An Improved YOLOv3 Algorithm Combined with Attention Mechanism for Flame and Smoke Detection

Efficient attention based deep fusion CNN for smoke detection in fog environment

A single-chip CMOS smoke and temperature sensor for use as an intelligent fire detector is proposed. The proposed smoke sensor measures smoke density based on the light-scattering method. The temperature sensor is integrated with the smoke sensor not only to sense heat from a fire but also to compensate for the temperature dependency of the smoke sensor. The prototype chip includes an on-chip photodiode (PD), pixel circuit, correlated double sampling (CDS) circuit, and analog-to-digital converter (ADC). The prototype chip was fabricated using a 0.35-mu m CMOS process and was placed inside the smoke detection chamber, while the thermistor for the temperature sensor is placed outside the chamber. The measurement results show plusmn 1% smoke detection accuracy over the range 4% ~ 25% and plusmn1degC temperature-sensing accuracy over the range 25degC ~ 95degC. The power consumption of the prototype chip is 220 nW, excluding the infrared light-emitting diode (IR LED).

There are a lot of flammable materials in the textile workshop, and once a fire occurs, it will cause property damage and casualties. At present, smoke detection in textile workshops mainly relies on temperature‐sensing smoke sensors with low detection rate and poor real‐time performance, which cannot meet the task of smoke detection in complex environments. Therefore, this paper proposes an improved mixed Gaussian and YOLOv5 smoke detection algorithm for textile workshops. In order to reduce the interference of static background in smoke detection, an improved gaussian mixture algorithm is used to extract suspected smoke areas in video by using the dynamic characteristics of smoke. Then, an adaptive attention module is added to the feature pyramid infrastructure of the YOLOv5 target detection network to improve the multi‐scale target recognition ability. In addition, the focal loss function is used to reduce the impact of background and foreground class imbalances on the detection results. The experimental results show that the detection accuracy of the proposed method is 94.7%, and the average detection speed is 66.7 FPS. By comparing with the existing state‐of‐the‐art algorithms, the detection capability of this method has been significantly improved. At the same time, it has high real‐time performance and detection accuracy in smoke detection in textile workshops.

Fire hazards have increased in recent years and detecting fire at an early stage is of utmost importance. An upward smoke movement can help identify location of a fire incident. Therefore smoke detection using vision based machine learning techniques have been quite useful. Recent techniques deploy deep learning models for smoke detection in an outdoor environment. Despite advancements in the field, smoke detection in challenging environments is still a concern in real time applications. Further, deep learning models have large memory footprint that hinders their usage in IoT based smoke detection systems. In this paper, a convolutional neural network with attention mechanism and residual learning is proposed for smoke detection using images of outdoor scenes. The model is lightweight with only 1.23 million parameters, reasonably lower than the existing deep learning models. The model achieves a detection rate of $$99.13\%$$ , and an accuracy of $$99.20 \%$$ on a publicly available dataset. Its performance is also compared with eight existing deep learning smoke detection models that shows its superiority over other models. Features extracted through the model are clustered using t-SNE visualization technique to demonstrate the model’s efficacy in distinguishing features of smoke and non-smoke images.

The fire detection system combines the simultaneous measurements of smoke, carbon monoxide, and carbon dioxide. The security of campus against intruders moving in laboratories, class rooms, staffrooms or washrooms. The fire alarm system consists of Fire detectors (with can be smoke detector, heat, or Infra-Red detectors), control unit and alarm system. A fire detection system is developed based on the simultaneous measurements of temperature and smoke. The fire detection system with the alarm algorithm detected fires that were not alarmed by smoke sensors, and alarmed in shorter times than smoke sensors operating alone. Previous fire detection algorithms used data from sensors for temperature, smoke, and combustion products. The smoke sensor alarms when the analog output signal exceeds or equal the threshold value. The node includes analog sensors to measure smoke, carbon monoxide (CO) and temperature. A fire alarm system should reliably and in a timely way notify building occupants about the presence of fire indicators, such as smoke or high temperatures.

Attention mechanism-based deep learning has played an important role in vision-based smoke detection in forest fire early warning systems. However, the lack of consideration of the specific characteristics of smoke may render existing attention mechanisms ineffective, e.g., in detecting small areas of smoke, particularly in the complex forest smoke scenes involving multiple points of ignition or varying scales. To enhance the accuracy and the interpretability of smoke detection, we propose a Spatial and Efficient Channel Attention mechanism, termed SECA, and integrate SECA into deep models to incorporate the characteristics of smoke diffusion. Technically, multi-kernel 1-dimensional (1D) convolution is utilized for multi-scale smoke-capturing, to replace single-kernel 2D or 3D convolution in existing methods. In implementation, our SECA mechanism can also be used as a common module and easily plugged into a backbone network. To accelerate our model, a DSConv-Haar Wavelet Downsampling technique called DHWD is also provided. Extensive experiments were conducted on public datasets and self-collected datasets. Compared to existing methods, our method can achieve a better or at least a comparable performance in smoke detection in terms of smoke detection accuracy, computational efficiency, and ease of use. For example, it surpasses baseline methods, demonstrating average improvements of 4.2% in mAP50 and of 3.7% in mAP50-95, respectively.

Nowadays, ship’s engine room is fire protected by automatic fire fighting systems, usually controlled from a place located outside the engine room. In order to activate the water mist extinguishing system automatically, at least two different fire detectors have to be activated. One of these detectors is a flame detector that is not hampered by various air flows caused by ventilation or draft and is rapidly activated and the other is smoke detector which is hampered by these flows causing its activation to be delayed. As a consequence, the automatic water mist extinguishing system is also delayed, allowing for fire expansion and its transfer to surrounding rooms. In addition to reliability of the ship’s fire detection system as one of the crucial safety features for the ship, cargo, crew and passengers, using a systematic approach in this research the emphasis is placed on the application of new methods in smoke detection such as the computer image processing and analysis, in order to achieve this goal. This paper describes the research carried out on board ship using the existing marine CCTV systems in early stages of smoke detection inside ship’s engine room, which could be seen as a significant contribution to accelerated suppression of unwanted consequences.

Forest fires are severe ecological disasters worldwide that cause extensive ecological destruction and economic losses while threatening biodiversity and human safety. With the escalation of climate change, the frequency and intensity of forest fires are increasing annually, underscoring the urgent need for effective monitoring and early warning systems. This study investigates the application effectiveness of deep learning-based object detection technology in forest fire smoke recognition by using the YOLOv11x algorithm to develop an efficient fire detection model. The objective is to enhance early fire detection capabilities and mitigate potential damage. To improve the model’s applicability and generalizability, two publicly available fire image datasets, WD (Wildfire Dataset) and FFS (Forest Fire Smoke), encompassing various complex scenarios and external conditions, were employed. After 501 training epochs, the model’s detection performance was comprehensively evaluated via multiple metrics, including precision, recall, and mean average precision (mAP50 and mAP50-95). The results demonstrate that YOLOv11x excels in bounding box loss (box loss), classification loss (cls loss), and distribution focal loss (dfl loss), indicating effective optimization of object detection performance across multiple dimensions. Specifically, the model achieved a precision of 0.949, a recall of 0.850, an mAP50 of 0.901, and an mAP50-95 of 0.786, highlighting its high detection accuracy and stability. Analysis of the precision‒recall (PR) curve revealed an average mAP@0.5 of 0.901, further confirming the effectiveness of YOLOv11x in fire smoke detection. Notably, the mAP@0.5 for the smoke category reached 0.962, whereas for the flame category, it was 0.841, indicating superior performance in smoke detection compared with flame detection. This disparity primarily arises from the distinct visual characteristics of flames and smoke; flames possess more vivid colors and defined shapes, facilitating easier recognition by the model, whereas smoke exhibits more ambiguous and variable textures and shapes, increasing detection difficulty. In the test set, 86.89% of the samples had confidence scores exceeding 0.85, further validating the model’s reliability. In summary, the YOLOv11x algorithm demonstrates excellent performance and broad application potential in forest fire smoke recognition, providing robust technical support for early fire warning systems and offering valuable insights for the design of intelligent monitoring systems in related fields.

Using computer vision to classify, locate and segment fire behavior in UAS-captured images

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.

The study was conducted at the Pampanga State Agricultural University (PSAU), Department of Computer Studies and Automation (DCSA), aimed to develop a Smoke and Fire Detection System for early detection of smoke and fire. The system features a microcontroller connected to sensors, including smoke, temperature, and fire sensors, which automatically triggers alarms when activated. Additionally, it sends SMS notification to the authorized personnel of the Fire Department of Magalang, Pampanga station and PSAU DCSA. The system can also record and display data on smoke, temperature, and fire sensors on the LCD monitor. The development of the system specifically its microcontroller made use of the Arduino Nano and Arduino Mega, while codes were developed using the Arduino Software IDE. Feedback on the capabilities and functions of the system was obtained through a survey questionnaire, observation, and key informant interviews. Respondents acknowledged the system’s potential to enhance fire prevention efforts effectively and efficiently.

Laptop Vision primarily based fireplace detection utilize image process has the potential to be helpful in conditions during which standard ways cannot be adopted. the fire detection rule uses visual characteristics of fires like brightness, colour, spectral texture, spectral flicker, and edge trembling to discriminate them from different visible stimuli. There are numerous varied fireplace detection techniques like infrared device, a thermal detector, smoke detector, flame detector, and optical smoke detector. These techniques aren't constantly reliable as they are doing not perpetually notice {the fireplace the fire |the fireplace} itself however notice one or additional phenomena ensuing from fire, like smoke, heat, infrared, UV radiation or gas, that might be created in different ways and hence, produces several false alarms. By the assistance of laptop vision and image process techniques, it's achievable to get higher results than standard systems as a result of pictures will offer additional reliable data.

Face mask-wearing detection is of great significance for safety protection during the epidemic. Aiming at the problem of low detection accuracy due to the problems of occlusion, complex illumination, and density in mask-wearing detection, this paper proposes a neural network model based on the loss function and attention mechanism for mask-wearing detection in complex environments. Based on YOLOv5s, we first introduce an attention mechanism in the feature fusion process to improve feature utilization, study the effect of different attention mechanisms (CBAM, SE, and CA) on improving deep network models, and then explore the influence of different bounding box loss functions (GIoU, CIoU, and DIoU) on mask-wearing recognition. CIoU is used as the frame regression loss function to improve the positioning accuracy. By collecting 7,958 mask-wearing images and a large number of images of people without masks as a dataset and using YOLOv5s as the benchmark model, the mAP of the model proposed in the paper reached 90.96% on the validation set, which is significantly better than the traditional deep learning method. Mask-wearing detection is carried out in a real environment, and the experimental results of the proposed method can meet the daily detection requirements.

<p class="Abstract" align="center"><strong>ABSTRACT</strong></p><p class="Abstract">The development of IoT-based smoke detectors using NodeMcu ESP8266 and smoke sensors has achieved satisfactory results. This tool has succeeded in providing an effective solution as a responsive early detection of fire. The implementation of remote monitoring through the website allows access to smoke detection information from far-flung locations, providing flexibility and affordability in security surveillance. NodeMcu ESP8266 as an IoT platform proved to be the right choice, bringing the ease of connectivity of tools with the internet. The device's quick response to the presence of smoke at various sensor distances confirms its reliability in detecting potential fires. The success of this research highlights the great potential of IoT technology in improving the level of security, especially in detecting fire threats efficiently. With tested and responsive tools, further implementation and development of functionality can be explored. Overall, the development of smoke detectors promises to make a positive contribution to the understanding and application of IoT technology in the context of public security and safety.</p><p><em> </em></p><p><em>Keywords: </em><em>IoT-Based Smoke Detectors, NodeMcu ESP8266, Remote Monitoring, Fire Early Warning Systems, Sensor Technology</em><em>.</em></p><p> </p><p class="Abstract" align="center"><strong>ABSTRAK</strong></p><p class="Abstract">Pengembangan alat pendeteksi asap berbasis IoT menggunakan NodeMcu ESP8266 dan sensor asap telah mencapai hasil yang memuaskan. Alat ini berhasil memberikan solusi efektif sebagai pendeteksi dini kebakaran yang responsif. Implementasi monitoring jarak jauh melalui website memungkinkan akses informasi deteksi asap dari lokasi yang berjauhan, memberikan fleksibilitas dan keterjangkauan dalam pengawasan keamanan. NodeMcu ESP8266 sebagai platform IoT terbukti menjadi pilihan yang tepat, menghadirkan kemudahan konektivitas alat dengan internet. Respons cepat alat terhadap keberadaan asap pada berbagai jarak sensor menegaskan kehandalannya dalam mendeteksi potensi kebakaran. Kesuksesan penelitian ini menyoroti potensi besar teknologi IoT dalam meningkatkan tingkat keamanan, khususnya dalam mendeteksi ancaman kebakaran secara efisien. Dengan alat yang teruji dan responsif, implementasi lebih lanjut dan pengembangan fungsionalitas dapat diexplorasi. Secara keseluruhan, pengembangan alat pendeteksi asap ini menjanjikan kontribusi positif terhadap pemahaman dan penerapan teknologi IoT dalam konteks keamanan dan keselamatan masyarakat.</p>

DEVELOPMENT OF COMPUTER VISION-BASED AUTOMATIC FLAME DETECTION ALGORITHM USING MATLAB SOFTWARE ENVIRONMENT