• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.161-165
• /
• 2023

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.66-69
• /
• 2007

차량의 종류(차종)에 관한 정보는 ITS(지능형 교통시스템) 및 각종 교통 관련 분야에서 각종 교통 분석 및 지표로 활용될 수 있는 기초 정보이며 교통제어나 차량에 연관된 범죄 등에서 자동차의 인식에 관한 연구의 중요성 때문에 이에 관련된 연구는 오래 전부터 수행되어왔다. 본 논문에서는 차량의 크기를 바탕의 이륜, 소형, 중형, 대형 등 4종으로 차량을 분류 하였다. 차량영역 획득 과정에서 발생하는 잡음 및 조명변화 등 환경적 요인을 극복하고자 윤곽선정보와 배경차분법을 이용해 획득된 차영상 정보의 합영상을 획득하였다. 실험영상으로는 실제 교통관제 시스템에서 획득된 영상을 사용하였으며 실험결과 90%이상의 인식률을 보였다.

• Journal of Web Engineering
• /
• v.21 no.4
• /
• pp.1283-1294
• /
• 2022

Traffic volume is gradually increasing due to the development of technology and the concentration of people in cities. As the results, traffic congestion and traffic accidents are becoming social problems. Detecting and tracking a vehicle based on computer vision is a great helpful in providing important information such as identifying road traffic conditions and crime situations. However, vehicle detection and tracking using a camera is affected by environmental factors in which the camera is installed. In this paper, we thus propose a deep learning based on vehicle classification and tracking scheme to classify and track vehicles in a complex and diverse environment. Using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

• The KIPS Transactions:PartD
• /
• v.10D no.6
• /
• pp.885-896
• /
• 2003

The typws of service using location Information are being various and extending their domain as wireless internet tochnology is developing and its application par is widespread, so it is prospected that LBS(Location-Based Services) will be killer application in wireless internet services. This location information is basic and high value-added information, and this information services make prior GIS(Geographic Information System) to be useful to anybody. The acquisition of this location information from moving object is very important part in LBS. Also the interfacing of acquisition of moving object between MODB and telecommunication network is being very important function in LBS. After this, when LBS are familiar to everybody, we can predict that LBS system load is so heavy for the acquisition of so many subscribers and vehicles. That is to say, LBS platform performance is fallen off because of overhead increment of acquiring moving object between MODB and wireless telecommunication network. So, to make stable of LBS platform, in this MODB system, acquisition of moving object location par as reducing the number of acquisition of unneccessary moving object location. We study problems in acquiring a huge number of moving objects location and design some acquisition model using past moving patternof each object to reduce telecommunication overhead. And after implementation these models, we estimate performance of each model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.3
• /
• pp.114-126
• /
• 2016

Domestic risk factors that are thought to be correlated with highly pathogenic avian influenza (HPAI) outbreak are migratory birds and moving objects such as poultry farm vehicles. In particular, the commercial vehicles that routinely circulate the local and/or remote poultry farms produce are thought to be major HPAI risk factors in South Korea. In this study, the driving histories of the vehicles belonging to poultry farms and/or commercial companies registered in the Korea Animal Integrated System (KAHIS) were analyzed using statistical and social networking tools in a Geographic Information System (GIS) in order to understand the pattern of the HPAI (H5N8) outbreak that occurred in 2014 in South Korea. Based on the 2014 HPAI outbreak patterns, HPAI-infected poultry farms were categorized according to geological features. The HPAI-infected poultry farms were categorized as 'regional-accumulation', 'regional-distribution', 'metropolitan-accumulation', 'metropolitan-distribution' and 'national-distribution' in endemic or non-endemic regions. We were able to categorize most HPAI-infected poultry farms into the five proposed categories, but further studies are required to categorize all such farms. Based on this categorization system, we propose efficient but economical prevention boundaries in South Korea. We strongly believe that our research could hugely impact government decisions to estimate the prevention area.

• Journal of Korean Society of Transportation
• /
• v.34 no.1
• /
• pp.68-80
• /
• 2016

Interest in freeway truck traffic has increased largely due to greater safety concerns regarding truck-related crashes. The negative interactions between slow-moving trucks and other vehicles are a primary cause of hazardous conditions, which lead to crashes with larger speed variations. To improve operational efficiency and safety, providing a climbing lane that separates slow-moving trucks from higher performance vehicles is frequently considered when upgrading geometrics. This study developed an operations strategy for freeway climbing lanes based on traffic conditions in real time. To consider traffic safety when designing a dynamic strategy to determine whether a climbing lane is closed or open, various factors, including the level of service (LOS) and the percentage of trucks, are investigated through microscopic simulations. A microscopic traffic simulator, VISSIM, was used to simulate freeway traffic streams and collect vehicle-maneuvering data. Additionally, an external application program interface, VISSIM's COM-interface, was used to implement the proposed climbing lane operations strategies. Surrogate safety measures (SSM), including the frequency of rear-end conflicts and, were used to quantitatively evaluate the traffic safety using an analysis of individual vehicle trajectories obtained from VISSIM simulations with various operations scenarios. It is expected that the proposed algorithm can be the backbone for operating the climbing lane in real time for safer traffic management.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.11
• /
• pp.44-52
• /
• 2011

In this article, we present a QoS-guaranteed IP mobility management scheme of Internet service for fast moving vehicles with multiple wireless network interfaces. The idea of the proposed mechanism consists of two things. One is that new wireless connections are established to available wireless channels whenever the measured data rate at the vehicle equipped with mobile gateway drops below to the required data rate of the user requirement. The other is that parallel distribution packet tunnels between an access router and the mobile gateway are dynamically constructed using multiple wireless network interfaces in order to guarantee the required data rate during the mobile gateway's movement. By doing these methods, the required data rate of the mobile gateway can be preserved while eliminating the possible delay and packet loss during handover operation, thus resulting in the guaranteed QoS. The architecture of the IETF standard HMIPv6 has been extended to realize the proposed scheme, and detailed algorithms for the extension of HMIPv6 has been designed. Finally, simulation has been done for performance evaluation, and the simulation results show that the proposed mechanism demonstrates guaranteed QoS during the handover with regard to the handover delay, packet loss and throughput.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.8
• /
• pp.41-50
• /
• 2012

Most of the developed countries and Korea have continued to invest much money in developing low-carbon vehicles such as electric car, methanol car and hydrogen car to replace the conventional fossil fuel vehicles. Government and local governments of each country, however, grope to construct roads for bicycle and public bicycle rental systems because bicycle is the only ultimate and feasible non-pollution transportation. Most of the current bicycle monitoring systems have achieved automation of rental process in bicycle stations, but they can not monitor bicycles in use. This paper develops GPS-CDMA modem combined terminals and implements a LBS-based bicycle monitoring system using them for public bicycle rental system. The monitoring system collects location information from GPS-CDMA modem combined terminals attached on bicycles and presents the moving tracks of bicycles on a GIS map for easy return and redistribution of bicycles. Also, the system helps to prevent from theft and vandalism of bicycles and to recommend the nearest bicycle station.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.1
• /
• pp.29-37
• /
• 2015

In this study, the estimation of axial load and total axial load was conducted using Bridge Weigh-in-Motion(BWIM) technique which generally consists of devices for measuring the strain induced in the bridge by the vehicles. axle detectors for collecting information on vehicle velocity and axle spacing. and data acquisition equipment. Vehicle driving test for the development of the BWIM system is necessary but it needs much cost and time. In addition, it demands various driving conditions for the test. Thus, we need a numerical-simulation method for resolving the cost and time problems of vehicle driving tests, and a way of measuring bridge response according to various driving conditions. Using a bridge model reflecting the dynamic characteristic contributes to increased accuracy in numerical simulation. In this paper, we conduct a numerical simulation which reflects the dynamic characteristic of a bridge using the Bridge Weigh-in-Motion technique, and suggest overload vehicle enforcement technology.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.2
• /
• pp.87-95
• /
• 2010

A Vehicular Ad-Hoc Network (VANET) is form of the Mobile Ad-hoc Network (MANET) to provide temporary communication among vehicles via wireless links. In VANET, the vehicle is one of the nodes in networks and communicates with each other. However, the wireless links disconnect very frequently, because vehicles have mobility and move freely. The reason why data accessibility degrades is that disconnection occurs frequently. To improve data accessibility, data replica allocation methods that made group to allocate data replica have proposed in MANET. However, those are not suitable because it is difficult to maintain stable links among the nodes moving fast by centralized group. In this paper, we proposed TBG (Tree Based Grouping) to allocate data replica with the distributed grouping method. Each node has own TBG and allocates data replica based on stability of links to improve data accessibility. The experiment demonstrates that the proposed method outperforms traditional methods in term of data accessibility.