• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.141-144
• /
• 2000

본 논문은 교통 안전 표지판 인식에 적용이 가능한 새로운 영상의 특징 정보 추출 방법을 제안한다. 제안된 방법은 인간의 인식 시스템에서 이용하는 기본 특징인 색과 형태정보를 이용하여 영상 인식에 적용한다. 색 정보의 추출은 RGB성분의 히스토그램 분포를 이용하고 형태 정보의 추출은 기하학적인 형태 정보 추출 방법과 모멘트를 이용한다. 본 논문은 유사 영상 검색을 위한 새로운 특징 정보 추출 방법과 간단한 특징 정보 표현 그리고 계산량의 감소 효과를 얻었다.

• Proceedings of the Safety Management and Science Conference
• /
• 2002.11a
• /
• pp.43-47
• /
• 2002

• Journal of Korean Society of Transportation
• /
• v.26 no.5
• /
• pp.195-204
• /
• 2008

When the drivers try to read an information on road signs, they can reach their destinations successfully. In this situation, human factors, road signs and geometric condition regarded as the most important factors for a safe driving should be a well-balanced relationship mutually. This research aims to prove the factors obstructing a safe driving, while drivers try to read an information on road signs for the next destination. For this sake, driving simulator was used and human factors, road signs etc. were considered in this experiment. The statistical analysis indicated what factors disturb a safe driving. The probability function using a Logistic Model was presented in this study. This result and experience will be used as a basic data in designing better road signs.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.40-42
• /
• 2023

해상등부표는 선박 통항의 안전을 위해서 필요한 시설로, 낚시 배와 소형 어선을 포함한 선박의 항로표지에 중요한 역할을 한다. 그런데 야간에는 해상에 설치된 등부표의 위치나 번호판 식별이 어려워 소형 어선이나 선박이 등부표에 가까이 접근하여 등부표를 발견하지 못하는 경우 충돌하여 선박이 파손되거나 인명사고가 발생한다. 이 적용사례는 소형 어선이나 선박이 야간에도 등부표의 위치와 번호판을 손쉽게 식별할 수 있도록 등부표에 윤곽표시조명장치를 구비하여 충돌사고의 예방과 항로표지서비스를 향상시키는 목적을 갖고 개발을 추진하였다. 윤곽표시조명장치는 태양광전원을 이용하여 IP68 방수형 고효율 LED조명을 구비하여 멀리서도 식별이 가능하여 야간에도 신속하게 안전한 항로를 확보할 수 있게 되었으며, 근접센서 콘트롤러를 결합하여 선박이 등부표에 가까이 접근하면 LED조명이 점멸하며 깜빡이면서 충돌위험을 알리는 경보기능을 추가하여 등부표와 충돌사고를 예방할 수 있게 되어 항로표지서비스의 향상을 도모하게 되었다.

• Proceedings of the KOR-KST Conference
• /
• 1999.10a
• /
• pp.129-134
• /
• 1999

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.298-300
• /
• 2023

국제수로기구는 해양정보 교환을 위한 제품표준 개발 지원을 위해 S-100 개발하고 현재 그 버전으로 5판으로 개정 하였다. 항로표지 정보는 항행경보와 항로표지 상태정보로 제공되는데, 국제수로기구는 해사안전정보(MSI)의 디지털 데이터 제작 및 교환 위해 S-124 개발되었고, 국제항로표협회는 S-201 항로표지 정보표준 개발을 완료하고, S-125 항로표지 상태정보 표준개발 진행 중이다. IALA/IHO는 S-100/S-200 개발 공동워크숍을 개최하고, S-125 항로표지 정보서비스에 대한 시연 및 워크숍 필요성 강조하였다. 본 연구는 항로표지 정보 서비스를 싱가포르 MPA와 협력하여 시험 시나리오 및 검증 계획을 수립하였다. S-124, S-125 기반의 정보 제공 서비스 및 선박 내비게이션을 통한 검증을 진행할 계획이며, 검증 결과는 IALA, IHO 회의로 보고할 계획이다. 항로표지 정보서비스 시험 결과는 관련 국제표준 개발에 기여하고, 항해환경에 해당 서비스 정착하는데 도움이 될 것으로 판단된다.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• Journal of Korea Spatial Information System Society
• /
• v.10 no.2
• /
• pp.13-24
• /
• 2008

A next generation video based car navigation is researched to supplement the drawbacks of existed 2D based navigation and to provide the various services for safety driving. The components of this navigation system could be a load object database, identification module for load lines, and crossroad identification module, etc. In this paper, we proposed the traffic lights and road sign recognition method which can be effectively exploited for crossroad recognition in video-based car navigation systems. The method uses object color information and other spatial features in the video image. The results show average 90% recognition rate from 30m to 60m distance for traffic lights and 97% at 40-90m distance for load sign. The algorithm also achieves 46msec/frame processing time which also indicates the appropriateness of the algorithm in real-time processing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.597-598
• /
• 2018

Recently, the future traffic system is mainly aiming traffic safety by collecting, managing and providing traffic information using traffic system. But In this paper, we propose traffic safety using traffic safety mark which is currently utilized transportation infrastructure. The vehicle receives the sensed data with the traffic safety sign as a host, and carries out communication between the vehicles or the infrastructure. By using the information of sensing data, various information can be obtained. In addition to the construction section, traffic accidents can also be utilized. Therefore, this paper is designed to simplify the frame of sensing data and contribute to traffic safety through continuous research.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2D
• /
• pp.235-242
• /
• 2008

Due to the lack of judgement in an information processing on road sign, older drivers usually are having a hard time driving than young group. Furthermore, according to increasing in aging population, older drivers in Korea have been growing much faster. That means research for older drivers' characteristics and the number of guide name for road sign should be needed. In accordance with suggestions, this study was carried out the number of guide names for road sign with a variety of ages from the twenties to the seventies. For the sake of this study, statistical verification was conducted to confirm a change of speed, a reading time and a misreading rate with Driving Simulator and Electrooculogram tool. As the results of study, change of speed in the age range has shown that the higher the proportion of age, the lower the rate of velocity. Also reading time in the age range with regression analysis found that the higher the proportion of age, the higher the rate of reading time by 0.106sec. Finally, a binary logistic model was used to find the main factors. As the results, 4 number of guide names for road sign have been the best of them for older driver. The result of this study verified the importance of ideal guide numbers on road sign for older driver and proved itself to be an effective method to determine the road safety for the road signs.