• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1998.05a
• /
• pp.119-124
• /
• 1998

방재에 있어서 화재의 초기감지가 얼마나 중요한 것인지를 우리는 잘 알고 있으나, 자동화재탐지설비에 대한 유지$\cdot$보수의 중요성에 대한 개념은 매우 미비하며, 이에 따른 연구도 빈약한 상태이다. 자동화재탐지설비는 건물내에 발생한 화재를 초기단계 즉 화재에 의하여 발생할 열 또는 연소생성물을 자동적으로 감지하고, 건물내의 관계자 및 거주자에게 음향장치에 의하여 화재의 발생을 알리는 설비이다. (중략)

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2002.11a
• /
• pp.117-123
• /
• 2002

자동화재탐지설비는 수신기, 감지기, 중계기, 발신기, 음향장치, 배선, 전원 등으로 구성되어 있는 것으로, 화재 발생시 생성되는 물리적, 화학적 현상을 자동으로 감지하여 음향장치를 작동함으로써 화재를 조기에 발견하여 초기소화를 가능하게 하고 관계자 또는 거주자가 신속히 피난할 수 있도록 하는 설비이다.(중략)

• 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.

• Fire Science and Engineering
• /
• v.22 no.4
• /
• pp.42-49
• /
• 2008

This research is to provide a scheme for an automatic fire alarm system with higher reliability through solving problems of malfunctioning (false or missing fire alarm) and power interruption (result from frequently unwanted activation, etc) of an automatic fire alarm system. A digital control system with microprocessor-based is proposed to reduce the possibility of malfunctioning through a combinational use of heat, smoke and CO sensors. Higher reliability could be achieved by these multiple sensors based fire detection system and fire distinction algorithm. In this research, we implemented actual fire detection system and conducted fire test to verify improvement on reliability.

• Journal of Advanced Marine Engineering and Technology
• /
• v.25 no.2
• /
• pp.375-382
• /
• 2001

In this study, an adapted Turbo Coding Algorithm for reducing communication error of a fire detection system for marine vessels, especially image transmission via power lone. Because it is necessary that this system communicate larger and faster than previous method, this study carried out enhancement a decoding speed by adaptation CRC with Turbo Code Algorithm, improvement of metric method, and reduction of decoding delay by using of Center-to-Top method. And the results are as follows: (1) Confirmed that a Turbo Code is so useful methods for reducing communication error in lots of noise environments. (2)Proposed technology in this study speed increasing method of Turbo Coding Algorithm proves 2 times faster than normal Turbo Code and communication error reducing as well in the board made by VHDL software & chips ALTERA company.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.25-26
• /
• 2015

The Unattended fire detection system using a wireless communication device is designed in this paper. If a fire occurs in some area, the system can detect and automatically extinguish the fire. The major functions for the system are: Unattended detection system for fire based on wireless communication system and Automatic extinguish device system; Thermal imaging camera and video camera system; Monitoring viewer and map viewer system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.331-336
• /
• 2017

The need for early fire detection technology is increasing in order to prevent fire disasters. Sensor device detection for heat, smoke and fire is widely used to detect flame and smoke, but this system is limited by the factors of the sensor environment. To solve these problems, many image-based fire detection systems are being developed. In this paper, we implemented a system to detect fire and smoke from camera input images using a convolution neural network. Through the implemented system using the convolution neural network, a feature map is generated for the smoke image and the fire image, and learning for classifying the smoke and fire is performed on the generated feature map. Experimental results on various images show excellent effects for classifying smoke and fire.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.133-142
• /
• 2010

P-type fire control panel, currently in use, has a big hazard that can cause the large scaled human death tolls and property damage in the massive fire because it is difficult to identify in real time the location of fire outbreak and whether search-device are broken down or not. In this paper, I suggest that the integrated fire automation system on based p-type fire control panel should be used, which can detect in real time the signal that occur when whether search-device are broken down or not, and can detect the arisen circumstances information of p-type fire control panel on the fire signal in the far away. The devised systems have designed and embodied the analysis of circumstances information and module that can analyze the circumstances information from the p-type fire control panel and the part of internet access installment which can gather and deliver the circumstances information from the fire prevention facility receiver.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2007.04a
• /
• pp.246-251
• /
• 2007

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.326-327
• /
• 2015

본 논문에서는 화재의 움직임 정보에 기반하여 역동적인 화재를 감지하는 기법을 제안한다. 우선 감시 카메라와 같은 고정형 감시 장치로부터 얻어진 색 정보를 분리하기 쉬운 좌표계로 변환하고 이전에 수집된 데이터들로부터 얻어진 사전 정보로부터 화염 영역을 추출한다. 또한 화염 영역의 가장자리가 움직임이 매우 크다는 사실에 기반하여 광흐름 벡터로 얻어진 시간적 분산값을 이용한 움직임 모델을 생성한다. 화염 영역은 움직임 모델과 결합되며 오탐을 걸러내기 위해 충분한 양의 화재 영역이 중첩될 때 최종적으로 화재를 판별한다. 본 논문에서 제안한 방법은 실험 결과에서 우수한 탐지 능력을 보인다.