• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.516-521
• /
• 2010

In this paper, we propose a video-based intelligent unmanned fire surveillance system using fuzzy color models. In general, to detect heat or smoke, a separate device is required for a fire surveillance system, this system, however, can be implemented by using widely used CCTV, which does not need separate devices and extra cost. The systems called video-based fire surveillance systems use mainly a method extracting smoke or flame from an input image only. The smoke is difficult to extract at night because of its gray-scale color, and the flame color depends on the temperature, the inflammable, the size of flame, etc, which makes it hard to extract the flame region from the input image. This paper deals with a intelligent fire surveillance system which is robust against the variation of the flame color, especially at night. The proposed system extracts the moving object from the input image, makes a decision whether the object is the flame or not by means of the color obtained by fuzzy color model and the shape obtained by histogram, and issues a fire alarm when the flame is spread. Finally, we verify the efficiency of the proposed system through the experiment of the controlled real fire.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.607-614
• /
• 2016

In this paper, we propose an intelligent fire learning and detection system using convolutional neural networks (CNN). Through the convolutional layer of the CNN, various features of flame and smoke images are automatically extracted, and these extracted features are learned to classify them into flame or smoke or no fire. In order to detect fire in the image, candidate fire regions are first extracted from the image and extracted candidate regions are passed through CNN. Experimental results on various image shows that our system has better performances over previous work.

• Biomedical Science Letters
• /
• v.12 no.3
• /
• pp.281-287
• /
• 2006

Cigarette smoke causes atypical structure of pulmonary and oxidative damage. Therefore, we carried out to determine if exposure to cigarette smoke alters pulmonary structure and anti-oxidant related enzyme in a animal model, when natural product extracts using by Nebulizer. The rat were divided into four groups: $H_2O-treated$ (Control), natural product (Camellia sinensis) extracts-treated (CS), natural product extracts-treated with cigarette smoke-exposed (CS+SM) and cigarette smoke-expose (SM). All groups are similar to Control group in weight, but SM group is lower than the other groups. Microscopic image of the pulmonary structure in SM group showed deleterious alterations in the morphology, but the other groups are maintained in normal structure. In anti-oxidant related enzymes, SOD (superoxide dismutase) and catalase, SM group represents the lowest enzyme activity among all groups. But G6PD (glucose-6-phosphate dehydrogenase) and LPO (lipid peroxidation) is SM group represents the highest enzyme activity among all groups. These result indicate that the natural product extracts is an efficient tissue protective substance against smoke-induced lung injury.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1596-1603
• /
• 2018

Rapidly detecting and warning of fires is necessary for minimizing human injury and property damage. Generally, when fires occur, both the smoke and the flames are generated, so fire detection systems need to detect both the smoke and the flames. However, most fire detection systems only detect flames or smoke and have the disadvantage of slower processing speed due to additional preprocessing task. In this paper, we implemented a fire detection system which predicts the flames and the smoke at the same time by constructing a CNN model that supports multi-labeled classification. Also, the system can monitor the fire status in real time by using Grad-CAM which visualizes the position of classes based on the characteristics of CNN. Also, we tested our proposed system with 13 fire videos and got an average accuracy of 98.73% and 95.77% respectively for the flames and the smoke.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.12
• /
• pp.947-954
• /
• 2017

In case of a fire in urban large structures such as super high-rise buildings, evacuation guidance must be provided to the occupants in order to minimize human deaths and injuries. Therefore, it is essential to provide emergency evacuation guidance when a major fire occurs. In order to effectively support evacuation guidance, it is important to identify major items such as fire location, occupant position, escape route, etc. Also, it is important to quickly identify evacuation areas where residents can safely evacuate from a fire. In this paper, we analyze the CCTV video and propose a method of measuring visibility of the evacuation zone from the smoke caused by the fire in order to determine the safety of evacuation area. To do this, we first extract the background video from the smoke video to measure the visibility of the specific area due to smoke. After generating an edge-extracted image for the extracted background video, the degree of visibility is measured by calculating the change in the edge strength due to smoke.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.3
• /
• pp.1003-1010
• /
• 2012

Background: This study examined the influence of body mass index (BMI), subjective body perception (SBP), and the differences between BMI and SBP influence on smoking among women. Methods: This study used the Korea National Health and Nutrition Examination Survey IV-2, 3 2008-2009. A urinary cotinine test was administered to 5485 women at least 19 years of age. Individuals whose cotinine level was at least 50 ng/mL were categorized as smokers. A multiple logistic regression analysis was performed to estimate the extent to which body-related variables affect female smoking. Results: Women with a lower BMI who perceived themselves to be normal or very fat were 2.09 times (1.14-3.83) more likely to smoke than women with a normal BMI and SBP. Women who were never married with a low BMI and thin SBP were 3.11 times (1.47-6.55) more likely to smoke than women with a normal BMI and SBP. Married women with a high BMI who considered themselves very fat were 0.63 times (0.43-0.94) less likely to smoke than women with a normal BMI and SBP. In contrast, divorced and widowed women with a low or normal BMI who considered themselves very fat were 26.1 times (1.35-507.3) more likely to smoke. Conclusions: Discrepancies between the objective physical condition (BMI) and the subjective body image (SBP) influence the female smoking rate. To reduce the number of female smokers, public education on the association between smoking behavior and weight issues is needed, especially among women with low BMI and distorted weight perception.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.411-414
• /
• 2009

Many victims and property damages are caused in fires every year. In this paper, intelligent fire-detection systems with embedded fire-detection algorithms for early fire detection and alarm is proposed to reduce fire damages by using image processing technique, high speed digital signal processor(DSP) technique, and information technique. The fire detection algorithms used for the proposed systems consist of flame and smoke detection algorithms. If flame or smoke is detected respectively, the corresponding alarm signal can be transferred to management computer. And if flame and smoke is detected simultaneously, the fire alarm signal shall be generated. Through several experiments in the physical environment, it is shown that the proposed system works well without malfunction.