• 한국지능시스템학회논문지
• /
• 제20권4호
• /
• pp.516-521
• /
• 2010

본 논문은 퍼지 칼라모델을 이용한 영상기반의 지능형 무인 화재감시 시스템을 제안한다. 일반적으로 화재 감시를 위해 열이나 연기를 감지하는 별도의 장치를 사용하지만, 널리 보급된 폐쇄회로를 이용하면 별도의 장치와 추가적인 비용 없이 화재를 감시할 수 있다. 이와 같이 영상만으로 화재를 감시하는 시스템은 주로 연기나 불꽃을 추출하는 방법을 사용한다. 그러나 연기검출 방식은 야간에 회색계열의 연기를 검출하기 곤란하고, 불꽃검출 방식은 온도, 인화물질, 화재규모 등에 따른 불꽃색상의 변화에 대응하지 못하는 문제점을 가지고 있다. 본 논문은 무인환경 특히 야간 및 다양한 불꽃색상의 변화에 대응할 수 있는 강인한 화재감시 시스템을 다룬다. 이를 위해 폐쇄회로의 입력영상으로부터 움직임 영역을 추출하고, 퍼지 칼라모델을 이용한 색상과 히스토그램을 이용한 모양을 통해 불꽃 여부을 판단하고, 이것의 확산이 확인될 경우, 화재경보를 발령하는 시스템을 구현한다. 마지막으로, 통제된 실제 화재 실험을 통해 제안하는 방법의 유효성을 검증한다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 추계학술대회 논문집
• /
• pp.1970-1976
• /
• 2008

Since Daegu subway station fire killed 192 citizens in 2003, the demands about safety MRT operation has been increased. Also, the studies and patents for MRT Surveillance are increasing. The related law and system are improving, too. This study suggests the solution for digital surveillance system that has the functions for restricted zone surveillance, the harmful gas and fire surveillance and abnormal behavior surveillance by comparing and analyzing the surveillance systems of advanced countries (United states, Hongkong, Japan etc). Then, we suggest UMS(Unified Message Service) system and image storing system for effective report and management.

• 센서학회지
• /
• 제25권6호
• /
• pp.394-398
• /
• 2016

In this paper, a fire detection system based on quantitative risk estimation is presented. Multiple sensors are used to build a comprehensive indicator that represents the risk of fire quantitatively. The proposed fire risk estimation method consists of two stages which determines the occurrence of fire and estimates the toxicity of the surveillance area. In the first stage, fire is reliably detected under diverse fire scenarios. The risk of fire is estimated in the second stage. Applying Purser's Fractional Effective Dose (FED) model which quantitates harmfulness of toxic gases, the risk of the surveillance area and evacuation time are calculated. A fire experiment conducted using four different types of combustion materials for the verification of the system resulted in a maximum error rate of 12.5%. By using FED calculation and risk estimation methods, the proposed system can detect various signs of fire faster than conventional systems.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1550-1555
• /
• 2011

This paper presents the system interface standard that are associated with additional devices like sensor nodes as well as fire monitoring panel, panic button and emergency call in city railroad environment. Existing fire monitoring panel, panic button and emergency call system is responsible for fire detection and alarm, emergency alarm and communication with the manager. Recently, researches that are associated with NVR-based intelligent integrated surveillance systems and existing alarm system are activated but most of the system is dedicated to it existing. In order to expand devices that is supported other monitoring function, separate device configuration or modification of integrated surveillance system are inevitable. In this study, interface standard between standard controller, integrated command center and each device that facilitate additional expansion of integrated surveillance system and avoid the extra cost is presented.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1275-1281
• /
• 2011

This paper presents synthetic circumstantial judgement system that detects and predicts a fire in subway station. Unlike conventional fire surveillance systems that judge the fire or not through smoke, CO, temperature or variation of temperature, a proposed system discovers a fire more easily or gives the alarm high possibility of fire to operator through recognition of fire levels based on Fuzzy Inference System using by FCM and information of objects from video data.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집
• /
• pp.1984-1988
• /
• 2009

MRT has various surveillance systems for passenger's safety and facility protection which are consisted of fire detection, trespasser observation and so on. However, these systems are not closely related each other because it is designed just for its own purpose, so it could be make wrong decision to surveillance system without important information to determine an accident or disaster. For more accurate event detection, surveillance system needs total situation-aware method using complementary data. This study introduces context-aware system for complex and accurate event detection. Therefore, we apply context-aware system to MRT surveillance system, selecting context-aware parameters and appling them to it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권10호
• /
• 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.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1027-1028
• /
• 2008

Most of the urban transit operation company in Korea have a passive surveillance system to monitor the status of the passengers and facilities in the urban transit service area. The surveillance system is based on CCTV, closed circuit television, and several sensors, such as a fire sensor. However, this system has some limitations to prevent and cope with the emergency quickly. So the urban transit operation companies have plans to be change their surveillance system to be active. The active surveillance system has an intelligent function to detect the event predefined by managers automatically. To construct the active surveillance system, there are a standard concept design and a function analysis. In this paper, we propose the classification of the functions of the active surveillance system for urban transit. We divide the functions into five parts, ordinary monitoring, safety monitoring, environment monitoring, administration support, and record management. And we describe the systems related to the every functions to clarify the classified functions.

• 한국항행학회논문지
• /
• 제13권6호
• /
• pp.1011-1016
• /
• 2009

본 논문에서는 공공장소에 광범위하게 설치되어있는 CCTV의 감시 기능을 활용하여 화재 발생 감지 방법을 제안하였다. 제안한 방법은 고정된 카메라로부터 칼라 정보를 이용하여 비디오 시퀀스의 화재 프레임 후보를 찾아내고, 공간 기법을 기반으로 감지된 화재 정보의 전경 색상을 분석하였다. 실험 결과, 비디오 시컨스에서 시 공간적 화재 후보 정보들이 급격히 변화할 때, 화재 감지의 성능이 우수함을 확인할 수 있었다.

• 한국항행학회논문지
• /
• 제15권3호
• /
• pp.471-477
• /
• 2011

CCTV 카메라는 비디오 감시분야나 화재검출 시스템 등에 다양하게 응용되는 바, 본 논문에서는 고정된 카메라에서 영상 정보를 취득하여 비디오 시컨스를 분석한 후 화재정보를 검출하는 방법을 제안하였다. 연속영상의 배경과 화재정보를 공간적으로 검출하고, 시공간적으로 편차가 급격하게 나타나면 화재 발생 인자로 결정하여 실험을 수행하였다.