dual-alarm function into fire protection suits and building materials, along with the development of a fire-alarm system featuring remote signal transmission capabilities, holds considerable promise for enhancing fire safety and developing intelligent early warning systems.

Deep Learning-Based Multistage Fire Detection System and Emerging Direction

Fires constitute a significant risk to public safety and property, making early and accurate detection essential for an effective response and damage mitigation. Traditional fire detection methods have limitations in terms of accuracy and adaptability, particularly in complex environments in which various fire stages (such as smoke and active flames) need to be distinguished. This study addresses the critical need for a comprehensive fire detection system capable of multistage classification, differentiating between non-fire, smoke, apartment fires, and forest fires. We propose a deep learning-based model using a customized DenseNet201 architecture that integrates various preprocessing steps and explainable AI techniques, such as Grad-CAM++ and SmoothGrad, to enhance transparency and interpretability. Our model was trained and tested on a diverse, multisource dataset, achieving an accuracy of 97%, along with high precision and recall. The comparative results demonstrate the superiority of the proposed model over other baseline models for handling multistage fire detection. This research provides a significant advancement toward more reliable, interpretable, and effective fire detection systems capable of adapting to different environments and fire types, opening new possibilities for environmentally friendly fire type detection, ultimately enhancing public safety and enabling faster, targeted emergency responses.

A Robustness Study on Early Fire Image Recognitions

With the advancement of society and the rapid urbanization process, there is an escalating need for effective fire detection systems. This study endeavors to bolster the efficacy and dependability of fire detection systems in intricate settings by refining the existing You Only Look Once version 5 (YOLOv5) algorithm and introducing algorithms grounded on fire characteristics. Primarily, the Convolutional Block Attention Module (CBAM) attention mechanism is introduced to steer the model towards substantial features, thereby amplifying detection precision. Subsequently, a multi-scale feature fusion network, employing the Adaptive Spatial Feature Fusion Module (ASFF), is embraced to proficiently amalgamate feature information from various scales, thereby enhancing the model’s comprehension of image content and subsequently fortifying detection resilience. Moreover, refining the loss function and integrating a larger detection head further fortify the model’s capability to discern diminutive targets. Experimental findings illustrate that the refined YOLOv5 algorithm attains accuracy advancements of 8% and 8.2% on standard and small target datasets, respectively. To ascertain the practical viability of the refined YOLOv5 algorithm, this study introduces a temperature-based flame detection algorithm. By amalgamating and deploying both algorithms, the ultimate experimental outcomes reveal that the integrated algorithm not only elevates accuracy but also achieves a frame rate of 57 frames, aligning with the prerequisites for practical deployment.

A modified vision transformer architecture with scratch learning capabilities for effective fire detection

Fire is considered to be one of the major influencing factors that cause fatalities, property damage, and economic, and ecological disruption. To perform the early detection of fire using data from vision sensors and prevent or reduce the damage that fires cause, deep learning models have been widely adopted to overcome the limitations of conventional methods. However, mainstream convolutional neural network (CNN) models have limited generalisation abilities in unseen scenarios and struggle to obtain a good trade-off among the accuracy, inference speed, and model size. Currently, vision transformers (ViT) outperform conventional CNN models; however, they are computationally expensive and required more data for training. They provide a limited performance for small and medium-sized datasets, which are very common in the fire scene classification domain. In this work, we employ a novel ViT architecture by combining shifted patch tokenisation and local self-attention modules for efficient fire scene classification and enable the model to learn from scratch even on small and medium-sized datasets. Furthermore, to make the model suitable for real-time inferencing, we modify the transformer encoder and eventually achieve a reduced number of floating-point operations and a reduced model size. Additionally, in this work, a medium-scale fire dataset is developed that contains complex real-world scenarios. Our model is assessed on three benchmark and a self-created datasets using several evaluation metrics, including a novel cross-corpse evaluation metric, as well as a robustness evaluation metric. The experimental results indicate that our model achieved an overwhelmingly better performance compared to existing methods in terms of the accuracy and model complexity.

An efficient fire detection network with enhanced multi-scale feature learning and interference immunity

Effective fire detection can identify the source of the fire faster, and reduce the risk of loss of life and property. Existing methods still fail to efficiently improve models’ multi-scale feature learning capabilities, which are significant to the detection of fire targets of various sizes. Besides, these methods often overlook the accumulation of interference information in the network. Therefore, this paper presents an efficient fire detection network with boosted multi-scale feature learning and interference immunity capabilities (MFII-FD). Specifically, a novel EPC-CSP module is designed to enhance backbone’s multi-scale feature learning capability with low computational consumption. Beyond that, a pre-fusion module is leveraged to avoid the accumulation of interference information. Further, we also construct a new fire dataset to make the trained model adaptive to more fire situations. Experimental results demonstrate that, our method obtains a better detection accuracy than all comparative models while achieving a high detection speed for video in fire detection task.

An efficient deep learning architecture for effective fire detection in smart surveillance

The threat of fire is pervasive, poses significant risks to the environment, and may include potential fatalities, property devastation, and socioeconomic disruption. Successfully mitigating these risks relies on the prompt identification of fires, a process in which soft computing methodologies play a pivotal role. Although, these fire detection methodologies neglected to explore the relationships among fire-indicative features, which are important to enable a model to learn more representative and robust features in remote sensing scenarios. In the context of small fire detection from aerial view using satellite imagery or unmanned arial vehicle (UAVs) presents challenges to capture rich spatial detail, hinder the model ability for accurate fire scene classification. Furthermore, it is significant to manage model complexity effectively to facilitate deployment on UAVs for fast and accurate responses in an emergency situation. To cope with these challenges, we propose an advanced model integrated a modified soft attention mechanism (MSAM) and a 3D convolution operation with a MobileNet architecture to overcome obstacles related to optimising features and controlling model complexity. The MSAM enabling the model to selectively emphasise essential features during the training process which acts as a selective filter. This adaptive attention mechanism enhances sensitivity and allowing the model to prioritise relevant patterns for accurate fire detection. Concurrently, the integration of a 3D convolutional operation extends the model spatial awareness, to capture intricate details across multiple scales, and particularly in small regions observed from aerial viewpoints. Benchmark evaluations of the proposed model over the FD, DFAN, and ADSF datasets reveal superior performance with enhanced accuracy (ACR) compared to existing methods. Our model surpassed the state-of-the-art models with an average ACR improvement of 0.54%, 2.64%, and 1.20% on the FD, ADSF, and DFAN datasets, respectively. Furthermore, the use of an explainable artificial intelligence (XAI) technique enhances the validation of the model visual emphasis on critical regions of the image, providing valuable insights into its decision-making process.

An Efficient Forest Fire Detection Algorithm Using Improved YOLOv5

Forest fires result in severe disaster, causing significant ecological damage and substantial economic losses. Flames and smoke represent the predominant characteristics of forest fires. However, these flames and smoke often exhibit irregular shapes, rendering them susceptible to erroneous positive or negative identifications, consequently compromising the overall performance of detection systems. To enhance the average precision and recall rates of detection, this paper introduces an enhanced iteration of the You Only Look Once version 5 (YOLOv5) algorithm. This advanced algorithm aims to achieve more effective fire detection. First, we use Switchable Atrous Convolution (SAC) in the backbone network of the traditional YOLOv5 to enhance the capture of a larger receptive field. Then, we introduce Polarized Self-Attention (PSA) to improve the modeling of long-range dependencies. Finally, we incorporate Soft Non-Maximum Suppression (Soft-NMS) to address issues related to missed detections and repeated detections of flames and smoke by the algorithm. Among the plethora of models explored, our proposed algorithm achieves a 2.0% improvement in mean Average Precision@0.5 (mAP50) and a 3.1% enhancement in Recall when compared with the YOLOv5 algorithm. The integration of SAC, PSA, and Soft-NMS significantly enhances the precision and efficiency of the detection algorithm. Moreover, the comprehensive algorithm proposed here can identify and detect key changes in various monitoring scenarios.

Fire Detection System for Urban Structures with Integrated use of Multisensors in Embodied Technology

Objective: Create a sustainable, low-cost and effective fire detection system (FDS) for urban buildings, based on embedded technology, as an alternative to traditional detection systems. Method: experimental research that used the hypothetical-deductive method, with assemble hardware using the ATMEGA328P microcontroller and the MQ2 gas sensors, MLX90614 temperature and LM393 flame. When building the software, a qualitative model was created, based on everyday observations, associating it with a logical expression; Then, a quantitative model was created based on experimental data subjected to computational analysis using the decision tree method, defining a heuristic for early detection of fire patterns with precision. Results and conclusions: The suggested FDS had a shorter response time than the red ampoule sprinkler and an accuracy of 94%. This system proved to be more agile than common detectors, reducing water and energy consumption when fighting fires and the amount of resources used to replace affected assets. Furthermore, it has a low cost, making it accessible even at a residential. Implications of the research: It can be said that this research represents an important step in the construction of sustainable FDS, bringing social, economic and environmental benefits; and efficient due to the use of computational data analysis. Originality/Value: FDS which uses embedded technology and computational analysis to process fire variables, improves this analysis and allows for more agile and accurate detection, in addition to making the detection system cheaper and reducing the use of resources due to the fire.

An Effective Attention-based CNN Model for Fire Detection in Adverse Weather Conditions

Worldwide, fire disasters cause social, economic, and environmental damage, so their early detection and instant response is crucial for saving lives and property, which is possible via a soft computing approach. Researchers have therefore proposed different artificial intelligence-based approaches to detect fire at its early stages. However, several factors including domain shift problems, limited performance, and model complexity reduced their effectiveness in a real-world environment. To address these challenges, this study proposes an extensive data augmentation approach to tackle the domain shift problem by employing a mono-depth and atmospheric scattering model to generate and synthesise hazy, foggy, and night-time images. To further enhance the detection of small fire-affected areas, a refined DenseNet backbone is employed. This network is fine-tuned to extract intricate spatial details across different scales and establish meaningful connections between them. Subsequently, we introduce a soft attention mechanism into the backbone network. This entails utilising a 3D convolutional operation within the proposed attention framework to capture more extensive spatial features, which contributes to an enhanced discriminatory capability for detecting fire. Moreover, we have created a novel dataset explicitly designed for effective fire detection from a remote sensing perspective, known as the aerial drone and satellite fire (ADSF) dataset, encompasses images captured by drones and satellites. This broader range of image sources affords coverage across a wider expanse of geographical locations, surpassing the capabilities of CCTV cameras. Our proposed model achieves significant accuracy improvements, surpassing the state-of-the-art (SOTA) on both original and augmented datasets. For the Yar, FD, DFAN, and ADSF original datasets, we observed average accuracy increases of 1.25%, 1.95%, 2%, and 1.5%, respectively. In the comparisons with augmented versions of these datasets, our model consistently outperforms the SOTA, with accuracy improvements of 0.7, 1.97%, 1.42%, and 1.53%, respectively. Additionally, in our ablation studies, the proposed model excels in terms of both performance and resource efficiency. It achieves higher frame rates of 22.0, 72.5, and 7.0 FPS on CPU, GPU, and Raspberry Pi, respectively, with just 7.2 million learning parameters, making it well-suited for real-time deployment on edge devices. Finally, a Grad-CAM XAI method is utilised to visualise and highlight the most important regions in images emphasized by the model. The code and dataset are publicly available at https://github.com/Hikmat-Yar/ISPRS-Fire-Detection.

Fire Detection and Geo-Localization Using UAV’s Aerial Images and Yolo-Based Models

The past decade has witnessed a growing demand for drone-based fire detection systems, driven by escalating concerns about wildfires exacerbated by climate change, as corroborated by environmental studies. However, deploying existing drone-based fire detection systems in real-world operational conditions poses practical challenges, notably the intricate and unstructured environments and the dynamic nature of UAV-mounted cameras, often leading to false alarms and inaccurate detections. In this paper, we describe a two-stage framework for fire detection and geo-localization. The key features of the proposed work included the compilation of a large dataset from several sources to capture various visual contexts related to fire scenes. The bounding boxes of the regions of interest were labeled using three target levels, namely fire, non-fire, and smoke. The second feature was the investigation of YOLO models to undertake the detection and localization tasks. YOLO-NAS was retained as the best performing model using the compiled dataset with an average mAP50 of 0.71 and an F1_score of 0.68. Additionally, a fire localization scheme based on stereo vision was introduced, and the hardware implementation was executed on a drone equipped with a Pixhawk microcontroller. The test results were very promising and showed the ability of the proposed approach to contribute to a comprehensive and effective fire detection system.

Visual Intelligence in Smart Cities: A Lightweight Deep Learning Model for Fire Detection in an IoT Environment

The recognition of fire at its early stages and stopping it from causing socioeconomic and environmental disasters remains a demanding task. Despite the availability of convincing networks, there is a need to develop a lightweight network for resource-constraint devices rather than real-time fire detection in smart city contexts. To overcome this shortcoming, we presented a novel efficient lightweight network called FlameNet for fire detection in a smart city environment. Our proposed network works via two main steps: first, it detects the fire using the FlameNet; then, an alert is initiated and directed to the fire, medical, and rescue departments. Furthermore, we incorporate the MSA module to efficiently prioritize and enhance relevant fire-related prominent features for effective fire detection. The newly developed Ignited-Flames dataset is utilized to undertake a thorough analysis of several convolutional neural network (CNN) models. Additionally, the proposed FlameNet achieves 99.40% accuracy for fire detection. The empirical findings and analysis of multiple factors such as model accuracy, size, and processing time prove that the suggested model is suitable for fire detection.

Enhancing Fire Detection Technology: A UV-Based System Utilizing Fourier Spectrum Analysis for Reliable and Accurate Fire Detection

This study proposes a low-cost and reliable smart fire alarm system that utilizes ultraviolet (UV) detection technology with an aspherical lens to detect fires emitting photons in the 185–260 nm range. The system integrates the aspherical lens with an accelerator and a digital compass to determine the fire source’s direction, allowing for safe evacuation and effective firefighting. Artificial intelligence is employed to reduce false alarms and achieve a low false alarm rate. The system’s wide detection range and direction verification make it an effective fire detection solution. Upon detecting a fire, the system sends a warning signal via Wi-Fi or smartphone to the user. The proposed system’s advantages include early warning, a low false alarm rate, and detection of a wide range of fires. Experimental results validate the system’s design and demonstrate high accuracy, reliability, and practicality, making it a valuable addition to fire management and prevention. The proposed system utilizes a parabolic mirror to collect UV radiation into the detector and a simple classification model that uses Fourier transform algorithm to reduce false alarms. The results showed accuracies of approximately 95.45% and 93.65% for the flame and UVB lamp, respectively. The system demonstrated its effectiveness in detecting flames in the range of up to 50 m, making it suitable for various applications, including small and medium-sized buildings, homes, and vehicles.

YONGʻINNI VIDEOTASVIRDA RANGLI FILTRLASH BILAN INTENSIVLIK OʻZGARISHI ASOSIDA ANIQLASH

The paper reviews achievements made in the field of video analytics and computer vision, which enable automatic detection of fires, based on video data. Various algorithms have been implemented in sought for effective fire detection methods using video. As one of these, a color-based fire detection algorithm is being described. However, using only one color model for fi re detection is an inefficient approach. The paper proposes a method for estimating temporal changes in pixel intensity, which is used to retrieve information about fires from fire-like objects in a video image. This method helps to calculate the average intensity value in a sequence of shots. A special software has been developed in the Python programming language using the OpenCV (Open Source Computer Vision Library) library, and the corresponding findings have been gained in view to demonstrate the effectiveness of the proposed method.

Vision Sensor Assisted Fire Detection in IoT Environment using ConvNext

To mitigate social, ecological, and financial damage, effective fire detection and control are crucial. Performing real-time fire detection in Internet of Things (IoT) environments, however, presents significant challenges due to limited storage, transmission, and computational resources. Early fire detection and automated response are essential for addressing these challenges. In this paper, we introduce an IoT-supported deep learning model designed for efficient fire detection. The proposed model builds upon the pre-trained weights of the ConvNext convolutional neural network, which excels at detecting minute features and distinguishing between yellow lights and fire patterns. Implemented on an IoT device, the system triggers an alert when a fire is detected, prompting necessary actions. Our method, tested on the forest fire dataset, demonstrated a 4% improvement in accuracy compared to existing deep learning models for fire detection.

Investigation of Combining Deep Learning Object Recognition with Drones for Forest Fire Detection and Monitoring

Forest fires are a global environmental problem that can cause significant damage to natural resources and human lives. The increasing frequency and severity of forest fires have resulted in substantial losses of natural resources. To mitigate this, an effective fire detection and monitoring system is crucial. This work aims to explore and review the current advancement in the field of forest fire detection and monitoring using both drones or unmanned aerial vehicles (UAVs), and deep learning techniques. The utilization of drones fully equipped with specific sensors and cameras provides a cost-effective and efficient solution for real-time monitoring and early fire detection. In this paper, we conduct a comprehensive analysis of the latest developments in deep learning object detection, such as YOLO (You Only Look Once), R-CNN (Region-based Convolutional Neural Network), and their variants, with a focus on their potential application in the field of forest fire monitoring. The performed experiments show promising results in multiple metrics, making it a valuable tool for fire detection and monitoring.

Survey on Fire Detection Using Image Processing

Abstract: With rising Urbanisation the frequency of fires has increased. A rapid need exists for quick and effective fire detection. Traditional fire detection systems are utilizing physical sensors to detect fire. Sensors gather information about the chemical characteristics of airborne particles, which traditional fire detection systems then use to generate an alarm. However, it can also result in false alerts; for instance, an ordinary fire alarm system might be triggered by smoking inside a space. Using a computer system based on vision for detecting fire would facilitate rapid and precise detection of fire with the ongoing developments in image processing. A lot of observable improvements have been developed to help a successful fire detection algorithm or model. This paper compiles research on methods that, when used, can effectively detect fire. In addition, a system architecture for fire detection is developed in this study. It suggests many fire detection methods, including Celik, SDD, F-RCNN, R-FCN and YOLOv3. This paper offers a thorough comparison of the same.

Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance

Abstract: Accidents caused by undiscovered fires have cost the globe a lot of money. The demand for effective fire detection systems is on the rise. Because of the system's inefficiency, existing fire and smoke detectors are failing. Analyzing live camera data allows for real-time fire detection. The fire flame features are investigated, and the fire is recognized using edge detection and thresholding methods, resulting in the creation of a fire detected model. It detects hazardous fires identified on the size, velocity, volume and the texture. In this paper we are proposing an emerging fire detection system based on Convolutional Neural Network. The model's experimental results on our dataset reveal that it has good fire detection capability and ability of detecting multi-scale fire in real-time. Keywords: Video Surveillance, Segmentation, Classification, Neural Network, Deep Learning, Object Detection.

Privacy-Preserving Efficient Fire Detection System for Indoor Surveillance

Residential fire is a proven hazard for human life and property. Vision based approaches for fire detection are superior to sensor based ones in terms of accuracy and alleviating false positives. Several frameworks that utilize vision-based monitoring in combination with convolutional neural network and other machine learning algorithms, such as support vector machine, K-mean clustering, logistic regression, neural network, and decision rules are available in literature for fire detection. While such frameworks are effective, they cannot be used in private spaces such as inside homes and offices as the privacy of occupants is compromised. In this article, a vision based fire detection framework for monitoring private spaces while preserving the privacy of the occupant is proposed. This is a novel endeavor as no other approach has looked at the issue of privacy preservation in fire detection with vision sensors. The framework utilizes a near infra-red camera to capture images in a manner that the privacy of occupants is preserved. To confirm that images captured with this camera do preserve occupants’ privacy, two random user surveys were conducted. For effective fire detection using these images, a novel system incorporating both spatial and temporal properties of fire is employed. Experiments were conducted and confirm the superiority of the proposed framework when compared with existing techniques in literature both in terms of performance and model size. In addition to this, the lightweight nature of the proposed system enables its effective use over resource-constrained environments as well. This is validated through a real-world prototypical implementation.

Fire and smoke detection with deep learning: A review

This paper outlines a state-of-the-art method for smoke and fire detection utilizing Convolutional Neural Networks (CNNs). The current smoke detectors installed in buildings pose a challenge for effective fire detection. The inefficiency of traditional methods in terms of speed and cost led to the exploration of using Artificial Intelligence (AI) to identify and alert from Closed Circuit Television (CCTV) footage. In this paper, an analytical overview of AI is conducted by using a selfcreated dataset of video frames containing flames and smoke. The data undergoes pre-processing before being used to train a CNN-based machine learning model. The goal of this review study is to understand the available literature in the field and propose a highly accurate, cost-effective, and simple system for fire detection in various scenarios.

Research on Application of the Feature Transfer Method Based on Fast R-CNN in Smoke Image Recognition

Most of the existing smoke detection methods are based on manual operation, which is difficult to meet the needs of fire monitoring. To further improve the accuracy of smoke detection, an automatic feature extraction and classification method based on fast regional convolution neural network (fast R–CNN) was introduced in the study. This method uses a selective search algorithm to obtain the candidate images of the sample images. The preselected area coordinates and the sample image of visual task are used as network learning. During the training process, we use the feature migration method to avoid the lack of smoke data or limited data sources. Finally, a target detection model is obtained, which is strongly related to a specified visual task, and it has well-trained weight parameters. Experimental results show that this method not only improves the detection accuracy but also effectively reduces the false alarm rate. It can not only meet the real time and accuracy of fire detection but also realize effective fire detection. Compared with similar fire detection algorithms, the improved algorithm proposed in this paper has better robustness to fire detection and has better performance in accuracy and speed.