• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.431-433
• /
• 2021

In this paper, abnormal behavior monitoring system using YOLO AI platform was implemented and had superior response characteristics compared to the conventional monitoring system using two-shot detection by using one-shot detection of YOLO system. The YOLO platform was trained using image dataset composed of abnormal behaviors such as assault, theft, and arson. The abnormal behavior monitoring system consists of client and server and can be applicable to smart cities to solve various crime problems if it is commercialized.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.353-355
• /
• 2012

본 논문에서는 지능형 감시 시스템을 위한 3가지 이상행위 검출 방법을 제안한다. 단순히 직접 감시나 센서에 의존한 문제점 검출이 아닌 비전 기반 기술을 적용하여 특정지역 및 모든 감시구역에 대하여 객체의 이상 행동을 감지하는 방법들을 소개한다. 제안하는 이상행위의 분류는 배회, 도주, 특정 감시 지역 침입 3가지로 정의한다. 휘도 기반의 평균 배경 모델링 방법을 통하여 움직임 물체를 검출하고, 검출된 객체를 분석(위치, 크기, 방향, 속도) 및 정의한다. 이때 이상행위의 판단에 따라 정의된 시나리오 환경으로 구성하고 분석하였다. 제안하는 방법은 실험에 사용된 3가지 이상행위에 대해 1초 안에 검출되는 것을 보였다.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.589-596
• /
• 2013

With the increase of social crime rate, the interest on the intelligent security system is also growing. This paper proposes a detection system of monitoring whether abnormal behavior is being carried in the images captured using CCTV. After detection of an object via subtraction from background image and morpholgy, this system extracts an abnormal behavior by each object's feature information and its trajectory. When an object is loitering for a while in CCTV images, this system considers the loitering as an abnormal behavior and sends the alarm signal to the control center to facilitate prevention in advance. Especially, this research aims at detecting a loitoring act among various abnormal behaviors and also extends to the detection whether an incoming object is identical to one of inactive objects out of image.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.89-96
• /
• 2021

In recent years, the fear of terrorism due to 'Lone Wolf' terrorism is spreading in the United States and Europe. The lone wolf terrorism, which carries out terrorism independently, without an organization behind it, threatens social security around the world. In Korea, those who have explosive national/social dissatisfaction due to damage caused by national policies, and delusional mental disorders can be classified as potential 'Lone Wolf' terrorists. In 'Lone Wolf' terrorism, unlike organized terrorism, it is difficult to identify signs of terrorism in advance, and it is not easy to identify terrorist tools and targets. Therefore, in order to minimize the damage caused by 'Lone Wolf' terrorism, it is necessary to architect an independent monitoring and tracking system for the police's quick response. In this paper, we propose to architect response system that can collect information from organizations that can identify the signs of potential 'Lone Wolf' terrorism, monitor the continuity of abnormal behavior, and determine the types of 'Lone Wolf' terrorism that can happen as continuous abnormal behaviors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.73-80
• /
• 2023

The recent steep increase in the minimum hourly wage has increased the burden of labor costs, and the share of unmanned stores is increasing in the aftermath of COVID-19. As a result, theft crimes targeting unmanned stores are also increasing, and the "Just Walk Out" system is introduced to prevent such thefts, and LiDAR sensors, weight sensors, etc. are used or manually checked through continuous CCTV monitoring. However, the more expensive sensors are used, the higher the initial cost of operating the store and the higher the cost in many ways, and CCTV verification is difficult for managers to monitor around the clock and is limited in use. In this paper, we would like to propose an AI image processing fusion algorithm that can solve these sensors or human-dependent parts and detect customers who perform abnormal behaviors such as theft at low costs that can be used in unmanned stores and provide cloud-based notifications. In addition, this paper verifies the accuracy of each algorithm based on behavior pattern data collected from unmanned stores through motion capture using mediapipe, object detection using YOLO, and fusion algorithm and proves the performance of the convergence algorithm through various scenario designs.

• Journal of Digital Contents Society
• /
• v.16 no.1
• /
• pp.25-32
• /
• 2015

With the increased frequency of crime such as assaults and sexual violence, the reliance on CCTV in arresting criminals has increased as well. However, CCTV, which should be monitored by human labor force at all times, has limits in terms of budget and man-power. Thereby, the interest in intelligent security system is growing nowadays. Expanding the techniques of an objects behavior recognition in previous studies, we propose a system to detect forms of violence between 2~3 objects from images obtained in CCTV. It perceives by detecting the object with the difference operation and the morphology of the background image. The determinant criteria to define violent behaviors are suggested. Moreover, provable decision metric values through measurements of the number of violent condition are derived. As a result of the experiments with the threshold values, showed more than 80% recognition success rate. A future research for abnormal behaviors recognition system in a crowded circumstance remains to be developed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.161-168
• /
• 2019

Recently, video equipments such as CCTV, which is spreading rapidly, is being used as a means to monitor and cope with abnormal situations in almost governments, companies, and households. However, in most cases, since recognizing the abnormal situation is carried out by the monitoring person, the immediate response is difficult and is used only for post-analysis. In this paper, we present the results of the development of video surveillance system that automatically recognizing the abnormal situations and sending such events to the smartphone immediately using the latest deep learning technology. The proposed system extracts skeletons from the human objects in real time using Openpose library and then recognizes the human behaviors automatically using deep learning technology. To this end, we reconstruct Openpose library, which developed in the Caffe framework, on Darknet framework to improve real-time processing. We also verified the performance improvement through experiments. The system to be introduced in this paper has accurate and fast behavioral recognition performance and scalability, so it is expected that it can be used for video surveillance systems for various applications.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.1056-1058
• /
• 2022

본 연구는 항만에서 안전 수칙을 위반하여 발생하는 사고 및 이상행동을 실시간 탐지를 수행한 후 위험 상황을 관리자가 신속하고 정확하게 대처할 수 있도록 지원하는 지능형 CCTV, Smart Eye를 제안한다. Smart Eye는 컴퓨터 비전(Computer Vision) 기반의 다양한 객체 탐지(Object Detection) 모델과 행동 인식(Action Recognition) 모델을 통해 낙하 및 전도사고, 안전 수칙 미준수 인원, 폭력적인 행동을 보이는 인원을 복합적으로 판단하며, 객체 추적(Object Tracking), 관심 영역(Region of Interest), 객체 간의 거리 측정 알고리즘을 구현하여, 제한구역 접근, 침입, 배회, 안전 보호구 미착용 인원 그리고 화재 및 충돌사고 위험도를 측정한다. 해당 연구를 통한 자동화된 24시간 감시체계는 실시간 영상 데이터 분석 및 판단 처리 과정을 거친 후 각 장소에서 수집된 데이터를 관리자에게 신속히 전달하고 항만 내 통합관제센터에 접목함으로써 효율적인 관리 및 운영할 수 있게 하는 '지능형 인프라'를 구축할 수 있다. 이러한 체계는 곧 스마트 항만 시스템 도입에 이바지할 수 있을 것으로 기대된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.367-369
• /
• 2004

허니팟은 공격자들이 쉽게 공격할 수 있는 시스템이나 네트워크를 구성하여, 악성해커나 스크립트 키드들이 어떻게 시스템을 침입하고 공격하는지 감시할 수 있도록 구성되어 있는 시스템을 말한다. 일반적으로 허니팟은 방화벽과 로그 기록 등으로 감사기능을 수행하는데, 악성해커는 그 로그마저 복구할 수 없도록 삭제하는 경우도 있기 때문에 독립적인 추적 시스템이 필요하다. 본 논문에서는 LKM(Linux Kernel Module)기법을 이용한 키로거를 통해 공격자가 세션 상에서 입력하는 모든 키보드 내용을 기록하여 공격자의 행동을 쉽고 빠르게 분석하는 원격 키스트로크 모니터링 시스템을 설계해 보았다.