Smoke Detection System Research Articles

Real-Time Smoke Detection in Surveillance Videos Using an Enhanced RT-DETR Framework with Triplet Attention and HS-FPN

This study addresses the urgent need for an efficient and accurate smoke detection system to enhance safety measures in fire monitoring, industrial safety, and urban surveillance. Given the complexity of detecting smoke in diverse environments and under real-time constraints, our research aims to solve challenges related to low-resolution imagery, limited computational resources, and environmental variability. This study introduces a novel smoke detection system that utilizes the real-time detection Transformer (RT-DETR) architecture to enhance the speed and precision of video analysis. Our system integrates advanced modules, including triplet attention, ADown, and a high-level screening-feature fusion pyramid network (HS-FPN), to address challenges related to low-resolution imagery, real-time processing constraints, and environmental variability. The triplet attention mechanism is essential for detecting subtle smoke features, often overlooked due to their nuanced nature. The ADown module significantly reduces computational complexity, enabling real-time operation on devices with limited resources. Furthermore, the HS-FPN enhances the system’s robustness by amalgamating multi-scale features for reliable detection across various smoke types and sizes. Evaluation using a diverse dataset showcased notable improvements in average precision (AP50) and frames per second (FPS) metrics compared to existing state-of-the-art networks. Ablation studies validated the contributions of each component in achieving an optimal balance between accuracy and operational efficiency. The RT-DETR-based smoke detection system not only meets real-time requirements for applications like fire monitoring, industrial safety, and urban surveillance but also establishes a new performance benchmark in this field.

Real‐time fire and smoke detection with transfer learning based on cloud‐edge collaborative architecture

AbstractRecent years have seen increased interest in object detection‐based applications for fire detection in digital images and videos from edge devices. The environment's complexity and variability often lead to interference from factors such as fire and smoke characteristics, background noise, and camera settings like angle, sharpness, and exposure, which hampers the effectiveness of fire detection applications. Limited picture data for fire and smoke scenes further challenges model accuracy and robustness, resulting in high false detection and leakage rates. To address the need for efficient detection and adaptability to various environments, this paper focuses on (1) proposing a cloud‐edge collaborative architecture for real‐time fire and smoke detection, incorporating an iterative transfer learning strategy based on user feedback to enhance adaptability; (2) improving the detection capabilities of the base model YOLOv8 by enhancing the data augmentation method and introducing the coordinate attention mechanism to improve global feature extraction. The improved algorithm shows a 2‐point accuracy increase. After three iterations of transfer learning in the production environment, accuracy improves from 93.3% to 96.4%, and mAP0.5:0.95 increases by nearly 5 points. This program effectively addresses false detection issues in fire and smoke detection systems, demonstrating practical applicability.

A new paradigm in cigarette smoke detection: Rapid identification technique based on ATR-FTIR spectroscopy and GhostNet-[formula omitted]

In the tobacco field, the analysis and classification of cigarette smoke are crucial for ensuring product quality, protecting consumer health, and driving industry innovation. These analyses provide a comprehensive understanding of tobacco products and serve as a scientific basis for production standards and regulatory policies. Traditional infrared spectroscopy techniques for tobacco quality analysis often suffer from limitations such as time consumption, high costs, and complexity. To achieve efficient detection of cigarette smoke and quality control of cigarettes, this study developed a cigarette mainstream smoke detection system based on Attenuated Total Reflectance Fourier transform infrared (ATR-FTIR) spectroscopy technology, aimed at rapidly acquiring the mid-infrared (MIR) spectral characteristics of cigarette smoke and combining deep learning for rapid cigarette type identification. Five different brands of cigarettes were selected for this study, and a total of 400 MIR spectra of cigarette smoke aerosols were collected. Using three spectral preprocessing methods and two-dimensional correlation spectroscopy (2DCOS), we extracted the fingerprint region (1850–650 cm-1) to generate 4800 2DCOS images. We then optimized the GhostNet network architecture and constructed a more compact and efficient deep learning model, GhostNet-α. A mixed-precision training strategy further enhanced model training speed and computational efficiency. Results show that Multiple Scatter Correction (MSC)-preprocessed synchronous 2DCOS images achieved 100 % classification accuracy. This study validates GhostNet-α’s efficiency and accuracy in cigarette smoke recognition, offering a new technical approach for quality control and rapid detection in the tobacco industry, significantly enhancing its competitiveness and consumer health protection.

A Forest Fire Smoke Monitoring System Based on a Lightweight Neural Network for Edge Devices

Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utilization of deep learning for smoke detection has achieved remarkable results. However, the existing deep learning models have poor performance in forest scenes and are difficult to deploy because of numerous parameters. Hence, we introduce an optimized forest fire smoke monitoring system for embedded edge devices based on a lightweight deep learning model. The model makes full use of the multi-scale variable attention mechanism of Transformer architecture to strengthen the ability of image feature extraction. Considering the needs of application scenarios, we propose an improved lightweight network model LCNet for feature extraction, which can reduce the parameters and enhance detecting ability. In order to improve running speed, a simple semi-supervised label knowledge distillation scheme is used to enhance the overall detection capability. Finally, we design and implement a forest fire smoke detection system on an embedded device, including the Jetson NX hardware platform, high-definition camera, and detection software system. The lightweight model is transplanted to the embedded edge device to achieve rapid forest fire smoke detection. Also, an asynchronous processing framework is designed to make the system highly available and robust. The improved model reduces three-fourths of the parameters and increases speed by 3.4 times with similar accuracy to the original model. This demonstrates that our system meets the precision demand and detects smoke in time.

Design of smoke detection system using deep learning and sensor fusion with recursive feature elimination cross-validation

The fire safety system is an important component that controls material and immaterial losses. Fire disasters are generally indicated by the appearance of excess smoke and changes in temperature, pressure, and changes in other parameters in the environment. Conventional smoke sensors are limited in reading parameter changes around their environment, making them less effective in early fire detection. This study aims to design a smoke detection system as an early fire detection system, using sensor fusion based on deep learning using the recursive feature elimination method with cross-validation (RFECV) using a random forest classifier used to select optimal parameters from public datasets as the basis for determining the sensor to be used. Based on the RFECV optimal feature, a deep learning algorithm was performed and obtained an accuracy of 0.99, a precision of 0.99, a recall of 1.00, and an F1 score of 0.99, with a latency time of 34.02 μs, which is 71.76% times faster than the original model.

Implementation of IoT Based Gas Leakage Detection Device

In this paper, we present the design and implementation of an innovative Internet of Things (IoT)-based gas and smoke detection system aimed at enhancing safety in various environments. Gas leaks and fires pose significant risks to life, property, and the environment, necessitating effective detection and mitigation strategies. Leveraging advancements in sensor technology, wireless communication, and smart automation, our system provides real-time monitoring of gas levels and smoke presence. Upon detection of a gas leak or smoke, the system initiates automated responses, including activating an exhaust fan for ventilation, disabling electrical appliances, and triggering audible alarms to alert occupants. Additionally, the system integrates with a mobile application, enabling remote monitoring and control. Through comprehensive testing and evaluation, we demonstrate the effectiveness and reliability of our system in enhancing safety and security. Our research contributes to the advancement of IoT-based safety systems and offers insights into future developments in safety engineering. Keywords— “IoT (Internet of Things)”, “Gas Sensor, Mobile Integration”, “Safety protocols”, “MQ2 sensor”, “LM324”.

An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

Multisensory Fusion Approaches for Accurate Smoke Detection in Smart Environments

The reassessment of alarm systems’ role in this regard has led to the search for improved ways of detecting fire. In this study, sensor fusion is explored to improve the accuracy and reliability of smoke detection. Since individual sensors are limited in their capabilities, this research seeks to merge different sensor data using complex fusion techniques. This paper gives a detailed analysis of several types of sensors that are used indoors and outdoors as well as firefighter training grounds that have multiple fire sources. To work around this problem, the Adaboost algorithm was used as an ensemble learning technique where sensor data were combined iteratively to form a strong classification model. The study then goes on to meticulously plot variable distribution graphsbar charts, carry out correlation analyses, and make comparisons with other studies done previously; these findings give insight into how effective sensor fusion methods could be when it comes to smoke detection. The research results indicate that incorporating multiple sensors can significantly enhance detection accuracy and reliability. Thus, the findings obtained from this study identify a promising path for creating more efficient smoke detection systems.

Application of the YOLOv6 Combining CBAM and CIoU in Forest Fire and Smoke Detection

Forest fires are a vulnerable and devastating disaster that pose a major threat to human property and life. Smoke is easier to detect than flames due to the vastness of the wildland scene and the obscuring vegetation. However, the shape of wind-blown smoke is constantly changing, and the color of smoke varies greatly from one combustion chamber to another. Therefore, the widely used sensor-based smoke and fire detection systems have the disadvantages of untimely detection and a high false detection rate in the middle of an open environment. Deep learning-based smoke and fire object detection can recognize objects in the form of video streams and images in milliseconds. To this end, this paper innovatively employs CBAM based on YOLOv6 to increase the extraction of smoke and fire features. In addition, the CIoU loss function was used to ensure that training time is reduced while extracting the feature effects. Automatic mixed-accuracy training is used to train the model. The proposed model has been validated on a self-built dataset containing multiple scenes. The experiments demonstrated that our model has a high response speed and accuracy in real-field smoke and fire detection, which provides intelligent support for forest fire safety work in social life.

SENSOR MQ-2 DETEKSI ASAP ROKOK BERBASIS INTERNET OF THINGS

Cigarette smoke contains toxic chemicals such as carbon monoxide (CO), nicotine and tar. The dangerous/poisonous ingredients in cigarettes cause health problems for those who smoke (active smokers) or those who don't smoke (passive smokers). To avoid the accumulation of cigarette smoke in the room, this research was created and carried out to detect cigarette smoke and reduce the levels of cigarette smoke in the room. Fan. will emit cigarette smoke into the room. The results of the detection of cigarette smoke levels will be sent to Labtop. This system was built using an MQ-2 sensor, ESP8266 microcontroller. The implementation of the cigarette smoke detection system is installed in 3 different rooms/places and is accessed by Internet of Things (IoT) network users. The research results show that every room where this system is installed will send data from cigarette smoke detection results to the lab. The MQ-2 sensor detects cigarette smoke, the data is sent to the internet network via the ESP8266, the data will be displayed on the laptop. From the sample test the tool responded well. This system will activate the fan at certain levels of cigarette smoke to reduce the level of cigarette smoke in the room. When the level is 0 ppm with the Green LED indicator on, the fan is not working or OFF. When the level shows 7 ppm the LED indicator lights up yellow and the fan will turn ON. For the red LED, the cigarette smoke level displayed is 32 ppm with the fan ON. These results prove that the system is functioning properly, detecting and controlling the operation of the fan to remove cigarette smoke from the room and transmit data to the internet network.

Real-Time Video Smoke Detection Based on Deep Domain Adaptation for Injection Molding Machines

Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-annotation, and an attention mechanism by fusing gray histogram image information. Additionally, the study incorporates the domain adversarial training of neural networks (DANN) to investigate the effect of domain shifts when adapting the smoke detection model from one injection molding machine to another on-site. It achieves the function of domain confusion without requiring labeling, as well as the automatic extraction of domain features and automatic adversarial training, using target domain data. Compared to deep domain confusion (DDC), naïve DANN, and the domain separation network (DSN), the proposed method achieves the highest accuracy rates of 93.17% and 91.35% in both scenarios. Furthermore, the experiment employs t-distributed stochastic neighbor embedding (t-SNE) to facilitate fast training and smoke detection between machines by leveraging domain adaption features.

Automatic Outdoor Fire detection using Deep learning

Abstract
 One of the unlucky phenomena that contribute to environmental disasters is fire, which also poses a serious threat to human safety and life, particularly when it is not recognized by sensor-based fire detection systems. Therefore, putting inexpensive and efficient sensors in certain locations will greatly speed up the detection of fires. Vision-based fire detection systems take advantage of the three fundamental features of fire: color, movement, and shape (fire shape). Work has been done to build smoke and fire detection systems based on images that use security cameras. In this study, fire photos are used to extract features before inputs are made. To one of the classification techniques that applies SVM-based machine learning. and CNN-based deep learning technique. We use the linear regression model so that the bounding box of the classified object determines the correct coordinates.

Real Time Fire and Smoke Detection System

Abstract: This research paper presents a real-time fire and smoke detection system using the YOLOv5 object detection algorithm. The system aims to detect fire and smoke in images and video streams captured by a camera in real-time, without the need for any preprocessing or manual intervention. The proposed system uses the YOLOv5 algorithm to detect the fire and smoke regions in the input images and videos. The YOLOv5 model is trained on a dataset of annotated images to recognize fire and smoke patterns accurately. The proposed system has been tested on different datasets and has achieved high accuracy and precision in detecting fire and smoke in real-time. The experimental results demonstrate that the proposed system is robust and efficient, and it can detect fire and smoke in real-time with high accuracy and low latency. The proposed system can be used in various applications, such as early warning systems, fire safety, and disaster management. It can also be integrated with the CCTV network directly

BCMNet: Cross-Layer Extraction Structure and Multiscale Downsampling Network With Bidirectional Transpose FPN for Fast Detection of Wildfire Smoke

At present, the wildfire smoke detection algorithm based on YOLOv3 has problems, such as low accuracy and slow detection speed. In this article, we propose a cross-layer extraction structure and multiscale downsampling network with bidirectional transpose FPN (BCMNet) for fast detection of wildfire smoke. First, a cross-layer extraction module, which combines linear feature multiplexing and receptive field amplification, is designed. It can improve the speed and accuracy of wildfire smoke detection. Second, a multiscale downsampling module with different convolution kernels and maximum pooling operation is designed to preserve the details of the image while downsampling. Then, a bidirectional transposed FPN based on transposed convolution upsampling is designed. It can bidirectionally fuse visual features of shallow layer and semantic features of deep layer on the corresponding scale. The feature information flow between smoke feature maps of different resolution is emphasized. Finally, a wildfire smoke detection system of the Internet of Things based on BCMNet is built by combining the hardware and detection model. The experimental results show that the proposed method achieves 85.50% mAP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sup> and 79.98% mAP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">75</sup> at 40 FPS on NVIDIA Geforce RTX 2080 Ti, which is superior to the common smoke detection methods.

A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5

Wildfire is one of the most significant dangers and the most serious natural catastrophe, endangering forest resources, animal life, and the human economy. Recent years have witnessed a rise in wildfire incidents. The two main factors are persistent human interference with the natural environment and global warming. Early detection of fire ignition from initial smoke can help firefighters react to such blazes before they become difficult to handle. Previous deep-learning approaches for wildfire smoke detection have been hampered by small or untrustworthy datasets, making it challenging to extrapolate the performances to real-world scenarios. In this study, we propose an early wildfire smoke detection system using unmanned aerial vehicle (UAV) images based on an improved YOLOv5. First, we curated a 6000-wildfire image dataset using existing UAV images. Second, we optimized the anchor box clustering using the K-mean++ technique to reduce classification errors. Then, we improved the network's backbone using a spatial pyramid pooling fast-plus layer to concentrate small-sized wildfire smoke regions. Third, a bidirectional feature pyramid network was applied to obtain a more accessible and faster multi-scale feature fusion. Finally, network pruning and transfer learning approaches were implemented to refine the network architecture and detection speed, and correctly identify small-scale wildfire smoke areas. The experimental results proved that the proposed method achieved an average precision of 73.6% and outperformed other one- and two-stage object detectors on a custom image dataset.

Experimental study on the effect of fire alarms on occupants for situational awareness and evacuation decision‐making using a mobile virtual reality head‐mounted display

AbstractFire alarms play a significantrole in situational awareness and decision‐making pertaining to evacuation for fire evacuation safety in office buildings that include small rooms, where many occupants cannot directly see fire or smoke. We conducted experiments using a mobile VR head‐mounted display to examine how individuals perceive the sound of fire alarms in rooms of different sizes. Comparing the cases of hearing the alarm sound in the large room and the small room, approximately 70% of the test participants answered that they wanted to check the situation more when they were in the small room because they could not understand the surrounding situation. Regardless of the room size, when test participants hear the early warning voice, approximately 40% of them would check the neighborhood and evacuate, and when they hear the evacuation directive voice alarm, more than 90% will take the same action. We also discussed the awareness process of occupants considering this result and the configuration of a smoke detection system in Japan. Approximately half of the people in the large room take checking actions; however, the remaining people do not take specific confirmation actions for about 1–3 min and do not check for fires or evacuate.

ASSESSMENT OF PREVENTIVE MEASURES ON FIRE SAFETY: CASE STUDY, ACCRA TECHNICAL UNIVERSITY

The study was set to assess the preventive measures of fire safety: case study, Accra Technical University. The research intends explicitly to identify the main causes of fire outbreaks, identify some effective measures to assess fire safety and give the best recommendations to overcome fire outbreaks at the university. The mixed method was adopted, comprising quantitative and qualitative methods for this research. A quantitative approach was used through field survey questionnaire distribution on the Google form platform to students and staff of Accra Technical University. The qualitative data was obtained through critical action research, including physical observation, which paved the way to gain in-depth knowledge about the existing fire safety measure at the Accra Technical University through narrative analysis. The data was analysed using IBM SPSS Version 26.0 for Windows, and Microsoft Excel generated frequencies percentages in tables where descriptive statistics were performed. The study revealed that power fluctuation, electrical appliance overload, lack of maintenance of electrical wiring, and the negligence of individuals were the main attributes. The study recommends regular firefighting audits, adequate fire safety awareness, fire alarms and smoke detection systems; proper electrical wiring requires regular attention. However, the university authorities should commend an emergency communication system and fire exits for overcoming fire outbreak eventualities.

Indoor fire detection utilizing computer vision-based strategies

Fires are an ever-increasing risk in the world for both indoor and outdoor environments. Current technologies for detection in indoor environments are smoke and flame detectors. However, these detectors have several limitations during both the ignition phase of a fire and propagation. These systems cannot detect an exact position of the fire nor how the fire is spreading, or its size, all of which is necessary information for fire services when dealing with these incidents. A potential solution is to use artificial intelligence techniques such as computer vision, which has shown the potential to detect and recognize objects and activities in indoor spaces. This study aims to develop a vision-based indoor fire and smoke detection system. Existing models based on the Faster R–CNN Inception V2 and the SSD MobileNet V2 models were explored and adopted in this work. This study utilized small training and testing datasets (for indoor specific fire cases) of varying pixel density images. Initial evaluation of the approach was carried out by testing both models on videos, including a mock-up bedroom and living room and a CCTV video of office space. Both high-density smoke environments and flame density scenarios were recognized. The promising results were achieved from using only 480 training images. Despite the success achieved by the Faster R–CNN Inception V2, the SSD MobileNet V2 model showed low accuracy and missed detection results. Future works can focus on integrating this with our previously developed approach, such as occupancy detection, enhancing training data and models, using more advanced detection models, and integrating the proposed approach with the fire fighting and HVAC control systems.

Home Security and Fire Detection System Design Using IoT-based Microcontroller ATmega2560

A smart home security system or SmartHome is a new technology in this modern era with the concept of IoT (Internet of Thing), namely by utilizing internet connectivity by connecting a microcontroller device as a data processor for input and output with other components such as sensors that can communicate via smartphones. The PIR sensor and the MQ-2 smoke detector are one of the important components in a security system both at home and in buildings. Based on statistical data sources at the National Police Headquarters, crime in cases of theft is increasing and statistical data from https://www.jakartafire.net/statistics causes and occurrence of fires are still quite high. Based on the above problems, the author's motivation in making a home security system and fire preventive based IoT using microcontroller ATmega2560 Wi-Fi. This design prototype uses the ATmega2560 microcontroller component as input and output data processing, the HC-SR501 PIR sensor as a motion detection sensor, the MQ-2 sensor as a sensor in reading smoke levels with the addition of other components such as a buzzer as warning sign information and LED as an indicator sensor is active. Monitoring media used is the Blynk application on the smartphone in real time when the sensor detects motion and smoke. In this study, the smoke detection system is set to detect smoke with a threshold value of &gt; 100 ppm. The PIR sensor coding and testing program works well and is already integrated with Blynk. In the second measurement, the sensor has an average voltage value on the MQ-2 sensor output on the 3.53 VDC sensor while the PIR sensor measurement when the sensor detects movement of the output voltage is 0 VDC and when the sensor status idle is 3.3 VDC.

Development and evaluation of a vision-based transfer learning approach for indoor fire and smoke detection

Fire poses a significant risk across industrial and domestic settings, especially to firefighters who must tackle the blaze. Current technology for detection in indoor environments are smoke detectors and flame detectors. However, these detectors have several limitations during the ignition phase of a fire and propagation. These systems cannot detect an exact position of the fire nor how the fire is spreading or its size, all of which is necessary information for fire services when dealing with these incidents. A potential solution is to use artificial intelligence techniques such as computer vision, which has shown the potential to detect and recognise objects and activities in indoor spaces. This study aims to develop a vision-based fire and smoke detection system. A deep learning technique that incorporates convolutional neural networks (CNN) was utilised to develop the real-time detection approach that can potentially provide necessary information for fire services, including identifying the position and size of the fire and how the fire spreads. A transfer learning approach using a pre-trained model was used to train the detector. Based on the detection and recognition tests using indoor fire and smoke videos, results indicated that the fire detection achieved up to 92.37% correct detections while the smoke detection did not perform as well. Hence, further improvement and evaluation of the detection approach will be conducted in future work, focusing on the impact of different parameters such as the detection model, building type, indoor space size and positioning of the detection camera. The present study provides an insight into the capabilities and potential applications of the concept.