• 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.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.242-248
• /
• 2019

Fire flame and smoke detection algorithm studies are challenging task in computer vision due to the variety of shapes, rapid spread and colors. The performance of a typical sensor based fire detection system is largely limited by environmental factors (indoor and fire locations). To solve this problem, a deep learning method is applied. Because it extracts the feature of the object using several methods, so that if a similar shape exists in the frame, it can be detected as false postive. This study proposes a new algorithm to reduce false positives by using frame similarity before using deep learning to decrease the false detection rate. Experimental results show that the fire detection performance is maintained and the false positives are reduced by applying the proposed method. It is confirmed that the proposed method has excellent false detection performance.

• Food Science and Preservation
• /
• v.15 no.4
• /
• pp.556-561
• /
• 2008

This study was carried out to identify the cause of benzo(a)pyrene[B(a)P] production during the manufacture of sesame oil and perilla oil, and to minimize such B(a)P synthesis. The distribution of B(a)P in sesame seed and perilla seed differed with seed-growing district, the range was $0.06{\sim}0.31{\mu}g/kg$ in domestic seed and $0.12{\sim}0.47{\mu}g/kg$ in imported seed. B(a)P contents after roasting at $220^{\circ}C$ for 20 min in sesame seed and perilla seed were $1.87{\sim}2.47{\mu}g/kg$ and $2.12{\sim}2.43{\mu}g/kg$, respectively, and levels in oils obtained from the roasted seeds were $3.68{\mu}g/kg$ and $4.64{\mu}g/kg$, respectively. These data refer to seeds subjected to codsed roasting. With open roasting, the levels were $0.63{\mu}g/kg$ and $0.56{\mu}g/kg$, respectively. Closed roasting resulted in absorption of B(a)P, with consequent high levels in oils. We introduced forced ventilation during closed roasting. We tested various methods to remove B(a)P from sesame oil and perilla oil. Neither centrifugation nor filtering with diatomite and diatomiteactive carbon removed B(a)P. A filtering method using active carbon was effective. But this method adversely affected the color and flavor of sesame oil and perilla oil.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.808-810
• /
• 2011

The background estimation algorithms had a significant impact on the performance of image processing and recognition. In this paper, background estimation algorithms were analysis of complexity and performance as preprocessing of image recognition. It was evaluated the performance of Gaussian Running Average, Mixture of Gaussian, and KDE algorithm. The simulation results show that KDE algorithm outperforms compared to the other algorithms.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.111-113
• /
• 2013

엘리베이터 내부에서는 흡연이나 음주 등 사회적으로 폐가되는 행동은 금지되어 있다. 승강기 내에서 흡연을 하는 것은 상도덕에 어긋나는 일이며 자라는 우리 아이들과 여성들에게 매우 치명적일 수 있다. 본 논문에서는 승강기 내에서 흡연을 하는 사람을 추출하여 포렌식 증거 자료로 제출하기 위해서이다. 방법은 흰색 막대를 입에 물거나, 연기를 내품는 사람을 추출하는 것이다. 방법은 장면 전환 검출에서 평균 명암 측정 방법으로 추출한다.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1027-1028
• /
• 2008

In this paper, we proposed image-processing technique for automatic real-time fire and smoke detection in tunnel fire environment. To minimize false detection of fire in tunnel we used motion information of video sequence. And this makes it possible to detect exact position of event in early stage with detection, test, and verification procedures. In addition, by comparing false detection elimination results of each step, we have proved the validity and efficiency of proposed algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.52-54
• /
• 2012

The fact of smoking is prohibited in elevators. Smoking in elevators that contrary to business ethics, and it can be fatal to our children and women. In this paper, people who smoke in elevators is submitted to forensic evidence. Method is to extract the white bar at the mouth, biting people that smoke. color histogram of scene change detection method is extracted.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.11a
• /
• pp.314-317
• /
• 2011

최근 국내 장애인 복합시설의 증가와 함께 많은 사고 사례가 발생하고 있다. 하지만 장애인 시설 화재시 재실자가 장애인으로 비장애인 보다 피난 효율이 저하되어 수 많은 인재가 발생하고 있다. 따라서 장애인시설 피난 방화와 관련하여 강화된 규정이 필요하고 많은 연구가 이루어져야 할 것이다. 이에 따라 국내 장애인복합시설을 대상으로 가연물 조사와 Cone Calorimeter 실험을 통해 화재하중과 가연물 연소성상 등을 연구 분석한 결과 장애인 시설의 화재하중이 공동주택보다 높다는 것을 확인하였다. Cone Calorimeter 실험을 통해서 6개 시료 중 4개의 시료가 기준치 이상의 발열량을 보였고, 방염블라인드의 경우 Co, $CO_2$ 유해연기의 검출량이 기준치 이상으로 그 위험성을 확인 할 수 있었다.

• Korean Journal of Environmental Agriculture
• /
• v.6 no.2
• /
• pp.12-21
• /
• 1987

Residues of some organo-chlorine pesticides on 108 solis collected from 5 sites of Chungnam avea during March 20-April 6, 1986 were investigated. 12 different kinds of Chemical components were detected showing the highest detection frequency with P.P'-DDE(67.6%) and the lowest with Heptachlor(1.8%). 4 different chemicals, ${\alpha}-BHC$, ${\gamma}-chlordane$, P.P'-DDD and P.P'-DDD and P.P'-DDE showed their average contents in the soils of 0.001 ppm and 0.005ppm for ${\beta}-BHC$, respectively. On the other hand, ${\alpha}-BHC$, ${\gamma}-chlordane$, P.P'-DDT. O.P'-DDT and P.P'-DDD showed 0.002ppm for their average contents of residues, respectively.

• Fire Science and Engineering
• /
• v.30 no.4
• /
• pp.1-5
• /
• 2016

This research performed tests of Video Fire Detector and criteria of installation to make suggestions regarding the criteria that must be reflected in NFSC 203 by comparing the standards of FM Approvals, UL, ISO7240 and NFPA 72. FM Standard related to Video Fire Detector test has been classified as Smoke, Flame type, but the UL Standard has classified only as a Smoke type. This research examined 6 cases of fire phenomenon detection case in ISO 7240 and 3 cases in NFPA 72, respectively. There are 15 items required for the installation standard of a Video Fire Detector and each field standard is presented as a per installation method. To apply a Video Fire Detector, the pertinent items (the definition of term, detector's classification, structure and function among its test item) must be inserted. In addition, 7 items of the fire test, i.e., the sensitivity adjustment, prevent false alarm, ambient temperature test, the effective sensitivity and detection distance and viewing angle, aging test, flood test, must be applied to the actual test. For installation in the field, the operation environment and levels of illumination, and NFSC 203 must be set, and standards relevant to the sound system, indicators' installation distance, etc. need to be inserted.