• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.1-6
• /
• 2014

Color image processing based on smoke detection is suitable detecting target to early detection of fire smoke. A method for detecting the smoke is processed in the pre-processing movement and color. And Next, characteristics of smoke such as diffusion, texture, shape, and directionality are used to post-processing. In this paper, propose the detection method of density distribution characteristic in characteristics of smoke. the generate a candidate regions by color thresholding image in Detecting the movement of smoke to the 10Frame interval and accumulated while 1second image. then check whether the pattern of the smoke by candidate regions to applying OBTP(Object Block Ternary Pattern). every processing is Block-based processing, moving detection is decided the candidate regions of the moving object by applying an adaptive threshold to frame difference image. The decided candidate region accumulates one second and apply the threshold condition of the smoke color. make the ternary pattern compare the center block value with block value of 16 position in each candidate region of the smoke, and determine the smoke by compare the candidate ternary pattern and smoke ternary pattern.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.2
• /
• pp.155-160
• /
• 2014

In this paper, an algorithm using RGB-depth camera is proposed to detect smoke in interrior. RGB-depth camera, the Kinect provides RGB color image and depth information. The Kinect sensor consists of an infra-red laser emitter, infra-red camera and an RGB camera. A specific pattern of speckles radiated from the laser source is projected onto the scene. This pattern is captured by the infra-red camera and is analyzed to get depth information. The distance of each speckle of the specific pattern is measured and the depth of object is estimated. As the depth of object is highly changed, the depth of object plain can not be determined by the Kinect. The depth of smoke can not be determined too because the density of smoke is changed with constant frequency and intensity of infra-red image is varied between each pixels. In this paper, a smoke detection algorithm using characteristics of the Kinect is proposed. The region that the depth information is not determined sets the candidate region of smoke. If the intensity of the candidate region of color image is larger than a threshold, the region is confirmed as smoke region. As results of simulations, it is shown that the proposed method is effective to detect smoke in interior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• Journal of the Korean Society of Tobacco Science
• /
• v.26 no.2 s.52
• /
• pp.179-185
• /
• 2004

This study was conducted to investigate the delivery pattern of volatile organic compounds(VOCs) in mainstream smoke generated by the combustion of a different ventilated cigarette. To compare the delivery pattern and the concentration of VOCs in mainstream smoke, the six different ventilated cigarette was manufactured and analyzed VOCs using the GC/MS. As a result of this experiments, cambridge filter used to trap the particulate matter in mainstream smoke did not affect on the trapping of VOCs components, and two impinger method among the trapping methods was the best condition to trap VOCs from mainstream smoke. As the slope of the delivery of VOCs such as isoprene, acrylonitrile and toluene were higher than 1, but that of benzene was lower than other VOCs.

• Journal of the Korean Society of Safety
• /
• v.27 no.3
• /
• pp.1-8
• /
• 2012

Characteristics of smoke emission in light duty diesel vehicles was investigated according to the year of production, engine displacement volume, and mileage. The smoke emission was measured using light extinction smoke measurement method under free acceleration test mode. Total number of the tested vehicles was 180. The year of production of the tested vehicles distributed from 2002 to 2007. The displacement volumes of the tested vehicles were categorized as 2-liter, 2.5-liter, 2.7-liter, and 3-liter. The mileage of the tested vehicles distributed from 20,000 km to 400,000 km. The more recent in the year of production of the tested vehicles did not show clearly lower in smoke emissions. Smoke emission showed different values according to driver's pedal pushing pattern. Also, smoke emission peak for each free acceleration test initially increased and reach a maximum of the peak values. Afterwards, the smoke peak gradually decreased as number of test increased. A new guide line was proposed to determine the smoke value from the light duty diesel vehicles based on smoke emission peak patterns which were obtained with several repeated free acceleration tests.

• Journal of ILASS-Korea
• /
• v.18 no.3
• /
• pp.132-139
• /
• 2013

Smoke emissions from light duty diesel vehicles were measured using light extinction method with the free acceleration test mode. The smoke emissions for each measurement cycle of the free acceleration method showed large variations according to driver's pedal pushing pattern. The smoke values for each measurement cycle initially increased and reach a peak value. Integration of the smoke emissions with time for each measurement cycle was performed to get a representative smoke value which was obtained by averaging the integrated results. Two kinds of integration time range were used. One is range over the whole measurement cycle of the free acceleration method. The other is only the acceleration range in the measurement cycle. Overall, variation of the representative smoke values obtained by the integration method was reduced comparing to the traditional representative smoke value which was obtained from a peak smoke value over the measurement cycle. Ten vehicles of the same model with 2.5 liter diesel engines, and seven vehicles of the same model with 2.7 liter diesel engines, were tested using the free acceleration test method.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.456-463
• /
• 1997

Atrium buildings are commonly found in Hong Kong since 1980. Those spaces are usually crowded with people and so fire protection systems have to be installed for providing a safe environment. Smoke control system was identified to be important but no clear design guidelines are available because the smoke filling process was not well-understood. In this paper., Computational Fluid Dynamics(CFD) or fire field model is applied to study the smoke filling pattern in atrium. Two common cases on smoke spreading out from a shop adjacent to the atrium; and with a fire located at the atrium floor itself were considered. Simulations with a modified form of the CFD package TEAM were performed. Application of the predicted results Is illustrated.

• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.69-75
• /
• 2022

Fire-alarm systems are safety equipment that facilitate rapid evacuation and early suppression in case of fire. It is highly desirable that fire-alarm systems have low false-alarm rates and are thus reliable. Until now, researchers have attempted to improve detector performance by applying new technologies such as IoT. To this end, IoT-based fire-detection systems have been developed. However, due to scarcity of large-scale operational data, researchers have barely studied malfunctioning in fire-alarm systems or attempted to reduce false-alarm rates in these systems. In this study, we analyzed false-alarm rates of smoke/temperature detectors and unwanted fire-alarm signal patterns at K institution, where Korea's largest IoT-based fire-detection system operates. After analyzing the fire alarm occurrences at the institution for five years, we inferred that the IoT-based fire-detection system showed lower false-alarm rates compared to the automatic fire-detection equipment. We analyzed the detection pattern by dividing it into two parts: normal operation and unwanted fire alarms. When a specific signal pattern was filtered out, the false-alarm rate was reduced to 66.9% in the smoke detector and to 46.9% in the temperature detector.

• Journal of the Korean Society of Tobacco Science
• /
• v.25 no.2
• /
• pp.144-153
• /
• 2003

This study was carried out to determine the relationship between smoke components and sensory evaluation by changes tobacco leaf blending. Seven different cigarettes were made by adding different types of oriental, reconstituted and expanded tobacco leaves. 62 kinds of smoke components which were 6 of general components, 34 of semi-volatile and volatile components, 9 of acid components, and 13 of phenolic components were analyzed. Eight kinds of sensory item were evaluated and also electronic nose system data was collected. All smoke components and sensory characteristics of mainstream smoke were changed by the different blending. To determine the relationship between smoke components and sensory test, the correlation and regression analysis were carried out by using SPSS statistical program. Tar, pH, and CO showed a high correlation with sensory evaluation item. As tar related to hotness, CO have a high correlation with offensive aroma. Semi-volatile and volatile components of smoke related to sensory characteristics such as aroma, taste, irritation, hotness and smoothness. When propylene, l,3-butadiene, butane, isoprene, and 2-methylfuran showed a high correlation with aroma; methyl chloride, methanol, toluene, ethyl benzene showed a high correlation with irritation. Some acidic components and phenolic components of smoke also had a high relation to smoke volume. Especially the acidic components such as 2-furoic acid, 2-hydroxybutyric acid, phenylacetic acid and palmitic acid; the phenolic components such as 4-vinyl phenol, pyrocatechol, 3-methyl catechol, hydroquinone showed a high correlation with smoke volume. As using regression analysis, it was possible to estimate the results of sensory evaluation from the smoke analysis data. From the results of electronic nose system analysis, we can find the different pattern by adding expanded tobacco leaf.