• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.5
• /
• pp.494-498
• /
• 2004

Fire accidents often happen in large buildings because large buildings are equipped with heavy electrical wiring and piping. When fire is to be occurred in those buildings, it is very dangerous to People and building structures. Therefore, multi-point wireless temperature sensors for large buildings are necessary in order to detect fire in the early time and thus to minimize the loss. A wireless device was composed of the transmitter and receiver. The specification of this device was as follows: 915MHz of transmitted frequency, 4 channels, 9600bps of the transmitted speed, and 10mW of the transmitted power. We confirmed through experiment that the temperature was well sensed and fire location was determined by the 4 channel sensors of the developed sensor system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.4
• /
• pp.41-53
• /
• 2018

Recently, the development of machine learning technology has led to the application of deep learning technology to existing image based application systems. In this context, some researches have been made to apply CNN (Convolutional Neural Network) to the field of fire detection. To verify the effects of existing preprocessing and feature extraction methods on fire detection when combined with CNN, in this paper, the recognition performance and learning time are evaluated by changing the VGG19 CNN structure while gradually increasing the convolution layer. In general, the accuracy is better when the image is not preprocessed. Also it's shown that the preprocessing method and the feature extraction method have many benefits in terms of learning speed.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.7-8
• /
• 2014

The smart fire detection and automatic extinguish device interface platform based on thermal imaging camera that early monitors fire is designed and implemented in this paper. If a fire occurs in some area, the developed system can detect and automatically extinguish the fire. The major functions for developing the system are: Image system and Viewer for fire detection based on Thermal imaging camera and Megapixel camera; Automatic extinuish device for early fir detection; Interface platform between monitoring systems and automatic extinguish device.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2008.04a
• /
• pp.108-111
• /
• 2008

Emergency lantern is an escape equipment of fire fighting. This equipment of obligation installation in buildings. But, We cast doubt on this equipment's reliability. Therefor we have need to study of this equipment's reliability. This paper research general emergency lantern for up grade reliability. For connection to fire alarm system, alarm for get lost general emergency lantern, and pilot lamp for interruption of electric power, and charge to rechargeable battery in general emergency lantern from fire alarm system. Then view very good result in reliability.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.52-54
• /
• 2010

본 논문에서는 최근 국가적으로 집중 투자되고 있는 U-City, U-Campus, U-Home 등 유비쿼터스 환경의 적합한 USN을 이용한 화재 탐지 시스템을 분석하고, 센서와 센서수신기 그리고 서버간의 안전한 통신과 무결성 확인을 위한 보안통신 프로토콜을 제안한다.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.4
• /
• pp.23-30
• /
• 2022

In this paper, we propose an algorithm that can accurately segment a fire even when it is surrounded by smoke of a similar color. Existing fire area segmentation algorithms have a problem in that they cannot separate fire and smoke from fire images. In this paper, the fire was successfully separated from the smoke by applying the color compensation method and the fog removal method as a preprocessing process before applying the fire area segmentation algorithm. In fact, it was confirmed that it segments fire more effectively than the existing methods in the image of the fire scene covered with smoke. In addition, we propose a method that can use the proposed fire segmentation algorithm for efficient fire detection in factories and homes.

• 방재와보험
• /
• s.49
• /
• pp.86-91
• /
• 1991

• Journal of the Korea Convergence Society
• /
• v.7 no.1
• /
• pp.37-42
• /
• 2016

Recent advances have been made in technology of sensor devices. Accordingly, the size of devices has been miniaturized, to which diverse functions can be applied. On top of that, the devices use image processing technology to observe circumstances of users' living spaces and detect risk situations saved in database. In case of detecting risk situations, M2M environment is constructed so that the information can be delivered to other communication devices to immediately raise an alarm. This paper aims to introduce solutions that construct M2M environment by using color detection algorithm of OpenCV and Raspberry Pi, raise an alarm to users in case of fire, and provide information on follow-up measures for it.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.50-53
• /
• 2022

In order to detect an object in yolv5, a process of annotating location information on an existing image is required when learning an image. The most representative method is to draw a bounding box on an image to store location information as meta information. However, if the boundary of the object is ambiguous, it will be difficult to make a bounding box. A representative example would be to classify parts that are not fire and parts that are fire. Therefore, in this paper, images of 100 samples judged to have caught fire were learned by varying the number of boxes. The results showed better fire detection performance in the model where the bounding box was trained by annotating it with three boxes by segmenting it slightly more than annotating it with one box by holding the edge as large as possible during annotating it with one box.