• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.282-285
• /
• 2009

This paper proposes a flame verification algorithm using motion and spatial persistency. Most previous vision-based methods using color information and temporal variations of pixels produce frequent false alarms due to the use of many heuristic features. To solve these problems, we used a Bayesian Networks. In addition, since the shape of flame changes upwards irregularly due to the airflow caused by wind or burning material, we distinct real flame from moving objects by checking the motion orientation and temporal persistency of flame regions to remove the misclassification. As a result, the use of two verification steps and a Bayesian inference improved the detection performance and reduced the missing rate.

• 한국위성정보통신학회논문지
• /
• 제6권2호
• /
• pp.41-45
• /
• 2011

본 논문에서는 컬러 화재영상에 포함된 화염의 색상 분석과 시공간적 특징 분석을 통하여 신뢰성 높은 화재 판정 조건을 제시한다. 이를 위하여 컬러영상에서 화염을 판정하는 컬러속성으로서 Y-휘도 성분과 Cr-색차 성분을 조합한 문턱치를 도출하고 화염 후보영역을 선정하였다. 선정된 화염 후보영역에 대해서는 화염의 공간적인 질감분석과 시간적인 동적변화를 DCT와 프레임간 휘도성분 변화량을 분석하여 최종 화염 판정 기준으로 제시하였다. 컴퓨터 모의실험을 통하여 제시한 화염 판정 조건의 신뢰성과 실용성을 검증하였다.

• 대한기계학회논문집B
• /
• 제26권4호
• /
• pp.561-569
• /
• 2002

This paper presents an investigation on $C_2$, CH, OH radicals and NOx emissions in partially premixed flames with acoustic excitation. The radicals are visualized by the digital image technique with optical filters and ICCD camera while NOx emissions are determined by a chemiluminescent detection(NOx analyser). The measurements are made in flames with an overall equivalence ratio (${\phi}_o$) 0.5 and a center tube equivalence ratio(${\phi}_c$) varing from 1.1 to 5.0 for a constant fuel flow rate. In the case of excitation, the visual shape of the flame is changed from laminar to turbulent-like flames. Images of $C_2$, CH, and OH radicals resemble those of the flame appearances as the excitation phase is varied, and the radicals generated at the upstream are convected toward the downstream. It is inferred that the flame characteristics is affected by the flow characteristics of air-fuel mixture. In the case of acoustic excitation, OH radicals are much increased relative to unexcitation. From the radicals and flame visualization under acoustic excitation, the reduction of flame length affects the shorter residence time of center tube mixture, and significantly influences the NOx reduction.

• 한국광학회:학술대회논문집
• /
• 한국광학회 2008년도 하계학술발표회 논문집
• /
• pp.419-420
• /
• 2008

• 대한기계학회논문집B
• /
• 제28권9호
• /
• pp.1110-1116
• /
• 2004

Experimental measurements of laser-induced ion mobility(LIIM) were performed for ethene/air premixed flames operated near the soot inception point. Soot was ionized using a pulsed laser operated at 532 nm. The ionization signal was collected with a tungsten electrode located in the post-flame region. ionization signals were collected using both a single electrode and dual electrode configuration. Prior LIIM studies have focused on the use of a single biased electrode to generate the electric field, with the burner head serving as the path to ground. In many practical combustion systems, a path to ground is not readily available. To apply the LIIM diagnostic to these geometries, a dual electrode geometry must be employed. The influence of electrode configuration, flame equivalence ratio, and flame height on ionization signal detection was determined. The efficacy of the LIIM diagnostic to detect soot inception in the post-flame region of a premixed flame using a dual electrode configuration was investigated. For the different dual electrode configurations tested, the dual parallel electrode geometry was observed to be most sensitive to detect the soot inception point in a premixed flame.

• 한국연소학회지
• /
• 제20권1호
• /
• pp.24-31
• /
• 2015

Flame structure, which contains a useful information for studying combustion instability of the flame, is often quantitatively visualized with PLIF (planar laser-induced fluorescence) and/or chemiluminescence images. The latter, a line-integral of a flame property, needs to be preprocessed before being inverted, mainly due to its inherent noise and the axisymmetry assumption of the inversion. A preprocessing scheme utilizing multi-division of ROI (region of interest) of the chemiluminescence image is proposed. Its feasibility has been tested with OH PLIF and $OH^*$ chemiluminescence images of SNG (synthetic natural gas) swirl-stabilized flames taken from a model gas turbine combustor. It turns out that the multi-division technique outperforms two conventional ones: those are, one without preprocessing and the other with uni-division preprocessing, reconstructing the SNG flame structure much better than its two counterparts, when compared with the corresponding OH PLIF images. It is also found that the Canny edge detection algorithm used for detecting edges in the multi-division method works better than the Sobel algorithm does.

• 방재기술
• /
• 통권29호
• /
• pp.39-45
• /
• 2000

All objects emit thermal radiation and this radiation is the basis of the techniques used to detect flames. The usual phenomena occurring in the initial stage of a fire are generally invisible products of a combustion and visible smoke. Liquid or gaseous materials do not undergo a smoldering stage such fires develop very rapidly. Also, the heat generated by the initial flames is usually not sufficient to active a heat detector. In this case the most effective criterion for automatic fire detection is the flame. In fire regulation of korea, the compulsory standard provided that a flame detector shall be installed a place of the attachment hight of detector is higher than 20 m, chemical plants, hangar, refinery, etc.. The result of the research and development are discriminated between a flame and other radiant emitters, developed PZT pyroelectric element is based on the use of photo-voltanic cell, developed IR band-pass filter that only allow a 4.3 radiation wavelength to reach the sensors and developed IR flame detector.

• 융합신호처리학회논문지
• /
• 제20권3호
• /
• pp.159-164
• /
• 2019

영상정보에서 색상만을 이용하여 산불을 감지하는 것은 매우 어려운 이슈이다. 본 논문은 산불을 포함하고 있는 동영상에서 영역의 색상과 움직임을 분석하여 산불영역을 감지하는 알고리즘을 제안한다. 제안하는 알고리즘에서는 조명 상태에 의존하지 않고 배경 영역을 추출 가능한 가우시안 믹스쳐 기반의 배경 분할 알고리즘을 이용하여 제거한다. 또한 RGB채널을 HSV채널로 변경하여 색상 기반으로 화염 후보들을 추출한다. 그렇게 추출된 화염후보들은 라벨링 및 트래킹을 하면서 면적이 일정하면서 이동하면 화염이 아니라고 판단한다. 이런 방법으로 추출된 화염후보 영역들이 2분 이상 같은 위치에 있으면 화염으로 판단한다. 구현된 알고리즘을 이용하여 실험한 결과 그 유효성을 확인하였다.

• 한국항공우주학회지
• /
• 제49권1호
• /
• pp.63-73
• /
• 2021

본 논문은 공중 혹은 해상배경에 표적과 화염이 동시에 존재할 때, 무인항공기에 장착된 EOTS(Electro-Optical Targeting System; 전자광학 추적장비)가 표적을 추적하기 위해 화염의 영향에 강건하도록 표적을 자동 인식하는 기법을 제안한다. 제안한 기법은 표적과 화염의 적외선 영상을 Gradient Vector Field로 변환하고, 각 Gradient magnitude를 Polynomial Curve Fitting 도구에 적용하여 다항식 계수를 추출 및 얕은 신경망 모델에 학습함으로써, 표적과 화염을 자동으로 인식한다. 확보한 표적 및 화염의 다양한 적외선 영상 DB를 학습데이터, 검증데이터, 시험데이터로 분류하여 제안한 기법의 표적 및 화염 자동 인식 성능을 확인하였다. 본 알고리듬을 활용하여 무인항공기의 자동비행 중 충돌회피, 산불탐지, 공중 및 해상의 목표물을 자동탐지 및 인식하는 분야에 적용될 수 있다.

• 한국전기전자재료학회논문지
• /
• 제37권3호
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.