• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.582-585
• /
• 2018

As traffic volume increases and road networks become more complicated, identifying for accurate traffic flow and driving smooth traffic flow are a concern of many countries. There are various analytical techniques and studies which desire to study about effective traffic flow. However, the necessary activity is finding the traffic flow pattern through data visualization including location information. In this paper aim to study a real-world urban traffic trajectory and visualize a pattern of traffic flow with a simulation tool. Our experiment is installing the sensor module in 40 taxis and our dataset is generated along 24 hours and unscheduled routes. After pre-processing data, we improved an open source traffic visualize tools to suitable for our experiment. Then we simulate our vehicle trajectory data with a dots animation over a period of time, which allows clearly view a traffic flow simulation and a understand the direction of movement of the vehicle or route pattern. In addition we further propose some novel timelines to show spatial-temporal features to improve an urban environment due to the traffic flow.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.05a
• /
• pp.38-46
• /
• 2007

본 논문에서는 실시간으로 획득된 영상을 분석하여 움직이는 다수 물체를 검출하고, 카메라를 자동 제어하여 관심 보행자만을 추적하는 시스템을 제안한다. 다수 물체 영역 검출은 차영상과 이전변환 밀도값을 이용한다. 검출된 다수 물체 영역에서 사람의 구조적 정보와 형태 정보를 이용하여 나무들의 흔들림으로 인한 영역이나 차량의 움직임 영역은 제거되고, 관심 보행자 영역만을 검출하였다. 관심 보행자 추적은 무게중심 차를 이용한 움직임 정보와 k-means 알고리즘으로 구한 세 점의 평균 색상 정보를 이용한다. 원거리 관심 보행자는 인식률을 높이기 위해 줌을 실행하여 확대하고, 관심 보행자의 화면상 위치에 따라 카메라 방향을 자동으로 조정하여 관심 보행자반을 연속적으로 추적한다. 실험 결과, 제안한 시스템은 실시간으로 움직이는 다수 물체를 검출하고, 사람의 구조적 특정과 형태 정보로 관심 보행자만을 검출할 수 있었고, 움직임 정보와 색상정보로 관심 보행자를 연속적으로 추적할 수 있었다.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.928-937
• /
• 2015

A portable head up display (HUD) using the optical combiner lens with a 0.47inch LCD panel for a portable multi-windows virtual display is proposed. The proposed system consists of several micro panels, optical devices, and RGB 3in1 light-emitting diodes (LED) for making the full color display, and video and audio format for the high definition multimedia interface (HDMI) for the connecting between HUD and mobile phone. The multi-windows HUD is designed as an alternative to conventional built-in type HUD targeting the mass volume aftermarket at an affordable price.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.61-63
• /
• 2004

지능화된 사물이 스스로 공간의 상황을 인식하여 필요한 행위를 대신해 주는 유비쿼터스 컴퓨팅의 응용 환경 하에서는 언제 어디서나 상황 정보를 분석하여 원하는 사용자에게 실시간으로 알려줄 수 있어야 한다. 그러나, 기존의 e-Logistics 물류 시스템에서는 실물의 흐름과 정보의 흐름간에 불일치가 존재하기 때문에 화물의 위치를 실시간으로 추적하는 것이 불가능하였다. 따라서, 우리는 이러한 문제들을 해결하기 위해 화물에 센싱 가능한 스마트 태그를 부착하고, 이로부터 실시간으로 수집된 정보를 이용하여 사용자에게 유용한 정보를 제공하는 u-Logistics 알림 시스템을 설계하고 구현하였다. 이 논문에서는 u-Logistics 시스템의 전체적인 구조를 기술하고, 특히 규칙의 정의에서부터 알림 서버가 실시간으로 이벤트를 수집하여 원하는 사용자에게 화욜 또는 차량에 대한 정보를 제공하기까지의 알림 시스템의 전반적인 처리 과정을 기술한다. 마지막으로, 물류 환경에의 적용 시나리오를 통하여 u-Logistics 알림 시스템의 구현을 제시한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.4
• /
• pp.21-28
• /
• 2019

As ICT technology develops, researches on the construction of communication system for the rapid processing using ICT technology in case of traffic accidents are actively under way. e-Call (Emergency call) is a vehicle ICT-based emergency rescue system that recognizes and reports traffic accidents. On the other hand, the existing bus information system collects the positioning data through the position tracking system mounted on the bus and transmits it to the center, and then provides various services based on the bus information of the collected buses. In this paper, we designed and implemented an emergency rescue system that using the existing bus information system in order to deal with accidents, failures, and emergency situations on public buses quickly.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.186-195
• /
• 2017

Recently, autonomous vehicles have been studied actively. There are various technologies such as ITS, Connected Car, V2X and ADAS in order to realize such autonomous driving. Among these technologies, it is particularly important to recognize where the vehicle is on the road in order to change the lane and drive to the destination. Generally, it is done through GPS and camera image processing. However, there are limitations on the reliability of the positioning due to shaded areas such as tunnels in the case of GPS, and there are limitations in recognition and positioning according to the state of the road lane and the surrounding environment when performing the camera image processing. In this paper, we propose that LED lights should be installed for autonomous vehicles in tunnels which are shaded area of the GPS. In this paper, we show that it is possible to measure the position of the current lane of the autonomous vehicle by analyzing the color temperature after constructing the tunnel LED lighting simulation environment which illuminates light of different color temperature by lane. Based on the above, this paper proposes a lane positioning technique using tunnel LED lights.

• International Journal of Highway Engineering
• /
• v.6 no.2 s.20
• /
• pp.37-45
• /
• 2004

The asphalt concrete pavement takes various advantages of better riding quality, serviceability and easier maintenance. At the same time, it addresses a weak point of the premature failures due to rapid increasement of traffic volume, heavy vehicles and high temperature in summer. It increases the expenditure of maintenance and repair. In order to improve the performance of asphalt pavement avoiding this premature failure, the use reinforcements with geosynthetics have been considered. Geosynthetics are known as an effective reinforcement to restrain fatigue and reflective cracks in asphalt pavements. In this study, a comprehensive parametric study is conducted to capture the efficiency of geosynthetic-reinforcements using viscoelastic properties of the asphalt concrete(AC) layer. The investigated parameters were reinforcement location, AC layer thickness, temperature distribution across the AC layer and modulus of AC and base layer. As a result of observations, that reinforced asphalt concrete could be used effectively for improving resistance against fatigue cracks and permanent deformation. Especially, when a geogrid was placed at the interface between the asphaltic base and the subbase, tensile stress in the horizontal direction was significantly reduced.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.331-335
• /
• 2007

Among the various application to use FRID, the parking control system widely uses it recently. However, it is rare for the existing systems to integrate several parking lot in the clustered shopping center. This paper proposes the integrated parking control system based on RFID. The system searches optimal path to parking lot with due regard to the position of users who own a tag and the status of parking lots. Then, it transmits the path to mobile devices of the users. The system consists of main server, middle ware to filter and manage tag information, parking lot client to send and manage the status of each parking lot and application module of mobile devices based on WIPI for displaying the optimal path. The main server integrates these components by a database and a new method to filters and manage tag information is newly proposed for the sake of maintaining the position and the direction of the cars in the middle ware. The implemented system shows that it is highly expected to be useful in an advanced integrated parking control system.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1163-1175
• /
• 2021

In autonomous driving, road markings are an essential element for object tracking, path planning and they are able to provide important information for localization. This paper presents an approach to update and measure road surface markers with HD maps as well as matching using inverse perspective mapping. The IPM removes perspective effects from the vehicle's front camera image and remaps them to the 2D domain to create a bird-view region to fit with HD map regions. In addition, letters and arrows such as stop lines, crosswalks, dotted lines, and straight lines are recognized and compared to objects on the HD map to determine whether they are updated. The localization of a newly installed object can be obtained by referring to the measurement value of the surrounding object on the HD map. Therefore, we are able to obtain high accuracy update results with very low computational costs and low-cost cameras and GNSS/INS sensors alone.