• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.

• Journal of Korean Society for Atmospheric Environment
• /
• v.20 no.6
• /
• pp.715-727
• /
• 2004

This study was carried out to evaluate non-smoker's exposure levels to environmental tobacco smoke (ETS) in the air of offices in urban areas. A total of 65 offices were selected from two large cities, i.e. Daegu and Daejeon. The field sampling was conducted repeatedly in summer (1999) and winter (1999～2000). The measured ETS markers included respirable suspended particles (RSP as PM$_{40}$ ), vapor and particulate phase ETS markers, including nicotine, 3-ethnyl pyridine (3-EP), ultraviolet absorbing particulate matter (UVPM), fluorescing particulate matter (FPM), and solanseol in ETS particles (SolPM). RSP was measured gravimetrically by a microbalance. The particle samples were then used for the determination of particulate ETS markers by HPLC, while vapor phase markers determined by GC/NPD. The analytical methods were validated for repeatability, linearity, detection limits, and duplication precision. The concentrations of RSP and other ETS markers were significantly higher in smoking offices than non-smoking offices. Despite the similar smoking strength in each office for different seasons, the concentration levels of ETS components appeared to be higher in winter than summer. The contributions of ETS to RSP concentrations based on SolPM, FPM, and UVPM methods were estimated to be in the range of 15.2 ～ 25.3% in smoking offices, whereas 2.4 ～ 15.9% in non-smoking offices. The cooling and heating types did not affect significantly the concentrations of RSP and other ETS markers. Finally, further research issues were suggested to obtain more scientific information on the non-smoker's exposure to ETS with respect to the frame of risk assessment..

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.516-521
• /
• 2010

In this paper, we propose a video-based intelligent unmanned fire surveillance system using fuzzy color models. In general, to detect heat or smoke, a separate device is required for a fire surveillance system, this system, however, can be implemented by using widely used CCTV, which does not need separate devices and extra cost. The systems called video-based fire surveillance systems use mainly a method extracting smoke or flame from an input image only. The smoke is difficult to extract at night because of its gray-scale color, and the flame color depends on the temperature, the inflammable, the size of flame, etc, which makes it hard to extract the flame region from the input image. This paper deals with a intelligent fire surveillance system which is robust against the variation of the flame color, especially at night. The proposed system extracts the moving object from the input image, makes a decision whether the object is the flame or not by means of the color obtained by fuzzy color model and the shape obtained by histogram, and issues a fire alarm when the flame is spread. Finally, we verify the efficiency of the proposed system through the experiment of the controlled real fire.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2013.04a
• /
• pp.150-151
• /
• 2013

화재감지기는 연기감지기는 이온전류의 변화량을 감지하는 이온화식 연기감지기와 발광부와 수광부로 이루어진 챔버내에 연기에 의한 광량의 변화를 감지하는 광전식 연기감지기로 구분된다. 국내에서는 광전식 연기감지기가 더 많이 사용되고 있는데 이러한 광전식 연기감지기의 챔버내에 이물질이 침입하게 되면 비화재보를 발생시키게 된다. 본 논문은 연기감지기의 연기감지 챔버에 대한 비화재보를 감소시키기 위한 신뢰성 시험에 대하여 논한 연구이다. 본 연구에서는 광전식 연기감지기의 신뢰성을 검증하는 방법으로 UL 268 등에 규정되어 있는 먼지, 즉, 분진에 대한 신뢰성을 검증방법을 제시하였다. 먼지에 대한 신뢰성 검증을 보다 적절하게 하기 위하여 분진챔버로 분진을 반복적으로 폭로됨에 따른 감도성능 변화를 분석하는 방법이 필요할 것으로 사료된다.

• Fire Science and Engineering
• /
• v.18 no.4
• /
• pp.78-85
• /
• 2004

This research analyzes Clean Room accidents, and presents research Clean Room, major fire prevention standards of Clean Room (FM, IRI, and NFPA Code), various results from Fire Simulation of analysis. The results are : the smoke diffusion is very quick coupled with the Heating, Ventilating, and Air Conditioning (HVAC) systems under fire ; the possibility of getting the result and the possibility the role of the Sprinkler systems to reduce the diffusion of the smoke. We learn about the importance to stop operating Heating, Ventilating, and Air Conditioning (HVAC) systems and to operate the Sprinkler system for securing safety with fire detection. Therefore, This research will be contributing to secure safety of Clean Room.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.119-121
• /
• 2013

The fact of smoking is prohibited in elevators. Smoking in elevators that contrary to business ethics, and it can be fatal to our children and women. In this paper, people who smoke in elevators is submitted to forensic evidence. Method is to extract the white bar at the mouth, biting people that smoke. ${\chi}^2$ histogram of scene change detection method is extracted.

• Fire Science and Engineering
• /
• v.24 no.2
• /
• pp.178-184
• /
• 2010

In this study, a smoke or a heat which occurs by a fire is perceived by wireless detector, this signal is transmitted to the receiving device by the wireless installation which is not the wire device and wire/wireless integration system which sends this signal to main server via wire system is proposed. In addition wireless heat/smoke detector, wireless module, firmware and wire/wireless integration controller were developed and for verifying regarding the efficiency and applicability of wire/wireless installation actual place application experiment was really accomplished with a transmission tower, a multipurpose building, and a station etc of the subway. The experimental result, it could operate the system which is proposed normally with all experimental object ones and, future actual place application possibility could verify.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.617-623
• /
• 2023

Among the fire incidents in Korea over the past decade, building fires are the most common, and property and human casualties are the most common. However, the existing fire fighting system does not only inform the location of emergency exits and guide safe routes to help casualties evacuate smoothly. A system was proposed to help successful evacuation by distinguishing vertical and horizontal characteristics using spatial characteristics. In this study, an effective evacuation system was proposed by predicting fires using temperature detection sensors and smoke sensor values, and calculating the optimal evacuation path through the Dijkstra algorithm.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1325-1334
• /
• 2016

The video incident detection System is a probe for rapid detecting the walker, falling, stopped, backwards, smoke situation in tunnel. Recently, the importance is increases from the downtown double deck tunnel in great depth underground space[1], but the legal basis is weak and the vulnerable situation experimental data. So, In this paper, we introduce a long-term log data analysis information in the tunnenl video incident detection system installed and experimental results in order to verify the feasibility of apply to video incident detection system for the double deck tunnel. It is proposed a few things about derives the problem of existing video incident detection system, improvements and reflect attributes for double deck tunnel. The contents described in this paper will contribute to refine the prototype of video incident detection system will apply to future double deck multi-layer tunnels.