• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.2
• /
• pp.198-202
• /
• 2009

Urban Search and Rescue (USAR) involves locating, rescuing (extricating), and medically stabilizing victims trapped in confined spaces. In this paper we state the current approach to USAR, address the limitations and discuss the way for moving in rugged topography. To achieve objectives such as surveillance, reconnaissance, and rescue, it is necessary to develop a driving mechanism that can handle rugged geographical features. We propose a new type of driving mechanism for a rescue robot that has a variable shape single-track. By using a variety shapes, it can get the gain of steering and rotating and the ability to overcome stairs. In this paper, we analyzed the design parameters for making variable transform shapes and determined the specifications of the robot to enhance adaptability to stairs.

• Journal of information and communication convergence engineering
• /
• v.16 no.2
• /
• pp.78-83
• /
• 2018

Rapidity and accuracy are important considerations when a drone is employed in a wide surveillance area to detect a target. They are more important when the scope of application is a search and rescue operation or the monitoring of natural disasters, which may require prompt warnings and response. During the actual operation of a drone, rapidity and accuracy are associated with the change in the altitude of the drone. The aim of this study is to analyze the characteristics of drones at varying altitudes and prove that altitude is a relevant factor in the performance of drones. Herein, the characteristics of the drone at varying altitudes were analyzed through several search simulations. The results suggest that a high-altitude drone is relatively advantageous compared to a low-altitude drone in a probability-based target search, and that the search altitude is also a very important and fundamental factor in target search by drones.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• Proceedings of the KOR-KST Conference
• /
• 1998.09a
• /
• pp.152-159
• /
• 1998

This paper presents a method evaluating benefits of ramp metering strategies on freeway safety. Based on the traffic and the accident data collected on a 4.2 km (2.6 mile) section of Interstate highway 35-West in Minneapolis, U.S.A., the relationship between traffic variables and safety measures is investigated. An aggregate specification that could be used to predict accident frequencies on freeways is proposed as a multiple regression form. The specification includes 15 minutes volume and occupancy data, which are commonly available from surveillance and control systems. The primary variables that appear to affect the frequencies of freeway accident are: vehicle-miles of travel, entrance ramp volumes and the dynamic effect of queue building. A simulation method evaluating the dynamic effect of control strategies on safety is proposed next. The potential benefits of freeway ramp metering on freeway safety are finally investigated via a proposed method.

• 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 Information Processing Systems
• /
• v.15 no.4
• /
• pp.1017-1028
• /
• 2019

Pedestrian tracking is a particular object tracking problem and an important component in various vision-based applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.115-119
• /
• 2020

Recently, CCTV installations are rapidly increasing in the public and private sectors to prevent various crimes. In accordance with the increasing number of CCTVs, video-based abnormal behavior detection in control systems is one of the key technologies for safety. This is because it is difficult for the surveillance personnel who control multiple CCTVs to manually monitor all abnormal behaviors in the video. In order to solve this problem, research to recognize abnormal behavior using deep learning is being actively conducted. In this paper, we propose a model for detecting abnormal behavior based on the deep learning model that is currently widely used. Based on the abnormal behavior video data provided by AI Hub, we performed a comparative experiment to detect anomalous behavior through violence learning and fainting in videos using 2D CNN-LSTM, 3D CNN, and I3D models. We hope that the experimental results of this abnormal behavior learning model will be helpful in developing intelligent CCTV.

• Journal of Veterinary Science
• /
• v.22 no.1
• /
• pp.13.1-13.14
• /
• 2021

African swine fever (ASF) is one of the most complex infectious swine diseases and the greatest concern to the pig industry owing to its high mortality and no effective vaccines available to prevent the disease. Since the first outbreak of ASF in pig farms, ASF has been identified in 14 pig farms in four cities/counties in South Korea. The outbreak was resolved in a short period because of the immediate control measures and cooperative efforts. This paper reviews the ASF outbreak and the experience of successfully stopping ASF in pig farms in South Korea through active responses to prevent the spread of ASF. In addition, suitable changes to build a sustainable pig production system and collaborative efforts to overcome the dangerous animal disease, such as ASF, are discussed.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.190-195
• /
• 2009

With the growth of information and communication technologies adoption in construction projects, it could be anticipated that more property owners and construction firms will attempt to use electronic gears and gadgets for site monitoring or surveillance purposes. As the construction workers may be the major group of project team members being monitored, from managerial perspectives and for ethical reasons, it is essential to investigate their degree of acceptance on site monitoring systems. Indeed studies on office workplace monitoring suggest that a monitoring system could shape or control the behaviors of employees. With adequate refinements, their research models could be applicable in the construction industry. This paper presents a model for analyzing the antecedences that affect workers' acceptance level on electronic monitoring, and investigating if there is any behavioral change.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.329-337
• /
• 2024

Free-space optical communication technology enables the high-speed data transmission and excellent anti-jamming security. We conduct research on satellite-to-ground free-space optical communication links for high-speed transmission of large-capacity surveillance and reconnaissance data. Since the satellite continues to move along its orbit while the optical signal is transmitted between the satellite and the ground, the pointing angle of the beam from the ground terminal needs to be corrected by Point Ahead Angle(PAA) so that the transmitted light reaches the expected location of the satellite. In this paper, we present the algorithm for PAA estimation and control.