• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.912-928
• /
• 2019

Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.8
• /
• pp.817-826
• /
• 2016

The importance of common life safety is getting growth with modern society progress. This paper shows the extended way of assessment of danger that outcomes better result than the previous assessment based on crime frequency assessment. The assessment of this paper involves time, illusion degree, floating population and the personal condition. The evidence theory is not beneficial when the number of component increases, the assessment is more complex than before. This research solves the problem through the fuzzy theory adoption. This paper shows more advanced result that can express better danger awareness and get the adjective expression.

• Convergence Security Journal
• /
• v.14 no.1
• /
• pp.3-10
• /
• 2014

Private security organizations are complementary to the national safety of life and property of individuals as a social role to play in maintaining peace and order. Pursuit of profit is to the public practice according to the logic of capitalist markets and customers seeking to protect the lives and property. However, the legal and institutional constraints of private security is being requirements inhibited by the development. Crime prevention as a private security role that the private companies, which will pursue the public interest. After all, the expansion of the private security crime is results in an increase in unit. The current level of private security in the 1970s remain, and the constraints is being under goodwill and expertise outside of the training system on the market. Variety of crimes, including cyber crime increases and considering the reality of the constraints on private security requirements are able to improve or supplement shall be realistic. In particular, the legal, regulatory and institutional factors must be improved, with goodwill, and for the creation of new industrial policy as a complement to the public interest should be also provided. The private security law interests through integration of private security guards should be guaranteed, and the term of the theorem, sales activities, ensuring the training of professional staff with professional qualifications system is to be settled. As a private security guard industry growth and development can be based on this composition.

• Smart Media Journal
• /
• v.6 no.1
• /
• pp.61-67
• /
• 2017

A large number of people living in modern times prefer remaining unmarried or living alone independently for the reason of their own will or another person's will. This is because they dislike being interfered with by other persons or because there is a financial problem. This behavior has become mainstream in persons working for professional jobs, persons having a strong disposition toward individual activity or college students. In particular, career women pursuing their own comfortable life have the tendency to prefer single life. However, sometimes, they become a target of crime that targets and makes bad use of this point. For these reasons. Consequently, sometimes, they additionally install and use a security system such as door security guard at front door and so on. It is not so difficult to lock the door security guard at the front door. However, it is apt to be forgotten. And when they are on the bedspread before falling asleep, in case they should check whether the door security guard is locked or in case they should lock it, they should get up, go to the entrance, and check and lock the door security guard. They often don't lock the door security guard due to their feeling that it is all right because of annoyance and inconvenience. This paper is intended to work for safety from crime such as illegal housebreaking by more conveniently using the door security guard after designing and implementing a system that can remotely control the door security guard, using a smartphone as a method of resolving this annoyance and keeping life more safe.

• Korean Security Journal
• /
• no.7
• /
• pp.155-189
• /
• 2004

The mission of the police as described by law is to guard the life, body and property of all citizens. Such duties should be accurately performed based on legal and democratic procedures because the works of the police are directively influencing the overall lives of the citizens by restricting their freedom. We are frequently watching the traffic police on the street or road. Traffic policing aims to reduce crime and the opportunities for criminal activity in relation to the use of roads, that is to improve road user behavior in order to reduce accidents. The characteristics of traffic accident change is not similar in each traffic condition. The purpose of this study is to analysis a type characteristics of traffic accident change, such as number of deaths and wounded persons by the time, the vehicle, the type the road, the age group. Based on the characteristics of traffic accident change, traffic accident countermeasures are proposed, in which some variable of traffic policies such as traffic facilities, traffic regulation, and traffic safety education.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.385-390
• /
• 2009

본 연구에서는 최근 학교 주변에서 발생하는 어린이 범죄 사고의 관리 및 예방을 위한 무선 센서 네트워크 기반의 스쿨존 안전관리 시스템을 제안한다. 학교 주변 무선센서네트워크 망 구축과 어린이들에게 부착되는 센서들을 통해 환경 및 위치 영상 센싱 정보들을 공간 지식화하여 안전과 관련된 서비스를 제공한다. 또한 스쿨존 망을 벗어나 통신이 되지 않는 어린이의 경우 기회주의적 네트워크를 통하여 관리할 수 있는 전략적 안전관리 방안을 제안한다.

• The Journal of Economics, Marketing and Management
• /
• v.10 no.6
• /
• pp.17-26
• /
• 2022

Purpose: This study analyzes advanced cases of overseas smart cities and examines policy implications related to the creation of smart cities in Korea. Research design, data, and methodology: Analysis standards were established through the analysis of best practices. Analysis criteria include Technology, Privacy, Security, and Governance. Results: In terms of technology, U-City construction experience and communication infrastructure are strengths. Korea's ICT technology is inferior to major countries. On the other hand, mobile communication, IoT, Internet, and public data are at the highest level. The privacy section created six principles: legality, purpose limitation, transparency, safety, control, and accountability. Security issues enable urban crime, disaster and catastrophe prediction and security through the establishment of an integrated platform. Governance issues are handled by the Smart Special Committee, which serves as policy advisory to the central government for legal system, standardization, and external cooperation in the district. Conclusions: Private technology improvement and participation are necessary for privacy and urban security. Citizens should participate in smart city governance.

• Proceedings of KOSOMES biannual meeting
• /
• 2003.11a
• /
• pp.99-104
• /
• 2003

The maritime security risk has been recognized since the terrorists attacked the world trade center and the Pentagon In this paper, maritime security risk is analyzed on the basis if the data of crime in Korean sea We propose the countermeasures to prevent maritime security threats

• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.425-431
• /
• 2017

As drones gain more popularity these days, drone detection becomes more important part of the drone systems for safety, privacy, crime prevention and etc. However, existing drone detection systems are expensive and heavy so that they are only suitable for industrial or military purpose. This paper proposes a novel approach for training Convolutional Neural Networks to detect drones from images that can be used in embedded systems. Unlike previous works that consider the class probability of the image areas where the class object exists, the proposed approach takes account of all areas in the image for robust classification and object detection. Moreover, a novel loss function is proposed for the CNN to learn more effectively from limited amount of training data. The experimental results with various drone images show that the proposed approach performs efficiently in real drone detection scenarios.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.701-708
• /
• 2021

As one of the most widely used technology in the world right now, Face recognition has already received widespread attention by all the researcher and institutes. It has been used in many fields such as safety protection, surveillance system, crime control and even in our ordinary life such as home security and so on. This technology with today's technology has advantages such as high connectivity and real time transformation. But we still need to improve its recognition rate, reaction time and also reduce impact of different environmental status to the whole system. So in this paper we proposed a face recognition system model with improved CNN which combining the characteristics of flat network and residual network, integrated learning, simplify network structure and enhance portability and also improve the recognition accuracy. We also used AR and ORL database to do the experiment and result shows higher recognition rate, efficiency and robustness for different image conditions.