• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• 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.

• Journal of Satellite, Information and Communications
• /
• v.6 no.2
• /
• pp.41-45
• /
• 2011

This paper presents a fire detection criterion based on flame color, spatial and temporal characteristic analysis of color fire images. To propose the criterion, Firstly the fire candidate regions were selected by using analyzed Cr and Y threshold value, and then texture analysis of candidate regions was performed by using DCT. Finally variation of Y values of these regions was calculated for temporal analysis. The proposed fire detection criterion was simulated by using fifteen test images and practicality was verified.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.4
• /
• 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.

• Proceedings of the Optical Society of Korea Conference
• /
• 2008.07a
• /
• pp.419-420
• /
• 2008

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.9
• /
• 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.

• Journal of the Korean Society of Combustion
• /
• v.20 no.1
• /
• 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.

• Fire Protection Technology
• /
• s.29
• /
• 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.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.159-164
• /
• 2019

Detecting wildfire using only color in image information is a very difficult issue. This paper proposes an algorithm to detect forest fire area by analyzing color and motion of the area in the video including forest fire. The proposed algorithm removes the background region using the Gaussian Mixture based background segmentation algorithm, which does not depend on the lighting conditions. In addition, the RGB channel is changed to an HSV channel to extract flame candidates based on color. The extracted flame candidates judge that it is not a flame if the area moves while labeling and tracking. If the flame candidate areas extracted in this way are in the same position for more than 2 minutes, it is regarded as flame. Experimental results using the implemented algorithm confirmed the validity.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.1
• /
• pp.63-73
• /
• 2021

This paper presents a algorithm for automatic target recognition robust to the influence of the flame in order to track the target by EOTS(Electro-Optical Targeting System) equipped on UAV(Unmanned Aerial Vehicle) when there is aerial target or marine target with flame at the same time. The proposed method converts infrared images of targets and flames into a gradient vector field, and applies each gradient magnitude to a polynomial curve fitting technique to extract polynomial coefficients, and learns them in a shallow neural network model to automatically recognize targets and flames. The performance of the proposed technique was confirmed by utilizing the various infrared image database of the target and flame. Using this algorithm, it can be applied to areas where collision avoidance, forest fire detection, automatic detection and recognition of targets in the air and sea during automatic flight of unmanned aircraft.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• 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.