• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.15-20
• /
• 2006

This paper describes research on intelligent game character through performance enhancements of physics engine in computer games. The algorithm that recognizes the physics situation uses momentum back-propagation neural networks. Also, we present an experiment and its results, integration methods that display optimum performance based on the physics situation. In this experiment on integration methods, the Euler method was shown to produce the best results in terms of fps in a simulation environment with collision detection. Simulation with collision detection was shown similar fps for all three methods and the Runge-kutta method was shown the greatest accuracy. In the experiment on physics situation recognition, a physics situation recognition algorithm where the number of input layers (number of physical parameters) and output layers (destruction value for the master car) is fixed has shown the best performance when the number of hidden layers is 3 and the learning count number is 30,000. Since we tested with rigid bodies only, we are currently studying efficient physics situation recognition for soft body objects.

• Spatial Information Research
• /
• v.21 no.3
• /
• pp.11-19
• /
• 2013

Compared with traditional video monitoring systems that provide a video-recording function as a main service, an intelligent video monitoring system is capable of extracting/tracking objects and detecting events such as car accidents, traffic congestion, pedestrian detection, and so on. Thus, the object tracking is an essential function for various intelligent video monitoring and surveillance systems. In this paper, we propose a background and local histogram-based object tracking approach for intelligent video monitoring systems. For robust object tracking in a live situation, the result of optical flow and local histogram verification are combined with the result of background subtraction. In the proposed approach, local histogram verification allows the system to track target objects more reliably when the local histogram of LK position is not similar to the previous histogram. Experimental results are provided to show the proposed tracking algorithm is robust in object occlusion and scale change situation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.176-190
• /
• 2019

The prevention of pedestrian accidents in crosswalks and intersections is very important. The C-ITS services provide a warning service for preventing accidents between cars and pedestrians. In the current pedestrian collision prevention warning service according to the C-ITS standard, however, it is difficult to provide real-time service because it detects pedestrians from a video-analysis server in the control center and sends service messages through the ITS system. This paper proposes a pedestrian collision-prevention warning system that detects pedestrians in the local field using an edge camera and sends a warning message directly to the driver through a roadside unit. An evaluation showed that the proposed system could deliver the pedestrian collision prevention-warning message to the driver satisfying the delay time within the 300 ms required by the C-ITS standard, even in the worst case.

• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.137-143
• /
• 2009

It is necessary to develop driving assistant information in order to prevent a rear-end collision with a crashed car which is at the blind curve on highway. Laboratory experiments were performed using a driving simulator to keep the traffic environment constant. This research was evaluated the effect of driver behavior according to providing collision avoidance information which was consisted of advisory, caution, and warning information by the dangerous degree of traffic situation. Driver behavior was evaluated to analyze the collision avoidance with a crashed car, and glance behavior was examined to measure the eye movements to the display on which provided the collision avoidance information. After experiment, the significance was evaluated on provided collision avoidance information. As the result of this research, the number of collision accident is reduced when the phased information was provided. In addition, it is clear that auditory information is more important than visual information in the case of providing the second information.

• Journal of the Society of Naval Architects of Korea
• /
• v.38 no.4
• /
• pp.23-29
• /
• 2001

An Obstacle Avoidance System(OAS) of Underwater Vehicle(UV) in diving and steering plane is investigated. The concept of Imaginary Reference Line(IRL), which acts as the seabed in the diving plane, is introduced to apply the diving plane avoidance algorithm to the steering plane algorithm. Furthermore, the distance to the obstacle and the slope information of the obstacle are used for more efficient and safer avoidance. As for the control algorithm, the sliding mode controller is adopted to consider the nonlinearity of the equations of motion and to get the robustness of the designed system. To verify the obstacle avoidance ability of the designed system, numerical simulations are carried out on the cases of some presumed three-dimensional obstacles. The effects of the sonar and the clearance factor used in avoidance algorithm are also investigated. Through these, it is found that the designed avoidance system can successfully cope with various obstacles and the detection range of sonar is proven to bea significant parameter to the performance of the avoidance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.251-252
• /
• 2019

본 논문에서는 소형 무인항공체 (UAV, Unmanded Aerial Vehicle)가 제한된 공역 (airspace)에서 발생할 수 있는 상황을 예측할 수 있는 시뮬레이터를 개발하여 테스트를 수행한 결과를 보인다. 많은 소형 UAV가 밀집해서 비행하는 상황을 가정하여 충돌의 발생 가능성을 줄이기 위해 공역을 고도에 따라 계층으로 나누었으며 시뮬레이터에 이를 반영하였다.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.27 no.1
• /
• pp.17-23
• /
• 1990

When a thin walled member is subjected to compression in a condition such as collision, the energy is mainly absorbed by axial crumpling. In this case, dynamic crushing strength of the member is increased due to the effects of strain-rate compared with the static strength, even though the inertia effect is neglected. In this paper, the method of predicting the static crushing for tubular members is presented using the kinematic method of plasticity. Since, a predicted crushing load, taking account of the dynamic yield stress, usually overestimates the effects of strain-rate, the average plastic flow stress for the effects of strain-rate is used to obtain the dynamic crushing load for tubular members. The analytical results are compared with the experiments published in references, and a good correlation is observed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.470-471
• /
• 2011

As the increase in maritime traffic and leisure, the marine accident risk has increased in the domestic coast. In this paper, we propose an anti-collision system between vessels using the shortest distance and the time to reach the distance in maritime. the shortest distance and the time to reach the distance calculated with vector analysis using AIS information, a prototype is implemented for smartphone application.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.295-296
• /
• 2022

자율운항선박은 선원의 항해 조작 없이 선박 스스로 운항하는 선박을 의미한다. 자율운항선박의 운항 시 충돌 및 사고 위험도가 큰 지역은 운항 중 선박을 많이 조우하게 되는 항 내 및 연안 지역이다. 실제로 충돌사고의 85% 이상이 항 내 및 연안 지역에서 발생한다. 따라서 자율운항선의 운항 안전성 확보를 위해 항 내 및 연안 지역에서의 운항 안전성을 검토하는 것은 미래 자율운항선 항 내 운용 체계에서 중요한 역할을 하게 된다. 대양에서는 선박 자체의 운항성능이 중요하지만, 항구 입출항 시에는 타선 및 터미널등과의 상호작용이 자율운항선의 입출항 안전성과 직결된다. 따라서 본 연구에서는 자율운항선이 항구 근처에 접근하여 입출항을 위해 대기하고 있는 경우에 입출항 결정을 내릴 수 있는 결정 알고리즘을 위한 해상혼잡도를 예측하는 알고리즘을 개발하는 과정을 소개한다. 혼잡 예측 알고리즘 개발을 위해 선박의 AIS통항 데이터를 분석하여 주요 항로를 구분하고 주요 항로의 이용 빈도 및 운항 시점의 선박 집중도 및 충돌위험 상황을 파라미터로 하여 특정 시간이 지난 후의 혼잡도를 예측하는 시스템을 개발하고자 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.81-83
• /
• 2023

자율운항선박은 선원의 항해 조작 없이 선박 스스로 운항하는 선박을 의미한다. 자율운항선박의 운항 시 충돌 및 사고 위험도가 큰 지역은 운항 중 선박을 많이 조우하게 되는 항 내 및 연안 지역이다. 실제로 충돌사고의 85% 이상이 항 내 및 연안 지역에서 발생한다. 따라서 자율운항선의 운항 안전성 확보를 위해 항 내 및 연안 지역에서의 운항 안전성을 검토하는 것은 미래 자율운항선 항 내 운용 체계에서 중요한 역할을 하게 된다. 대양에서는 선박 자체의 운항성능이 중요하지만, 항구 입출항 시에는 타선 및 터미널등과의 상호작용이 자율운항선의 입출항 안전성과 직결된다. 따라서 본 연구에서는 자율운항선이 항구 근처에 접근하여 입출항을 위해 대기하고 있는 경우에 입출항 결정을 내릴 수 있는 결정 알고리즘을 위한 해상혼잡도를 예측하는 알고리즘을 개발하는 과정을 소개한다. 혼잡 예측 알고리즘 개발을 위해 선박의 AIS통항데이터를 분석하여 주요 항로를 구분하고 주요 항로의 이용 빈도 및 운항 시점의 선박 집중도 및 충돌위험 상황을 파라미터로 하여 현재 시점부터 2주후 미래까지의 항로 혼잡도를 예측하고, 정확도를 제시한다.