• International Journal of Advanced Culture Technology
• /
• 제11권1호
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.

• 한국화재소방학회논문지
• /
• 제22권1호
• /
• pp.76-83
• /
• 2008

지하철 화재사고 경우 정확한 화재 유형 파악과 그에 따른 적절한 초기대응은 사고피해를 최소화하기 위한 중요한 사항이다. 그러나 지하철 화재사고 발생 시 기관사 또는 비상대응직원이 직접 목격하지 않으면 화재 유형을 즉시 파악하기란 불가능하다. 본 연구에서는 화재사고로 나타날 수 있는 오감(五感) 유형을 분석하여 오감 정보를 통해 신속한 화재사고 정보를 전달할 수 있도록 오감 유형을 제안하였다. 또한, 화재 시나리오에 따른 비상대응을 Activity-Action Diagram(AAD)로 정의하여 비상대응을 시스템화 하기 위한 기반을 제시하였다.

• 한국화재소방학회논문지
• /
• 제10권1호
• /
• pp.25-43
• /
• 1996

This paper has been studied about promotion system for fire assessment. Mainly system carried out for BCJ (Building Center of Japan) and JFSC (Japan Fire Safety Center) fire risk assessment system. Much of the work of fire science and fire protection engineering is now explicitly designed to fill gaps or improve accuracy or flexibility In some comprehensive fire hazard or fire risk models.

• 센서학회지
• /
• 제33권3호
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• 한국BIM학회 논문집
• /
• 제13권2호
• /
• pp.37-46
• /
• 2023

The main objective of this study is to propose a method to enhance building safety using the Industry Foundation Classes (IFC) schema in Building Information Modeling (BIM). To achieve this goal, a fire object relationship diagram is created by using the Model View Definition (MVD) and Property Set (Pset) methodology, as well as the Work Breakdown Structure (WBS) based object relationship analysis. The proposed method illustrates how to represent objects and tasks related to fire prevention and human safety during a building fire, including variables that are relevant to these aspects. Furthermore, the proposed method offers the advantage of considering both the IFC object hierarchy and the project work hierarchy when creating new objects, thereby expanding the attribute information for fire safety and maintenance. However, upon confirmation via an IFC viewer after development, a problem with the accuracy of mapping between attributes and objects arises due to the issue of proxy representation of related object information and newly added object information in standard IFC. Therefore, in future research, a mapping method for fire safety objects will be developed to ensure accurate representation, and the scope of utilization of the fire safety object diagram will be expanded. Furthermore, efforts will be made to enhance the accuracy of object and task representation. This research is expected to contribute significantly to the technological development of building safety and fire facility design in the future.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.468-474
• /
• 2022

본 논문에서는 딥러닝을 이용하여 실시간 화재경보 시스템을 구현하는 방법을 제안한다. 화재경보를 위한 딥러닝 학습 이미지 데이터셋은 인터넷을 통하여 1500장을 취득하였다. 일상적인 환경에서 취득된 다양한 이미지를 그대로 학습하게 되면 학습 정확도가 높지 않은 단점이 있다. 본 논문에서는 학습 정확도 향상을 위해 화재 이미지 데이터 확장 방법을 제안한다. 데이터증강 방법은 밝기 조절, 블러링, 불꽃사진 합성을 이용해 학습 데이터 600장을 추가해 총 2100장을 학습했다. 불꽃 이미지 합성방법을 이용하여 확장된 데이터는 정확도 향상에 큰 영향을 주었다. 실시간 화재탐지 시스템은 영상 데이터에 딥러닝을 적용하여 화재를 탐지하고 사용자에게 알림을 전송하는 시스템이다. Edge AI시스템에 적합한 YOLO V4 TINY 모델을 custom 학습한 모델을 이용해 실시간으로 영상을 분석해 화재를 탐지하고 그 결과를 사용자에게 알리는 웹을 개발하였다. 제안한 데이터를 사용하였을 때 기존 방법에 비하여 약 10%의 정확도 향상을 얻을 수 있다.

• 한국항행학회논문지
• /
• 제27권5호
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• 방재기술
• /
• 통권16호
• /
• pp.20-23
• /
• 1994

This article investigates the different numerical methods, which are widely used for purpose of simulating a fire compartment the particular numerical methods such as finite difference, finite element, control Volume, and finite analysis are discribed in order to understand basic concepts and their applications. The fire simulations using fferent methods for the different physical geometrics have been reported in many recent literatures The convergence rate, the accuracy, and the stability are no simply dependent upon the specific method, The study of popular nu-merical methods by being compared among those is therefore significant to understand the nu-merical simulation of fire compartment.

• 한국화재소방학회논문지
• /
• 제28권3호
• /
• pp.20-28
• /
• 2014

대향류 메탄/공기 확산화염에서 복사모델이 소화한계에 미치는 영향이 수치적으로 검토되었으며, 수치결과의 검증을 위하여 기초실험이 병행되었다. 소화약제로는 $N_2$와 $CO_2$가 고려되었으며, 다른 정확도를 갖는 복사모델 OTM과 SNB에 따른 소화농도의 차이가 검토되었다. 주요 결과로서, $N_2$가 첨가된 경우, 복사모델의 정확도에 따라 소화농도의 큰 차이가 발생되지 않는다. 그러나 강한 복사효과를 갖는 $CO_2$가 낮은 신장율의 화염에 첨가되었을 때, SNB와 같은 예측 정확도가 높은 복사모델이 고려되어야 한다. 특히 연료에 첨가된 $CO_2$의 경우 복사모델 SNB와 OTM에 의한 소화농도는 차이를 갖게 된다. 따라서 소화농도 예측을 위해서는 수치해의 정확도와 계산시간을 고려한 합리적인 복사모델의 선택이 필수적이라 할 수 있다.