교통안전시설물의 관리는 도로교통의 안전과 직결되는 문제이다. 운전자는 신호등, 표지판, 노면표시 등을 통해 운전에 필요한 정보 를 얻는다. 노후된 표지판과 노면표시는 운전자에게 잘못된 정보를 제공할 수 있으므로 주기적인 시설물의 관리가 필요하다. 본 연구 는 딥 러닝 기술을 활용해 운전자 시각의 영상 자료에서 교통안전표지를 자동으로 탐지하고자 하며, 교통안전표지의 공통된 색상 특 징을 기반으로 클래스를 그룹으로 묶어 데이터셋을 구축하는 방법을 제안한다. 객체탐지의 성능지표로 널리 활용되는 mAP를 사용해 클래스 묶음 여부에 따른 탐지 성능을 비교한 결과, 색상 기반 클래스 묶음을 적용한 모델의 탐지 성능이 비교군에 비해 약 36% 상승 함을 확인하였다.

PURPOSES: The purpose of this study is to estimate the impact of variable message signage (VMS) on traffic safety as a function of road curve radius using statistical methods. METHODS: In order to analyze the impact of VMS installations on traffic safety, travel speed, lateral distance, and geometric data relating to road curvature in each study area was acquired and analyzed for the impact of providing VMS information on driver performance and traffic safety using statistical methods including student t-test, Mann-Whitney test, and the Anderson-Darling test for estimating traffic safety hazard zone in each lane. RESULTS: As a result of analyzing driver performance characteristics before and after providing VMS information, it was determined that by providing VMS information, mean travel speed is deceased and vehicles are driven with increased precision, following the centerline in the first and second lanes. Also the results of analyzing traffic safety impacts of VMS indicate that traffic safety performance factors in the first lane of the Gapyeong section can, on average, increase in the left and right side of the lane by 19.22% and 68.98%, respectively, and in the case of the second lane, safety impacts, on average, can increase in both sides by 100%. For the Hongcheon section, traffic safety impacts in the first lane, on average, can increase along the left and right sides of the lane by 32.31% and 47.18%, and within the second lane, traffic safety can be increased along the left and right side of the lane by 10.97% and -0.01%, respectively. CONCLUSIONS: Based on the results of this study, the impact on traffic safety obtained by providing VMS information for road sections with smaller curve radii is greater than can be obtained for road sections with larger curve radii.

PURPOSES: This study is to develop a road traffic sign recognition and automatic positioning for road facility management. METHODS: In this study, we installed the GPS, IMU, DMI, camera, laser sensor on the van and surveyed the car position, fore-sight image, point cloud of traffic signs. To insert automatic position of traffic sign, the automatic traffic sign recognition S/W developed and it can log the traffic sign type and approximate position, this study suggests a methodology to transform the laser point-cloud to the map coordinate system with the 3D axis rotation algorithm. RESULTS: Result show that on a clear day, traffic sign recognition ratio is 92.98%, and on cloudy day recognition ratio is 80.58%. To insert exact traffic sign position. This study examined the point difference with the road surveying results. The result RMSE is 0.227m and average is 1.51m which is the GPS positioning error. Including these error we can insert the traffic sign position within 1.51m CONCLUSIONS: As a result of this study, we can automatically survey the traffic sign type, position data of the traffic sign position error and analysis the road safety, speed limit consistency, which can be used in traffic sign DB.