• Journal of Korea Multimedia Society
• /
• v.15 no.2
• /
• pp.258-265
• /
• 2012

Our country is suffering from many human victims and property damages caused to occur great and small tidal waves in southern areas every year. Even though there were progressing many researches for storm surges, it was required more researches for detection of tidal wave and prevention system of its which can be applied in practical living fields. In this paper, we propose the disaster prevention system that can approximately detect a dangerousness of coast flooding and number of overtopping per time based on images of CCTV considering actual field application. And if it is detected a hazard of flooding of coast, the proposed detection system for tidal wave based GIS is quickly informed the areas of flooding to manager. The analyzing results of CCTV image of this proposed are derived from difference images between photos of fine day and photos or videos which are taken for the typhoon which is called "DIANMU" at our laboratory.

• The Journal of the Korea Contents Association
• /
• v.12 no.3
• /
• pp.9-16
• /
• 2012

The research of vehicle license plate recognition has been widely studied for the smart city project. The license plate recognition can be hard due to the geometric distortion and the image quality degradation in case of capturing the driving car image at CCTV without trigger signal on the road. In this paper, the high performance vehicle license plate recognition system using edge-based segment image is introduced which is robust in the geometric distortion and the image quality degradation according to non-trigger signal. The experimental results of the proposed real time license plate recognition algorithm which is implemented at the CCTV on the road show that the plate detection rate was 97.5% and the overall character recognition rate of the detected plates was 99.3% in a day average 1,535 vehicles for a week operation.

• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.1003-1010
• /
• 2018

When an applicant requests the emergency situation call or safe return service using a smart device, the smart surveillance service can select the CCTV(closed circuit television) cameras around the applicant using applicant's location information, then automatically takes a photograph to track the applicant. Since the surrounding CCTV camera shoots the applicant continuously using location information and the applicant can be observed by the monitor agent in real time, this service can be very helpful in an applicant's emergency situation or safe return. The existing smart surveillance service does not consider the priority of the emergency situation call and safe return service. Therefore, there is the disadvantage that the applicant who requests an emergency situation call service can not be photographed when safe return service has already preoccupied CCTV cameras which are capable of taking a picture of the applicant. The proposed smart surveillance service improves this disadvantage by using service priority.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.5
• /
• pp.813-827
• /
• 2017

Surveillance cameras installed in tunnels capture the various video frames effected by dynamic and variable factors. In addition, localizing and managing the cameras in tunnel is not affordable, and quality of capturing frame is effected by time. In this paper, we introduce a new method to detect and track the vehicles in tunnel by using surveillance cameras installed in a tunnel. It is difficult to detect the video frames directly from surveillance cameras due to the motion blur effect and blurring effect on lens by dirt. In order to overcome this difficulties, two new methods such as Differential Frame/Non-Maxima Suppression (DFNMS) and Haar Cascade Detector to track cars are proposed and investigated for their feasibilities. In the study, it was shown that high precision and recall values could be achieved by the two methods, which then be capable of providing practical data and key information to an automatic accident detection system in tunnels.

• Journal of the Korea Society for Simulation
• /
• v.31 no.2
• /
• pp.11-20
• /
• 2022

There is a critical need for AI assistance in guard operations of Army base perimeters, which is exacerbated by changes in the national defense and security environment such as force reduction. In addition, the possibility for human error inherent to perimeter guard operations attests to the need for an innovative revamp of current systems. The purpose of this study is to propose a real-time object detection AI tailored to military CCTV surveillance with three unique characteristics. First, training data suitable for situations in which relatively small objects must be recognized is used due to the characteristics of military CCTV. Second, we utilize a data augmentation algorithm suited for military context applied in the data preparation step. Third, a noise reduction algorithm is applied to account for military-specific situations, such as camouflaged targets and unfavorable weather conditions. The proposed system has been field-tested in a real-world setting, and its performance has been verified.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.3
• /
• pp.10-18
• /
• 2024

Vehicle loading is one of the main causes of bridge deterioration. Although WiM (Weigh in Motion) can be used to measure vehicle loading on a bridge, it has disadvantage of high installation and maintenance cost due to its contactness. In this study, a non-contact method is proposed to estimate the vehicle loading history of bridges using deep learning and CCTV images. The proposed method recognizes the vehicle type using an object detection deep learning model and estimates the vehicle loading based on the load-based vehicle type classification table developed using the weights of empty vehicles of major domestic vehicle models. Faster R-CNN, an object detection deep learning model, was trained using vehicle images classified by the classification table. The performance of the model is verified using images of CCTVs on actual bridges. Finally, the vehicle loading history of an actual bridge was obtained for a specific time by continuously estimating the vehicle loadings on the bridge using the proposed method.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.736-738
• /
• 2018

최근 딥러닝의 발전에 따라 무인감시, CCTV 등 영상감시 시스템도 지능화되고 있다. 하지만 쓰레기 무단투기 감시는 여전히 관리자가 실시간으로 CCTV 영상을 관제하는 형태로 이루어지고 있다. 이러한 문제를 해결하기 위해 본 논문에서는 CCTV 영상에서 쓰레기 무단투기를 검출하는 방법을 제안하며 검출 방법으로 차 영상과 합성곱 신경망을 이용한다. 실험은 합성곱 신경망에서의 쓰레기봉투 분류 문제 위주로 진행하였다. 합성곱 신경망의 네트워크는 Inception v3를 사용하였으며 실험 결과, 약 99.52%의 쓰레기봉투 분류율을 얻을 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.125-131
• /
• 2020

As technology advances, the importance of software education is increasing. Accordingly, interest in information subjects is increasing, but intending elementary learners to show algorithms only for specialized IT skills that could spoil the interest. In this paper for the elementary school students, through the four stages, 2015 revision curriculum analysis, creating of training program development operating plans, applying programs for the targeting students and analysis of results and evaluation, using Rich Picture technique which is various tools such as pictures and speech bubble symbols for the learners can express the intelligent CCTV algorithm freely and easily so they can understand fully about the algorithm of intelligent CCTV that uses artificial intelligence to extract faces from subjects. Suggest on this paper, the proposal of educational program can help the learner to grasp the principle of the algorithm by using the flowchart. As the result, Through the modification and development of the proposed program, we will conduct research on IT creative education that can be applied in various areas.

• The Journal of the Korea Contents Association
• /
• v.11 no.7
• /
• pp.437-447
• /
• 2011

This study will compare and analyze the effect of satisfaction of security needs on life satisfaction according to sociodemographic features and will find the factors of security needs satisfaction and life satisfaction. a total of three humdred questionnaires was distributed to male and female who live in Seoul(Gang-dong, Gang-sue, Songpa-gu and Gand-buk) in Aug. and Sept., 2010 and over nineteen years old. Except making the wrong questionnaires, total questionnaires was sampled from 259 questionnaires using judgment sampling method after selecting. Data analysis be used by SPSSWIN 18.0 Version. The validity and reliability of questionnaires are verified for factorial analysis and reliability analysis and also T test and F test are used for finding for differences of life satisfaction and satisfaction of security needs. And, this study is tested the regression analysis for the effects on the life satisfaction and satisfaction of security. Utilizing CCTV on the Life Satisfaction, this study were drawn the conclusions as following. First, the satisfaction of security needs as demographic characteristics have the part of the difference. the result shows to different psychological needs as educational level at the group less than college graduates. Second, the result of satisfaction of security as demographic characteristics is significantly higher in the male group and life satisfaction as education is significantly higher in more than college graduates. Third, the satisfaction of security needs of citizens through the CCTV effects to life satisfaction. environmental needs and information needs are as high as life satisfaction.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.124-137
• /
• 2018

The main purpose of this study is to find the hotspots of crimes that occur frequently in the space and to derive the appropriate CCTV installation location. One of the characteristics of crime is clustered around past occurrence area, and these crimes are strongly correlated. It is also possible to find the cause of the clusters and the variables that affect the crime through the history of the crime. In addition to the traditional OLS model, spatial differential model including spatial autocorrelation and spatial error model were used to select the variables influencing the five major crime rate, the theft rate and the foreign resident rate. The variables affecting the Five major crimes were positive (+) sign for the welfare and the rate of the bar cluster rate, and negative (-) for the street density. The CCTV area occupies 46% of the hotspots based on the overlapping of the areas where the elderly people are crowded, the bar cluster, many multicultural families, and the areas with low density of street lamps. It turned out. Taking into account the current CCTV operation, the total number of new cases to cover the risk point was 89.