• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.2
• /
• pp.8-17
• /
• 2008

This paper proposes a robust license plate extraction method from images taken under unconstrained environments. Utilization of the color and the edge information in complementary fashion makes the proposed method deal with not only various lighting conditions, hilt blocking artifacts frequently observed in compressed images. Computational complexity is significantly reduced by applying Hough transform to estimate the skew angle, and subsequent do-skewing procedure only to the candidate regions. The true plate region is determined from the candidates under examination using clues including the aspect ratio, the number of zero crossings from vertical scan lines, and the number of connected components. The performance of the proposed method is evaluated using compressed images collected under various realistic circumstances. The experimental results show 94.9% of correct license plate extraction rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.316-318
• /
• 2006

본 논문에서는 차세대 지능형 교통시스템인 UTIS(Urban Traffic Information System)의 빠른 접속 요구 조건을 만족하기 위한 DLC(Dynamic Limited Contention) 알고리즘을 제안한다. UTIS 네트워크는 고속으로 이동하는 차량에 설치된 모바일 노드와 도로 변에 설치된 노변 기지국으로 구성되며, 이 네트워크를 통해서 IP 데이터 그램의 전송 서비스, 방송 데이터를 실시간으로 전송하는 실시간 전송 서비스 그리고 차량의 위치를 계속적으로 알려 주는 위치 탐색 서비스를 지원한다. 이러한 전송 서비스를 지원하기 위해서 UTIS는 물리 계층과 MAC 계층으로 구성된다. 그러나 UTIS에서는 차량의 고속 이동으로 인해서 셀(cell)간의 핸드오프가 빈번히 발생하고 또한 위치 추적과 방송 서비스와 같은 실시간 전송 서비스를 지원해야 하기 때문에 기존의 802.11 MAC을 사용할 수 없다. 즉 UTIS에서의 빠른 등록 요구 조건을 충족시키기 위해 기존의 802.11에서 사용하는 경쟁(contention) 방식은 비효율적이다. 본 논문에서는 셀 내에 도착하는 노드 수에 따라 경쟁을 하는 그룹의 크기를 동적으로 조절하는 DLC 알고리즘을 제안한다. 기존의 UTIS에서는 그룹 크기를 정적으로 결정하고 모바일 노드는 자신의 주소에 이 정적 그룹 크기로 modulo하여 자신의 속한 그룹을 초기에 계산한다. 기지국이 접속해야하는 그룹을 폴링 메시지로 지정할 때 그 그룹에 속한 모바일 노드들만이 제한적으로 경쟁하게 된다. 이러한 정적인 그룹 크기는 셀 내에의 노드의 숫자와 그룹 크기의 분포를 고려하지 않는 방식으로 비효율적이다. 본 DLC 알고리즘에서는 전 폴링 주기 동안에 경쟁하는 노드의 빈도수를 계속적으로 추적하여 등록 시점에 경쟁하는 그룹의 개수를 동적으로 조절하게 된다. 이러한 방식은 UTIS와 같이 접속 시간이 제한적이고 접속하려는 노드 수가 빠르게 변화하는 환경 하에서 기존의 802.11 MAC 프로토콜과 정적인 그룹 크기 방식에 비해 효율적이다.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.151-160
• /
• 2010

For the realization of future intelligent transportation systems, fine-grained lane-by-lane traffic monitoring and control functionalities are among the most important technology barriers to overcome. To satisfy the accuracy requirement for traffic monitoring, a GNSS receiver network is designed. The designed receiver network consists of three different types of entities; reference server, broadcaster, and client. For deployment flexibility, all the entities utilize the international message standard RTCM SC-104 version 3.0. For fine-grained traffic monitoring, the client is designed to utilize position-domain carrier-smoothed-code filters to provide accurate vehicle coordinates in spite of frequent addages and outages of visible satellites. An experiment result is presented to evaluate the positioning accuracy of the proposed method.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.11a
• /
• pp.329-350
• /
• 2017

e-내비게이션은 유엔 산하 국제해사기구(IMO)가 2020년 국제적인 시행을 목표로 도입한 차세대 해양안전 종합관리시스템이다. 각종 해상 운항정보를 디지털화 해 선박 운항자에게 실시간 맞춤형 정보를 제공해 준다. 육상에서 차량용 내비게이션처럼 선박을 운항하는 데 운항항로, 날씨, 돌발 변수 등을 제공하면서 선박 사고를 줄이는 역할을 한다. 크루즈와 같은 큰 선박부터 작은 낚시용 선박에서도 이용이 가능하다. 해수부는 2020년 이후 약 1,000조원의 시장이 열릴 것으로 내다보고 있다. 진입 장벽이 높은 해상장비 시장에 우리나라도 ICT 강점을 바탕으로 디지털로 변화하는 이 시장에 주도권을 잡기 위해 노력중이다. 이를 위하여 e-내비게이션 분야의 미국 특허정보를 확보하여 DB화 하고, DB에서 제공하는 특허적 행위(M&A, 특허 매입, 신규 R&D 등)를 중심으로 하는 미래기술예측 분석틀을 활용하여 유망기술을 발굴하고자 한다. 미래기술예측 분석틀은 미래기술예측의 3대 주제를 (1) 미래 기술의 대상과 범위, (2) 미래 기술의 주인과 수혜자, (3) 미래 기술로의 투자 시점으로 설정하고, 3~10년까지의 근미래(Near Future Only), 측정 및 검증 가능한 미래(Data Oriented), 미래를 만드는 힘 있는 주체에게만(Activity Oriented) 집중하여 분석을 시도하고자 한다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.6
• /
• pp.619-623
• /
• 2008

A lane detection system is one of the major components of intelligent vehicle systems. Difficulties in lane detection mainly come from not only various weather conditions but also a variety of special environment. This paper describes a simple and stable method for the broken lane tracking in various environments. Probabilistic Hough Transform (PHT) and the Least-square method (LSM) are used to track and correct the lane orientation. For the efficiency of the proposed method, two regions of interest (ROIs) are placed in the lower part of each image, where lane marking areas usually appear with less intervention in our system view. By testing in both a set of static images and video sequences, the experiments showed that the proposed approach yielded robust and reliable results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.765-773
• /
• 2009

Currently Telematics traffic information services have been various because we can collect real-time traffic information through Intelligent Transport System. In this paper, we proposed and implemented a short-term traffic information prediction model for giving to guarantee the traffic information with high quality in the near future. A Short-term prediction model is for forecasting traffic flows of each segment in the near future. Our prediction model gives an average speed on the each segment from 5 minutes later to 60 minutes later. We designed a Bayesian network for each segment with some casual nodes which makes an impact to the road situation in the future and found out its joint probability density function on the supposition of GMM(Gaussian Mixture Model) using EM(Expectation Maximization) algorithm with training real-time traffic data. To validate the precision of our prediction model we had conducted various experiments with real-time traffic data and computed RMSE(Root Mean Square Error) between a real speed and its prediction speed. As the result, our model gave 4.5, 4.8, 5.2 as an average value of RMSE about 10, 30, 60 minutes later, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.2 s.7
• /
• pp.23-31
• /
• 2005

ITS(Intelligent Transportation System) implementing information collection services and information support services for cars of moving fast needs a communication system of special aim such as RF-DSRC(Radio Frequency Dedicated Short Range Communication). Before RSE(Road Side Equipment) and OBE(On-Board Equipment) will be able to communicate RF-DSRC, OBE first have to request Link Initialization Access using ACTC(Activation Channel) in allocated ACTS(Activation Slot) by Slotted ALOHA. Even though Link Initialization Access is a important element to decide performance of communication system, optimal mathematic modeling study of Link Initialization Access which is adapted RF-DSRC characteristics is not enoush. So, in this paper, we propose mathematical modeling about Link Initialization Access of RF-DSRC. And then we computed Link Initialization Access probability defining offer load(G) which is adapted RF-DSRC characteristics for analyzing performance of modeling.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.9
• /
• pp.799-808
• /
• 2012

Bit operation of scrambler in the WAVE System become less efficient because parallel processing is impossible in terms of hardware and software. In this paper, we propose algorism to find the starting position of the matrix table. Also, when bit operation algorithm of scrambler and algorithms for matrix table, algorithm used to find starting position of the matrix table were compared with the performance as 8 bit, 16bit, 32 bit processing units. As a result, the number of processing times per second could be done 2917.8 times more in an 8-bit, 5432.1 times in a 16-bit, 10277.8 times in a 32 bit. Therefore, algorithm to find the starting position of the matrix table improves the speed of the scrambler in the WAVE and the receiving speed of a variety of information gathering and precision over the Vehicle to Infra or Vehicle to Vehicle in the Intelligent Transport Systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.96-107
• /
• 2015

VANET technologies provide real-time traffic information for mitigating traffic jam and preventing traffic accidents, as well as in-vehicle infotainment service through Telematics/Intelligent Transportation System (ITS). Due to the rapid increasement of various requirements, the vehicle communication with a limited resource and the fixed frame architecture of the conventional techniques is limited to provide an efficient communication service. Therefore, a new flexible operation depending on the surrounding situation information is required that needs an adaptive design of the network architecture and protocol for efficiently predicting, distributing and sharing the context-aware information. In this paper, Vehicle-to-Infrastructure (V2I) based on communication between vehicle and a Road Side Units (RSU) and Vehicle-to-Vehicle (V2V) based on communication between vehicles are effectively combined in a new MAC architecture and V2I and V2V vehicles collaborate in management. As a result, many vehicles and RSU can use more efficiently the resource and send data rapidly. The simulation results show that the proposed method can achieve high resource utilization in accordance. Also we can find out the optimal transmission relay time and 2nd relay vehicle selection probability value to spread out V2V/V2I collaborative schedule message rapidly.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.948-956
• /
• 2014

Today, Intelligent Vehicle Detection System seeks to reduce the negative factors, such as accidents over to get the traffic information of existing system. This paper proposes detection algorithm for the illegal U-turn vehicles which can cause critical accident among violations of road traffic laws. We predicted that if calculated optical flow vectors were shown on the illegal U-turn path, they would be cause of the illegal U-turn vehicles. To reduce the high computational complexity, we use the algorithm of pyramid Lucas-Kanade. This algorithm only track the key-points likely corners. Because of the high computational complexity, we detect center lane first through the color information and progressive probabilistic hough transform and apply to the around of center lane. And then we select vectors on illegal U-turn path and calculate reliability to check whether vectors is cause of the illegal U-turn vehicles or not. Finally, In order to evaluate the algorithm, we calculate process time of the type of algorithm and prove that proposed algorithm is efficiently.