• 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.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.455-462
• /
• 2013

This paper proposes a detection system that, by determining whether a dangerous act is being carried out among other pedestrians in the images captured using CCTV, provides pre-warnings and establishes emergency measures. To determine the presence of a dangerous act, after setting zones of interest and danger zones within those zones of interest, the danger level is determined in accordance with the range of encroachment upon detecting an object. Especially, this research aims at detecting a suicide jump from the bridge and extends to detecting a dangerous act among pedestrians from detecting a dangerous act of only one person with no one in the previous research. This system classifies the status into 3 levels as safe, alert, and danger according to the amount of part being over the bridge railing. If a situation is deemed as warning-worthy and emergency, the integrated control center is immediately alerted to facilitate prevention in advance.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• 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 Broadcast Engineering
• /
• v.20 no.3
• /
• pp.430-439
• /
• 2015

The demand of violence detection techniques using a video analysis to help prevent crimes is increasing recently. Many researchers have studied vision based behavior recognition but, violent behavior analysis techniques usually focus on violent scenes in television and movie content. Many methods previously published usually used both a color(e.g., skin and blood) and motion information for detecting violent scenes because violences usually involve blood scenes in movies. However, color information (e.g., blood scenes) may not be useful cues for violence detection in surveillance videos, because they are rarely taken in real world situations. In this paper, we propose a method of violent behavior detection in surveillance videos using motion vectors such as flow vector magnitudes and changes in direction except the color information. In order to evaluate the proposed algorithm, we test both USI dataset and various real world surveillance videos from YouTube.

• 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.

• International Commerce and Information Review
• /
• v.17 no.3
• /
• pp.225-250
• /
• 2015

While strategic alliance of multinational corporation has boost, opportunistic behavior is also increased recently. This study examines the cause of opportunism in strategic alliance by focusing on the development of opportunistic behavior, a process in which resource complementarity and risk perception decides attitudinal direction, ultimately leading to opportunism. Empirical test based on 257 alliance participants shows that risk perception had a greater influence on firms' attitudinal and behavioral directions compared to benefit perception. Notably, relational risk heavily influenced firms' competitive attitude and opportunistic behavior. Finally, the study concludes that firms' competitive and independent attitude caused by risk perception negatively influence alliance outcome. Based on the results, it is drawn that alongside the external tools such as surveillance, control, monitoring or legalistic pleas, management of risk perception during the alliance process has significance influence on the achievement of alliance goals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.182-184
• /
• 2012

마이크로소프트에서 개발한 키넥트(kinect)는 엑스박스(XBox) 게임 컨트롤러로 사용하는 장비이며 이 센서를 이용하여 사용자의 인체 행동을 인식하여 게임을 진행할 수 있는 센서 시스템이다. 또한 윈도우 환경에서 키넥트를 활용하여 다양한 응용 프로그램 개발을 할 수 있도록 SDK를 제공하고 있다. 현대사회에서 각종 범죄가 늘어남에 따라서 CCTV의 운용이 늘어나고 있으며 지정된 구역을 감시하는데 다양한 영상 장비들과 프로그램이 운용하고 있다. 시장에 판매되고 있는 CCTV 장비들 중에서 사람 추적기능을 가능 제품은 가격이 대부분 고가이다. 또한 야간에서는 사람의 감지가 힘들다. 본 연구에서는 키넥트의 골격 추적기능과 음성인식 기능을 활용하여 실시간 영상 녹화 프로그램을 개발하고자 하며, 개발된 프로그램은 키넥트 센서로 영상을 실시간 녹화하고 침입자에 대한 움직임을 자동 추적하여 녹화하는 DVR 시스템을 제안하고자 한다. 또한 야간에서는 깊이(Depth) 영상을 이용하여 인물을 인식과 추적을 한다. 궁극적으로 키넥트 센서(Kinect Sensor)의 CCTV기능에 대한 활용성을 연구하는데 목적을 가진다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.10
• /
• pp.1095-1102
• /
• 2014

In this paper, We proposed the approach of GPU and motion vector to analysis the Human activity in real-time surveillance system. The most important part, that is detect blob(human) in the foreground. We use to detect Adaptive Gaussian Mixture, Weighted subtraction image for salient motion and motion vector. And then, We use motion vector for human activity analysis. In this paper, the activities of human recognize and classified such as meta-classes like this {Active, Inactive}, {Position Moving, Fixed Moving}, {Walking, Running}. We created approximately 300 conditions for the simulation. As a result, We showed a high success rate about 86~98%. The results also showed that the high resolution experiment by the proposed GPU-based method was over 10 times faster than the cpu-based method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.25-30
• /
• 2011

This paper present a method for abnormal traffic behavior, or trajectory, detection in static traffic surveillance camera with user-defined trajectories. The method computes the abnormality of moving object with a trajectory of the object and user-defined trajectories. Because of using user-define based information, the presented method have more accurate and faster performance than models need a learning about normal behaviors. The method also have adaptation process of assigned rule, so it can handle scene variation for more robust performance. The experimental results show that our method can detect abnormal traffic behaviors in various situation.