• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.597-598
• /
• 2013

A lot of fire and crime accidents are caused to a significant national loss. For example, the network and power facilities in national industry facilities, the fire risk region in large scale factories such as nuclear and thermal power plants, large-sized buildings, cultural properties, metal and steel mills, chemical plants, oil refineries. The development of a fire detection system that can detects the temperature and movement of objects as high-level quality is essential to prevent these incidents and accidents fundamentally. In this paper, the fire detection system based on infrared thermal imaging & CCD camera id designed to solve these problems.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.202-203
• /
• 2023

최근 화재 탐지 분야는 불꽃 연기의 특징과 인공지능 인식(Detection) 모델을 활용하여 탐지율을 높이려는 연구가 많이 진행되어 왔다. 기존 화재 탐지 정확도를 높이기 위한 모델 연구 이외에도 불꽃·연기의 특징을 다양한 방법으로 데이터 가공한 학습 데이터셋을 활용하는 연구들이 진행되고 있다. 본 논문에서는 화재 탐지시 불꽃/연기의 오탐지율이 높은 것을 확인하고 오탐지율을 낮추기 위해 화재 상황을 인식하여 분류하는 방법과 데이터셋을 제안한다. 제안한 모델은 동영상을 학습데이터로 활용하여 화재 상황의 특징을 추출하여 분류모델에 적용하였다. 평가는 한국정보화진흥원(NIA)에서 진행하는 화재 데이터셋을 이용하여 Yolov8, Slowfast의 모델 성능을 비교 및 분석하였다.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.695-706
• /
• 2022

Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.411-414
• /
• 2009

Many victims and property damages are caused in fires every year. In this paper, intelligent fire-detection systems with embedded fire-detection algorithms for early fire detection and alarm is proposed to reduce fire damages by using image processing technique, high speed digital signal processor(DSP) technique, and information technique. The fire detection algorithms used for the proposed systems consist of flame and smoke detection algorithms. If flame or smoke is detected respectively, the corresponding alarm signal can be transferred to management computer. And if flame and smoke is detected simultaneously, the fire alarm signal shall be generated. Through several experiments in the physical environment, it is shown that the proposed system works well without malfunction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.12
• /
• pp.6089-6097
• /
• 2012

This study suggested a method of detecting an incident inside tunnel by using camera that is installed within the tunnel. As for the proposed incident detection method, a static object, travel except vehicles, smoke, and contra-flow were detected by extracting the moving object through using the real-time background image differencing after receiving image from the camera, which is installed inside the tunnel. To detect the moving object within the tunnel, the positive background image was created by using the moving information of the object. The incident detection method was developed, which is strong in a change of lighting that occurs within the tunnel, and in influence of the external lighting that occurs in the entrance and exit of the tunnel. To examine the efficiency of the suggested method, the experimental images were acquired from Marae tunnel and Expo tunnel in Yeosu of Jeonnam and from Unam tunnel in Imsil of Jeonbuk. Number of images, which were used in experiment, included 20 cases for static object, 20 cases for travel except vehicles, 4 cases for smoke, and 10 cases for contra-flow. As for the detection rate, all of the static object, the travel except vehicles, and the contra-flow were detected in the experimental image. In case of smoke, 3 cases were detected. Thus, excellent performance could be confirmed. The proposed method is now under operation in Marae tunnel and Expo tunnel in Yeosu of Jeonnam and in Unam tunnel in Imsil of Jeonbuk. To examine accurate efficiency, the evaluation of performance is considered to be likely to be needed after acquiring the incident videos, which actually occur within tunnel.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.4
• /
• pp.7-18
• /
• 2008

To realistically produce fluids such as smoke for the visual effects in the films or animations, we need two main processes: a physics-based modeling of smoke and a rendering of smoke simulation data, based on light transport theory. In the computer graphics community, the physics-based fluids simulation is generally adopted for smoke modeling. Recently, the interest of the particle-based Lagrangian simulation methods is increasing due to the advantages at simulation time, instead of the grid-based Eulerian simulation methods which was widely used. As a result, because the smoke rendering technique depends heavily on the modeling method, the research for rendering of the particle-based smoke data still remains challenging while the research for rendering of the grid-based smoke data is actively in progress. This paper focuses on realistic rendering technique for the smoke particles produced by Lagrangian simulation method. This paper introduces a technique which is called particle map, that is the expansion and modification of photon mapping technique for the particle data. And then, this paper suggests the novel particle map technique and shows the differences and improvements, compared to previous work. In addition, this paper presents irradiance map technique which is the pre-calculation of the multiple scattering term in the volume rendering equation to enhance efficiency at rendering time.

• 한국HCI학회:학술대회논문집
• /
• 2007.02b
• /
• pp.484-488
• /
• 2007

연극이라는 것은 복합적인 표현예술장르로 하나의 요소가 아닌 여러 가지의 요소들아 합쳐져 연극이라는 예술작품을 만들게 되어 있다. 현대의 연극공연에서 영상의 비중은 날로 높아지고 있다. 무대 공간의 공간감, 협소함, 표현의 제약 등을 따져 볼 때 그것은 당연한 이유일지도 모른다. 연극이라는 것은 최종적으로 배우와 관객과 함께 호흡할 때 완성되는 것으로 배우의 연기에 따라 영상도 실시간으로 반응할 수 있어야한다. 이러기 위해서는 영상뿐만 아니라 배우와 인터렉션할 수 있는 영상의 제어 또한 상당부분 생각하지 않을 수 없다. 그리고 무대의 뜨거운 조명과 그 아래의 영상은 같은 빛으로 만들어진 작품이기 때문에 빛이라는 환경적 요인에서 벋어나지 못한다. 그 밖의 스크린의 존재와 무대의 조형물과의 조화 등도 생각해야 한다. 하지만, 연극의 성공은 관객의 몰입정도에 따라 결정된다. 몰입요소는 음악, 배우, 무대 등의 기존 연극요소가 있으며 여기에 영상 활용은 관객을 더욱 연극으로 몰입시킬 수 있는 또 다른 중요 표현방법이 된다. 그 영상의 활용방안과 문제점은 현재 여러 기술과 방법으로 해결되어지고 있으며, 연극에서 사용되는 영상은 더욱 발전 가능성과 활용 가치를 가지고 있다. 본 논문 이러한 대중문화인 연극에서 공간에서의 영상 미디어 활용의 중요성과 관객의 몰입에 관한 발전 가능성에 대한 연구이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.350-352
• /
• 2013

야외에서 촬영된 영상은 안개나 연무 등에 의한 화질 저하가 나타난다. 이를 해결하기 위하여 안개제거를 위한 여러 장의 영상, 추가정보를 이용하는 안개제거 방법과 한 장의 영상을 이용한 안개제거 방법들이 제안되어왔다. 본 논문에서는 한 장의 영상에서 안개나 연기를 제거하여 가시성이 향상된 영상을 제공하는 방법을 제안한다. 이를 위하여 본 논문에서는 안개영상 모델에 대한 2차원 방정식 풀이를 통해 원 영상에 안개가 어느 정도의 비율로 섞여있는지를 나타내는 전달률(transmission rate)을 계산하고, 계산된 전달률을 이용하여 안개가 제거된 영상을 구한다. 제안된 방식은 기존 방법들과 달리 필터를 사용하지 않고 화소단위의 연산만을 사용하므로 후광효과가 발생하지 않고, 연산량이 매우 적어 실시간 처리가 가능하다.