• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.455-460
• /
• 2016

Recently, with more severe types felonies such as robbery and sexual violence, the importance of crime prediction and prevention is emphasized. For accurate and prompt crime prediction and prevention, both a classification model of crime with high accuracy based on past criminal records and well-designed system interface are required. However previous studies on the analysis of crime factors have limitations in terms of accuracy due to the difficulty of data preprocessing. In addition, existing crime monitoring systems merely offer a vast amount of crime analysis results, thereby they fail to provide users with functions for more effective monitoring. In this paper, we propose a classification model for types of crime based on random-forest algorithms and system design factors for real-time crime prediction. From our experiments, we proved that our proposed classification model is superior to others that only use criminal records in terms of accuracy. Through the analysis of existing crime monitoring systems, we also designed and developed a system for real-time crime monitoring.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.1000-1003
• /
• 2013

The monitoring system using a surveillance camera, has the advantage that can be observed in real time the blind spot of the crime, case to be mounted is increasing. However, surveillance camera, is used for the purpose of verification of the crime later than risk detection of crime before advance. Therefore, in this paper, in order to supplement the weak information collection monitoring system using the monitoring camera, by using the position information of the smartphone, infers the person monitoring region, the movement path of the image information other event occurs it is a fusion iT monitoring system that provides information of the user who judged. Result of the experiment, the proposed system confirmed the improved efficiency and usability than conventional systems.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.3
• /
• pp.83-90
• /
• 2010

In modern society, there has been an increase in needs to protect the life and property of the people, because the number of various crimes is on the increase due to the sudden and complicated changes of the urban environment. For the needs, security persons in the urban area are expanding the role and skill of police for more effective crime prevention and surveillance, although the number of policeman/woman is insufficient and their tasks are hard. Recently, a system to observe and prevent crime in effective has been introduced by using such an artificial surveillance device as CCTV to monitor focusing on one area for 24 hours. However, the system brings such problems as the insufficiency of systematic criteria to install surveillance device and the invasion of privacy. Therefore, in this study, artificial surveillance zones to monitor crimes are selected by applying spatial features between artificial surveillance devices including CCTV and crime occurrence place, and using GIS spatial analysis techniques. As a result of selecting, it's found that the number of CCTV is absolutely insufficient and spatial distribution is not fully considered in the existing location of installed CCTV.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.400-403
• /
• 2011

다양한 특성의 도시공간의 확장은 경제 활동의 활성화는 물론 도시공간에서의 범죄발생 확대로 이어지고 있다. 이에 따라 국민의 생명과 재산보호, 사회질서유지 등을 위한 각종 대책과 경찰의 역할을 확대되고 있으나 효율적인 범죄예방 활동이 부족한 상태이다. 따라서 이 연구에서는 체계적인 범죄 모니터링을 위한 기초연구의 일환으로 도시공간에서의 범죄가 발생하는 공간에 대한 패턴을 이해하고 분석하여 도시 내 안전구역을 분석하여 GIS 공간분석기법의 효용성을 나타내었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.57-60
• /
• 2003

최근 대부분의 기업 정보 범죄가 기업 내부자 소행으로 일어난다. 허가되지 않은 사용자의 불법적인 사용 및 도용은 기업 내부의 정보유출, 파괴 등 기업에 막대한 피해를 가져온다. 이런 환경에서 공용으로 사용되는 기업 정보에 대한 사용자별 파일 또는 디렉토리 접근에 대한 실시간적인 관리가 이루어져야 한다. 본 논문에서는 멀티 유저 윈도우서버의 디렉토리 및 파일에 접근하는 사용자를 실시간적으로 모니터링하고, 사용자 권한에 위배되는 행동을 모니터링하는 시스템을 설계 및 구현한다.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.14 no.2
• /
• pp.37-44
• /
• 2015

The purpose of this study is to propose the calculation model of CCTV monitor size for school. Literature review analyzed the concept and technical characteristics of CCTV system including equation of object size calculation. Case study showed that the sizes of CCTV monitors installed in the security offices of the six object schools were 19 inches on average. And the numbers of monitor screen partitions were at least 12 on average. Due to too many partitions in small monitors of approximately 19 inches, the faces of the objects of filming in each screen could not be properly identified. Experimental test presented that the vertical length of face image clearly recognized on the screen is at least 20mm. Based on the result, this paper developed the equation for calculating monitor size. Pilot test said that 27inch Monitor is needed for 4 screens. The practitioners of school districts and schools can make appropriate CCTV system environments considering the their own CCTV system conditions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.3
• /
• pp.323-330
• /
• 2009

The demand that we are monitoring security and crime of the urban facilities is increasing recently, but the using CCTV devices are expensive. In this research, we enlarge the angle of view using the Fish-eye Lens and the Photogrammetry, the efficiency of monitoring enhance. First, we carry out the calibration of the Fish-eye Lens indoors, we calculate the correction parameters, and then covert the original image-point to new image-point correcting distortion. Second, the correction program with the correction parameters can obtain the real-time correcting image. Lastly, for authorization the developed program we compare correcting-image with scanning-imge, it is showed the RMSE is 3.2pixel.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.546-554
• /
• 2019

Typically, closed-circuit television (CCTV) monitoring is mainly used for post-processes (i.e. to provide evidence after an incident has occurred), but by using a streaming video feed, machine-based learning, and advanced image recognition techniques, current technology can be extended to respond to crimes or reports of missing persons in real time. The multi-CCTV cooperation technique developed in this study is a program model that delivers similarity information about a suspect (or moving object) extracted via CCTV at one location and sent to a monitoring agent to track the selected suspect or object when he, she, or it moves out of range to another CCTV camera. To improve the operating efficiency of local government CCTV control centers, we describe here the partial automation of a CCTV control system that currently relies upon monitoring by human agents. We envisage an integrated crime prevention service, which incorporates the cooperative CCTV network suggested in this study and that can easily be experienced by citizens in ways such as determining a precise individual location in real time and providing a crime prevention service linked to smartphones and/or crime prevention/safety information.

• Journal of Cadastre & Land InformatiX
• /
• v.44 no.1
• /
• pp.139-150
• /
• 2014

Recently the violent crimes is the emerging social issue and the crime prevention is important policy both for maintenance of public order and the national welfare. To prevent these crimes with the geospatial data, we study the geospatial crime DB features, analytical method and linking method of current National Police Agency's crime system data. In this study, the Geospatial Information Open Platform(Vworld) was used to map the test site crime DB on the thematic map. We also researched the mesh-up thematic map and optimal location model of petrol car and CCTV.

• The Journal of Society for e-Business Studies
• /
• v.13 no.2
• /
• pp.101-115
• /
• 2008

Recently in the human society, the crime using small arms has increased. Also, many accidents happen because of incomplete management of chemicals and radiation. Accordingly, it is necessary to manage dangerous objects by tracing the position of dangerous objects and rapidly providing the correct information for them. This paper presents a web-based system for real-time monitoring of dangerous objects using RFID in order to overcome the limitations and problems of current dangerous objects management techniques. In this paper, we define the architecture for web-based dangerous objects monitoring system and the scheme for storing information of a dangerous object in the RFID tag. We also implement the web-based monitoring system and present the execution result of the system. The proposed real-time monitoring system is composed of the dangerous objects monitoring server which manages information of dangerous objects and controls them, the dangerous objects monitoring middleware which is mediator between dangerous objects and the server, the RFID reader which reads information of dangerous objects from RFID tags attached to the objects and the database which stores information, status and position of dangerous object. The proposed system manages diverse dangerous objects such as small arms, radiation and harmful chemicals based on the position of them using RFID, so the user can check dangerous objects when they are checked in and checked out and the user can acquire the real-time position information of them through the system. Furthermore, the user can visually monitor dangerous objects through web browser from any where and at any time because the system is web-based system and it provides graphical user interface.