• Journal of Multimedia Information System
• /
• v.4 no.2
• /
• pp.79-82
• /
• 2017

Smoke and fire have different shapes and colours. This article suggests a fully connected system which is used two features using Adaboost algorithm for constructing a strong classifier as linear combination. We calculate the local histogram feature by gradient and bin, local binary pattern value, and projection vectors for each cell. According to the histogram magnitude, this paper applied adapted weighting value to improve the recognition rate. To preserve the local region and shape feature which has edge intensity, this paper processed the normalization sequence. For the extracted features, this paper Adaboost algorithm which makes strong classification to classify the objects. Our smoke detection system based on the proposed approach leads to higher detection accuracy than other system.

• Fire Science and Engineering
• /
• v.32 no.5
• /
• pp.15-21
• /
• 2018

This study examined the growth characteristics and carbonization pattern when a fire occurs due to a flammable liquid sprinkled on a vinyl floor. When acetone was sprinkled on a floor, the flame reached its peak in approximately 0.2 s after it was ignited. The lower part of the flame showed a laminar pattern while the upper part showed a turbulent pattern. The pattern showed a turbulent pattern and generated white smoke. The combustion completed floor surface showed carbonization of a dim pore pattern. In the case of benzene, an intense flame was formed in approximately 0.6 s after ignition. The flame length was measured to be approximately 50 mm. When the flame became weak, a significant amount of black smoke was generated due to incomplete combustion. The combustion completed floor surface showed carbonization of a pour pattern and splash pattern. In the case of alcohol, an intense flame was formed in approximately 1.1 s after ignition. In addition, the depth of carbonization was significant where the flammable liquid was collected and a trace of carbonization was observed at the boundary of the flow path of the flammable liquid.

• Journal of the Korean Society of Tobacco Science
• /
• v.29 no.2
• /
• pp.118-124
• /
• 2007

GRLs(Guidance Residue Levels) of agricultural chemicals for tobacco are recommended by the CORESTA Agro-Chemical Advisory Committee guide. In the GRLs list, organochlorine group is one of pesticides commonly used on tobacco cultivation. In this model study, the quantitative correlation in the transfer rate of pesticide residue into tobacco smoke by spiking of organochlorine pesticides to cigarette and pyrolysates were investigated. The spiking concentration referred to the range of GRLs list and the organochlorine pesticides in mainstream smoke were analyzed by GC-MS. For the understanding of the composition variation versus temperature, the behavior of pesticides was investigated by pyrolysis-gas chromatography-mass spectrometry(Py-GC-MS). In this study, the transfer rate of pesticide residue into tobacco smoke at four different spiking concentration and the composition of pyrolysates were analyzed differently. At $10\;{\mu}g/cig$ spiking concentrations, the organochlorine pesticides were transferred into tobacco smoke in $0.02\;{\sim}\;10.19\;%$ each of component and the most of pesticides were pyrolyzed during smoking. It was found that the decomposition compounds from organochlorine pesticides were mainly composed of oxygenated and nitrogenous compounds. This study could estimate that the transfer rate of pesticides into tobacco smoke is very small amount.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.388-396
• /
• 2009

This paper proposes a new fire-smoke detection method by using extracted features from camera images and pattern recognition technique. First, moving regions are detected by analyzing the frame difference between two consecutive images and generate candidate smoke regions by applying smoke color model. A smoke region generally has a few characteristics such as similar color, simple texture and upward motion. From these characteristics, we extract brightness, wavelet high frequency and motion vector as features. Also probability density functions of three features are generated using training data. Probabilistic models of smoke region are then applied to observation nodes of our proposed Dynamic Bayesian Networks (DBN) for considering time continuity. The proposed algorithm was successfully applied to various fire-smoke tasks not only forest smokes but also real-world smokes and showed better detection performance than previous method.

• 한국가시화정보학회:학술대회논문집
• /
• 2005.12a
• /
• pp.50-53
• /
• 2005

The turbulent flow around a sphere was investigated in a streamwise meridian plane using two experimental techniques: smoke-wire flow visualization in wind tunnel at Re=5,300 and PIV measurements in a circulating water channel at Re=7,400. The smoke-wire visualization shows flow separation points near an azimuthal angle of $90^{\circ}$, recirculating flow, transition from laminar to turbulent shear layer, evolving vortex roll-up and fully turbulent eddies in the sphere wake. In addition, the mean flow pattern extracted by particle tracing method in water tunnel at Re= 14,500 reveals two distinct comparable toroidal(not closed) vortices in the recirculation region. The mean velocity field measured using a PIV technique demonstrates the detailed wake configuration of close symmetric recirculation and near-wake configuration with two toroidal vortices, reversed velocity zone and vorticity contours.

• Journal of the Society of Naval Architects of Korea
• /
• v.41 no.5
• /
• pp.63-69
• /
• 2004

This study contains the CFD analysis to predict the flow in engine room and utilize the results as a reference for arranging smoke detectors. FLUENT, a commercial CFD code is adopted because of its good application experience in DSME(Daewoo Shipbuilding & Marine Engineering Co.. Ltd.). The target is the engine room of VLCC. which was delivered in 2002. The model for analysis includes main structure elements, ventilation ducts, main engine and other big size equipment. From the analysis results, the internal flow pattern can be observed and some guidelines for the position of smoke detectors cane be presented.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5522-5536
• /
• 2017

In this paper, a video based smoke detection method using dynamic texture feature extraction with volume local binary patterns is studied. Block based method was used to distinguish smoke frames in high definition videos obtained by experiments firstly. Then we propose a method that directly extracts dynamic texture features based on irregular motion regions to reduce adverse impacts of block size and motion area ratio threshold. Several general volume local binary patterns were used to extract dynamic texture, including LBPTOP, VLBP, CLBPTOP and CVLBP, to study the effect of the number of sample points, frame interval and modes of the operator on smoke detection. Support vector machine was used as the classifier for dynamic texture features. The results show that dynamic texture is a reliable clue for video based smoke detection. It is generally conducive to reducing the false alarm rate by increasing the dimension of the feature vector. However, it does not always contribute to the improvement of the detection rate. Additionally, it is found that the feature computing time is not directly related to the vector dimension in our experiments, which is important for the realization of real-time detection.

• Tunnel and Underground Space
• /
• v.28 no.1
• /
• pp.38-58
• /
• 2018

The ventilation system plays a crucial role in underground mine safety. The main objective of the ventilation system is to supply sufficient air to dilute the contaminated air at working places and consequently provide tenable environment during the normal operation, while it also should be capable of controlling the fire propagation and facilitate rescue conditions in case of fire in mines. In this study, a smoke control fan was developed for the auxiliary ventilation as well as the fire smoke exhaust. It works as a free-standing auxiliary fan without tubing to dilute or exhaust the contaminated air from the working places. At the same time, it can be employed to extract the fire smoke. This paper aims to examine the smoke control efficiency of the fan when combined with the current ventilation system in mines. A series of the site experiments and numerical simulations were made to evaluate the fan performance in blind entry development sites. The tracer gas method with SF6 was applied to investigate the contaminant behavior at the study sites. The results of the site study at a large-opening limestone mine were compared with the CFD analysis results with respect to the airflow pattern and the gas concentration. This study shows that in blind development entry, the most polluted and risky place, the smoke fan can exhaust toxic gases or fire smoke effectively if it is properly combined with an additional common auxiliary fan. The venturi effect for smoke exhaust from the blind entry was also observed by the numerical analysis. The overall smoke control efficiency was found to be dependent on the fan location and operating method.

• 한국가시화정보학회:학술대회논문집
• /
• 2004.11a
• /
• pp.14-17
• /
• 2004

A purpose of this visual experiment is to investigate the effect of reduced frequency qualitatively by examining wake pattern change for insect flying motion. Insect is composed of two pair wing with forewing and hindwing, flying motion of insect is performed pitching and plunging so it makes a separation over the wings. The separation affects at the wake pattern and changed wake pattern has an influence on lift, drag and propulsion. This experiment is conducted by using a smoke wire technique and a camera is fixed at hindwing to take a photograph of wake. An electronic device is mounted below test section to find exact the mean positional angle of wing. The reduced frequency in experiment is 0.15, 0.3 and 0.45. We obtained the result which that reduced frequency is closely related to wake pattern that determines flight efficiency.

• Fire Science and Engineering
• /
• v.33 no.6
• /
• pp.126-131
• /
• 2019

Real-scale fire tests were performed on animal-origin foods using a gas stove with no overheating prevention device. When the animal-origin foods were ignited, a large quantity of white smoke and steam was generated from them; however, when they became dry and began to carbonize, a dark smoke was generated. Even after the gas stove was overheated for more than 5400 s, mackerel, pollack, chicken, etc., did not ignite. However, pork, beef, and tuna caught fire after 2643 s, 2819 s, and 6492 s of heating, respectively. The flame patterns of animal-origin foods were in the forms of a mixed laminar flow and a turbulent flow, and a halo pattern was produced. A sand glass form of the flame pattern was generated when a kitchen hood was operated, but a triangular flame pattern was produced when the kitchen hood was not operated. When the tuna in the pot was overheated, it spontaneously ignited after 6492 s, with the surface temperature of the kitchen hood rapidly rising to 464.5 ℃. Moreover, the temperature at the back of the pot, which was 6 cm away from the outer surface of the upper part of the pot, was 869 ℃ after 6660 s because of the radiant heat. The flame formed a sand glass pattern on the kitchen wall. When the kitchen hood was not operated, or when the flame grew lower than the height of the ceiling, a triangular pattern was formed.