• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.16 no.6
• /
• pp.102-108
• /
• 2002

This paper handles the design of a real time traffic data acquisition system using loop detector and piezo-electric sensor to acquire the vehicle information EISA compatible parallel I/O interface card is designed to sample 30 I/O channels at variable rates for raw traffic data acquisition. The control software is designed to generate the traffic data informations from the raw data. The traffic data information provides vehicle length, speed, number of axles, etc. Vehicle types are detected and categorized into eleven types from the vehicle length, axles positions and axle counts information. The traffic information is formed into packet and transferred to the remote hosts through serial communications for ITS applications.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.75-78
• /
• 2006

이 논문은 이동 차량의 궤적 정보 관리를 통한 물류 관리 시스템을 제안한다. 물류 시스템은 물류 센터에서 차량과 배송 물품의 위치를 지속적으로 모니터링하고, 이와 연관된 서비스를 제공하는 시스템이다. 따라서 물류 차량의 실시간 위치 정보관리가 필수적이다. 제안된 시스템은 기존의 지리 정보와 더불어 실세계 모바일 환경에서 물류 배송 정보의 효율적 관리 기능을 지원한다. 또한 효과적인 물류 이동 경로 관리 및 검색을 위하여 시공간 색인 기법을 적용하였다. 제안된 시스템은 물류 관리 뿐만 아니라 이와 유사한 서비스를 제공하는 차량 추적 시스템, 위치 기반 서비스 등과 같이 모바일 환경에서 실시간으로 변화하는 관리 대상 객체의 위치 정보를 관리하는 분야에 적용 가능하다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.693-696
• /
• 2004

무선 컴퓨팅 기술 및 이동 객체의 위치를 정확하게 추적할 수 있는 GPS 기술의 발달로 인하여 물류 차량 관리, 항공 교통 통제 등과 같은 실시간 환경의 위치 정보 응용시스템의 개발이 활발해지고 있다. 특히, 지리정보와 위치정보를 이용한 현장업무처리 시스템과 차량의 위치를 관제 센터에서 실시간으로 파악하는 차량 위치 추적 시스템에 관한 연구가 대표적인 응용 시스템으로 등장하였다. 이러한 변화에 따라 이동성을 지원하는 무선 단말기를 기반으로 한 Mobile GIS 환경에서의 위치 정보 활용은 큰 관심을 불러일으키고 있으며, 또한 이러한 서비스를 효율적으로 제공하기 위해서 위치 기반 서비스 (LBS:Location Based Service)의 기술개발이 필요하게 되었다. 본 논문에서는 전력설비 고장복구업무에 LBS를 적용하기 위해 차량에 장착하는 MDT에서 국가기본도와 전력설비도 지리정보 서비스가 가능한 Mobile GIS Engine을 설계하고 구현한 결과를 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.178-180
• /
• 2022

최근 차량 플랫폼의 발달로 인하여 차량 내 ECU 간의 정보교환이 증가하였다. 기존의 센트럴 게이트웨이 아키텍처 네트워크에서는 늘어난 정보교환으로 인한 과부하가 발생하였다. 따라서 ECU 들끼리 Domain 을 형성하도록 하여 DCU 를 활용한 Domain 기반 차량용 통신 아키텍처가 해법으로 제시되었다. 본 연구에서는 DCU 와 ECU 간의 네트워크 플랫폼을 소형 전동차를 이용하여 제작한다. 이 네트워크를 검증하기 위하여 목표물 추적 알고리즘을 통해 네트워크가 정상 작동하는지 확인한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.1
• /
• pp.153-159
• /
• 2012

Driver's view has blind spot of automobile surroundings due to physical components of automobile architecture. Obstacles on blind spot are the cause of car destruction and car accidents. Cars which produced in recent have obstacle detection sensors and rear view cameras which provide information of obstacles on the blind sopt, and have also AVM(Around View Monitoring) which provides automobile surroundings for driver's safe driving. During a low-speed travel while parking or moving in a narrow street, a driver get help for safe driving by taking information of automobile surroundings using the above-mentioned devices. In this paper, we present a design and implementation of a 4-sided monitoring (4SM) system, which helps a driver see an integrated view of a vehicle's perimeter at a glance, using a car PC connected to four cameras installed on the front, rear, left, and right sides.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.137-148
• /
• 2005

The position information of individual vehicles on a road at every time instant can be used to analyze the microscopic behaviors of driving of each vehicle. The limited information obtained from previous imaging technology such as traffic volume and interval velocity cannot be used to explore such microscopic traffic conditions. Also, information gathering for the microscopic behaviors by manual analysis of captured video takes large amount of time and man-power. In the paper we develop the rule-based vehicle tracking technology from which the position information of individual vehicles on a road at every time instant can be automatically obtained. Also, we extract the position data of driving vehicles on a road, length of 130m for every 0.05 second, and calculate the velocity of each traced vehicles to compare with the real velocity for the verification of accuracy. In the future, this type of tracking techniques based on video analysis can be widely used to provide the practically important information of road traffic conditions and to analyze the academically important microscopic behaviors of driving patterns.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.81-93
• /
• 2022

Recently, there have been many studies on object recognition around the vehicle and recognition of traffic signs and traffic lights in autonomous driving. In particular, such the recognition of traffic lights is one of the core technologies in autonomous driving. Therefore, many studies for such the recognition of traffic lights have been performed, the studies based on various deep learning models have increased significantly in recent. In addition, as a high-quality AI training data set for voice, vision, and autonomous driving is released on AIHub, it makes it possible to develop a recognition model for traffic lights suitable for the domestic environment using the data set. In this study, we developed a recognition model for traffic lights that can be used in Korea using the AIHub's training data set. In particular, in order to improve the recognition performance, we used various models of YOLOv4 and YOLOv5, and performed our recognition experiments by defining various classes for the training data. In conclusion, we could see that YOLOv5 shows better performance in the recognition than YOLOv4 and could confirm the reason from the architecture comparison of the two models.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.11
• /
• pp.263-270
• /
• 2019

Vehicular cloud computing is a new emerging technology that can provide drivers with cloud services to enable various vehicular applications. A vehicular cloud is defined as a set of vehicles that share their own resources. Vehicles should collaborate with each other to construct vehicular clouds through vehicle-to-vehicle communications. Since collaborating vehicles to construct the vehicular cloud have different speeds, directions and locations respectively, the vehicular cloud is constructed in multi-hop communication range. Due to intermittent wireless connectivity and low density of vehicles with the limited resources, the construction of vehicular cloud with multi-hop communications has become challenging in vehicular environments in terms of the service success ratio, the service delay, and the transmitted packet number. Thus, we propose a multi-hop vehicular cloud construction protocol that increases the service success ratio and decreases the service delay and the transmitted packet number. The proposed protocol uses a connection time-based intermediate vehicle selection scheme to reduce the cloud failure probability of multi-hop vehicular cloud. Simulation results conducted in various environments verify that the proposed protocol achieves better performance than the existing protocol.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.701-702
• /
• 2020

본 논문에서는 Jetson-Nano와 데스크탑에서 OpenCV와 YOLOv3 실시간 객체 인식 알고리즘을 이용하여 웹캠을 통해 주차장 등의 출입 차량 인식 통계 시스템을 개발하였다. 최근 에지컴퓨팅에 관심이 증가하고 있는 시점에서 Nvidia사에서 개발하여 보급하고 있는 Jetson-Nano에 YOLOv3 tiny와 OpenCV를 이용하여 차량인식을 수행하고, 구글에서 개발한 오픈 소스 Tesseract-OCR을 이용해 차량번호인식하여 입출차 혹은 주차시 차량정보를 확인할 수 있다. 딥러닝 학습 알고리즘에서 전기차 번호판의 특징점을 인식하여 전기차를 판별하여 일반차량이 전기차 주차구역에 불법주차하는 것을 모니터링할 수도 있다. 출입한 차량 데이터 베이스에서 입출차 시각, 차량번호, 전기차여부등이 확인 가능하다.

• Journal of KIISE:Information Networking
• /
• v.37 no.6
• /
• pp.420-430
• /
• 2010

Due to increasing demand for improving road safety and optimizing road traffic, Vehicular Ad-Hoc Networks (VANET) have been subject to extensive attentions from all aspects of commercial industry and academic community. Security and user privacy are fundamental issues for all possible promising applications in VANET. Most of the existing security proposals for secure VANET concentrate authentication with privacy preservation in vehicle-to-vehicle (V2V) and vehicle-to-roadside infrastructure (V2I) communications and require huge storage and network capacity for management of revocation list. Motivated by the fact, we propose a new scheme with security and privacy preservation which combines V2V and V2I communication. With our proposed scheme, the communication and computational delay for authentication and overhead for management of revocation list can be significantly reduced due to mutual authentication between a vehicle and a Roadside Unit (RSU) requires only two messages, and the RSU issues the anonymous certificate for the vehicle on behalf of the Trust Authority (TA). We demonstrate that the proposed protocol cannot only guarantee the requirements of security and privacy but can also provide efficiency of authentication and management of revocation list.