• 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.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.4
• /
• pp.50-58
• /
• 2017

Recently, some methods of converging heterogeneous fire sensor data have been proposed for effective fire detection, but the rule-based methods have low adaptability and accuracy, and the fuzzy inference methods suffer from detection speed and accuracy by lack of consideration for images. In addition, a few image-based deep learning methods were researched, but it was too difficult to rapidly recognize the fire event in absence of cameras or out of scope of a camera in practical situations. In this paper, we propose a novel fire detection system combining a deep learning algorithm based on CNN and fuzzy inference engine based on heterogeneous fire sensor data including temperature, humidity, gas, and smoke density. we show it is possible for the proposed system to rapidly detect fire by utilizing images and to decide fire in a reliable way by utilizing multi-sensor data. Also, we apply distributed computing architecture to fire detection algorithm in order to avoid concentration of computing power on a server and to enhance scalability as a result. Finally, we prove the performance of the system through two experiments by means of NIST's fire dynamics simulator in both cases of an explosively spreading fire and a gradually growing fire.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2015

In this paper, we propose an efficient parallel implementation method of a widely used complex four-stage fire detection algorithm using a graphics processing unit (GPU) to improve the performance of the algorithm and analyze the performance of the parallel implementation method. In addition, we use seven different resolution videos (QVGA, VGA, SVGA, XGA, SXGA+, UXGA, QXGA) as inputs of the four-stage fire detection algorithm. Moreover, we compare the performance of the GPU-based approach with that of the CPU implementation for each different resolution video. Experimental results using five different fire videos with seven different resolutions indicate that the execution time of the proposed GPU implementation outperforms that of the CPU implementation in terms of execution time and takes a 25.11ms per frame for the UXGA resolution video, satisfying real-time processing (30 frames per second, 30fps) of the fire detection algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.8
• /
• pp.1-10
• /
• 2014

This paper proposes a parallel implementation of the video based 4-stage fire detection algorithm using a general-purpose graphics processing unit (GPGPU) to support real-time processing of the high computational algorithm. In addition, this paper compares the performance of the GPGPU based fire detection implementation with that of the CPU implementation to show the effectiveness of the proposed method. Experimental results using five fire included videos with an SXGA ($1400{\times}1050$) resolution, the proposed GPGPU implementation achieves 6.6x better performance that the CPU implementation, showing 30.53ms per frame which satisfies real-time processing (30 frames per second, 30fps) of the fire detection algorithm.

• Fire Science and Engineering
• /
• v.22 no.4
• /
• pp.54-60
• /
• 2008

In this study, damage characteristics of MCCB and terminal block due to poor contact were analyzed, and various poor contact detection techniques were suggested. Firstly, the detection techniques using thermocouple and infrared thermal camera were analyzed respectively. Also, thermo-cap during poor contact detected abnormal status effectively by changing its color, and the detection system using an odor detector and odor capsules was analyzed. Lastly, poor contact detection screw was made using characteristics of fusible alloy, and we applied the poor contact detection screw to terminal block. The above methods could prevent electrical fire caused by poor contact effectively if they are used properly.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.

• Fire Science and Engineering
• /
• v.30 no.2
• /
• pp.27-34
• /
• 2016

This paper studies a fire detection system using an optical fiber linear detector which can minimize damage from a fire by the most adaptable even in poor environmental conditions such as a tunnel or utility-pipe conduit vulnerable to fire. Using a strand of optical fiber, temperature can be displayed in intervals of meters and a fire can be detected remotely from a distance of several kilometers. Thanks to its strengths such as high reliability and long life, it is widely applied in harsh environments in the overseas. Therefore demands are expected to grow greatly in Korea as well. However, all optical signal drive and analysis module except for the optical fiber linear detector, tend to rely on import. Firstly this study deduced the location and the method of processing signals measuring temperature by using the optical fiber linear detector in order to develop a technology for a domestic model of fire detection system. Secondly this study designed and manufactured the optical analysis test module, and then we checked its performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.594-597
• /
• 2010

This paper proposes a fire detection algorithm using low-cost camera to detect visual features of fire. In the previous work sensor cameras were used, but here we use very simple cameras. This method uses YCbCr and YIQ color model to detect candidate regions of fire. The candidate areas are extracted from the boundaries of the fire. noise removal elimination is performed. Regardless of environmental changes around the fire area, the results of the proposed algorithm are very satisfactory.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.4
• /
• pp.479-485
• /
• 2011

A video flame detection method analyze the temporal and spatial characteristics of the regions which have the flame-like color and moving objects in the input video. The video flame detector should be able to reduce a false alarm rate without the degradation of flame detection capability. The conventional methods can reject the false alarm caused by the car lights and some electric lights. However they make the false alarm caused by the warning lights, neon sign, and some periodic flickering lights which have the flame-like color and temporal features. This paper propose the video flame detection method with periodicity analysis based false alarm rejection. The proposed method can detect the periodicity of the flickering electric lights and can reject the false alarm caused by the periodic electric lights. The computer simulation showed that the proposed method did not make the false alarm in the test video with the periodic electric lights. But the conventional methods made a false alarm in the same test video.

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.287-293
• /
• 2014

Early fire detection is very important to avoid loss of lives and material damage. The conventional smoke detector sensors have difficulties in detecting smoke in large outdoor areas. The video-based smoke detection can overcome these drawbacks. This paper proposes a new smoke detection method in video sequences. It uses the ratio of variation rate of subband energy in the wavelet transform domain. In order to reduce the false alarm, candidate smoke blocks are detected by using motion, decrease of chromaticity and the average intensity of block in the YUV color space. Finally, it decides whether the candidate smoke blocks are smokes or not by using their temporal changes of subband energies in the wavelet transform domain. Experimental results show that the proposed method noticeably increases the accuracy of smoke detection and reduces false alarm compared with the conventional smoke detection methods using wavelets.