• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.320-330
• /
• 2020

Fire is difficult to achieve good performance in image detection using deep learning because of its high irregularity. In particular, there is little data on fire detection in underground utility facilities, which have poor light conditions and many objects similar to fire. These make fire detection challenging and cause low performance of deep learning models. Therefore, this study proposed a fire detection model using deep learning and estimated the performance of the model. The proposed model was designed using a combination of a basic convolutional neural network, Inception block of GoogleNet, and Skip connection of ResNet to optimize the deep learning model for fire detection under underground utility facilities. In addition, a training technique for the model was proposed. To examine the effectiveness of the method, the trained model was applied to fire images, which included fire and non-fire (which can be misunderstood as a fire) objects under the underground facilities or similar conditions, and results were analyzed. Metrics, such as precision and recall from deep learning models of other studies, were compared with those of the proposed model to estimate the model performance qualitatively. The results showed that the proposed model has high precision and recall for fire detection under low light intensity and both low erroneous and missing detection capabilities for things similar to fire.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.117-126
• /
• 2023

Traditional markets, formed naturally, often feature aged buildings and facilities that are susceptible to fire. However, the lack of adequate fire detection systems in these markets can easily lead to large-scale fires upon ignition. Therefore, this study was conducted with the aim of detecting fires in traditional markets, utilizing thermal imaging cameras for data collection and the YOLOv8 model for object detection experiments. Data were collected in the night markets within traditional markets of xx city and by simulating fire scenarios. A comparative analysis of the Nano and XL models of YOLOv8 revealed that the XL model is more effective in detecting fires. The XL model not only demonstrated higher accuracy in correctly identifying flames but also tended to miss fewer fires compared to the Nano model. In the case of objects other than flames, the XL model showed superior performance over the Nano model. Taking all these factors into account, it is anticipated that with further data collection and improvement in model performance, a suitable fire detection system for traditional markets can be developed.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.9-16
• /
• 2020

In this paper, we propose a prototype design and implementation of a fire detection algorithm using multiple sensors. The proposed topic detection system determines fire by applying rules based on data from multiple sensors. The fire takes about 3 to 5 minutes, which is the optimal time for fire detection. This means that timely identification of potential fires is important for fire management. However, current fire detection devices are very vulnerable to false alarms because they rely on a single sensor to detect smoke or heat. Recently, with the development of IoT technology, it is possible to integrate multiple sensors into a fire detector. In addition, the fire detector has been developed with a smart technology that can communicate with other objects and perform programmed tasks. The prototype was produced with a success rate of 90% and a false alarm rate of 10% based on 10 actual experiments.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.476-481
• /
• 2019

Early detection of fire is an important measure for minimizing the loss of life and property damage. However, fire and smoke need to be simultaneously detected. In this context, numerous studies have been conducted on image-based fire detection. Conventional fire detection methods are compute-intensive and comprise several algorithms for extracting the flame and smoke characteristics. Hence, deep learning algorithms and convolution neural networks can be alternatively employed for fire detection. In this study, recorded image data of fire in a ship engine room were analyzed. The flame and smoke characteristics were extracted from the outer box, and the YOLO (You Only Look Once) convolutional neural network algorithm was subsequently employed for learning and testing. Experimental results were evaluated with respect to three attributes, namely detection rate, error rate, and accuracy. The respective values of detection rate, error rate, and accuracy are found to be 0.994, 0.011, and 0.998 for the flame, 0.978, 0.021, and 0.978 for the smoke, and the calculation time is found to be 0.009 s.

• Journal of the Korean Institute of Gas
• /
• v.16 no.6
• /
• pp.107-114
• /
• 2012

Fire detection system is used for detection and alarm-generation of danger in case of fire. Most fire detection systems being used these days often malfunction from false positive and false negative errors. To improve detection reliability, an integrated fire detection algorithm using multi-senor information of heat, smoke and carbon monoxide detectors is suggested, then built and tested using the LabVIEW environment. Simulated using sensor measurement data offered by National Institute of Standards and Technology (NIST), possibility of reducing false positive and false negative errors is verified.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3475-3489
• /
• 2014

Here we present a simple flame detection method for an infrared (IR) thermal camera based real-time fire surveillance digital signal processor (DSP) system. Infrared thermal cameras are especially advantageous for unattended fire surveillance. All-weather monitoring is possible, regardless of illumination and climate conditions, and the data quantity to be processed is one-third that of color videos. Conventional IR camera-based fire detection methods used mainly pixel-based temporal correlation functions. In the temporal correlation function-based methods, temporal changes in pixel intensity generated by the irregular motion and spreading of the flame pixels are measured using correlation functions. The correlation values of non-flame regions are uniform, but the flame regions have irregular temporal correlation values. To satisfy the requirement of early detection, all fire detection techniques should be practically applied within a very short period of time. The conventional pixel-based correlation function is computationally intensive. In this paper, we propose an IR camera-based simple flame detection algorithm optimized with a compact embedded DSP system to achieve early detection. To reduce the computational load, block-based calculations are used to select the candidate flame region and measure the temporal motion of flames. These functions are used together to obtain the early flame detection algorithm. The proposed simple algorithm was tested to verify the required function and performance in real-time using IR test videos and a real-time DSP system. The findings indicated that the system detected the flames within 5 to 20 seconds, and had a correct flame detection ratio of 100% with an acceptable false detection ratio in video sequence level.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.1
• /
• pp.70-76
• /
• 2006

The objective of this paper is to propose a reference model of a fire detection and monitoring system using MS/TP protocol. The reference model is designed to satisfy the requirements of response time and flexibility. The reference model is operated on the basis of BACnet, a standard communication protocol for building automation systems. Validity of the reference model was examined using a simulation model. This study also evaluated the performance of the BACnet-based fire detection and monitoring system in terms of network-induced delay. Simulation results show that the reference model satisfies the requirements of the fire detection and monitoring system.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.9
• /
• pp.847-854
• /
• 2014

The paper presented a method of early fire detection based on the environmental characteristics inside the nacelle of wind turbine generator system(WTGS). The rising rates of the temperature and smoke density were used as the parameters for early fire detection. By considering the characteristics of temperature and smoke density of a nacelle, this method is very reliable and can minimize the possibility of a malfunction of fire detection. The performance of the method was tested through sets of experiments by using nacelle simulator.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.305-306
• /
• 2006

To avoid the large scale of damage when fire occurs in the tunnel, it is necessary to have a system to minimize the damage, and early discovery of the problem. In this paper, we have proposed algorithm using the image processing, which is the high-speed detection for the occurrence of fire or smoke in the tunnel. The fire detection is different to the forest fire detection as there are elements such as car and tunnel lightings and other variety of elements different from the forest environment. Therefore, an indigenous algorithm should be developed.The two algorithms proposed in this paper, are able to complement with each other and also they can detect the exact position, at the earlier stay of detection. In addition, by comparing properties of each algorithm throughout this experiment, we have proved the propriety of algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.8
• /
• pp.734-741
• /
• 2004

This paper presents a network based fire detection system using CAN, in order to evaluate feasibility of home automation protocol for smart home. In general, because a traditional fire detection system has an analog transmission method with 4-20mA current, it has several shortcomings such as weakness to noise. Hence, as an alternative to the traditional system, this paper presents the architecture of CAN based fire detection system and the design method of CAN communication network. Also, the performance of the suggested system is evaluated through an experimental testbed. Especially, CAN has several advantages such as low cost and easiness of implementation compared to Ethernet or ARCNET, which are low layer of BACNet. Therefore, if CAN is adopted as low layer of BACNet, the home automation system is implemented more effectively.