• Korean Journal of Construction Engineering and Management
• /
• v.20 no.6
• /
• pp.34-43
• /
• 2019

The maintenance cost for road pavement is gradually increasing due to the continuous increase in road extension as well as increase in the number of old routes that have passed the public period. As a result, there is a need for a method of minimizing costs through preventative grievance preventive maintenance requires the establishment of a strategic plan through accurate prediction of road pavement. Hence, In this study, the deep neural network(DNN) and the recurrent neural network(RNN) were used in order to develop the expressway pavement damage prediction model. A superior model among these two network models was then suggested by comparing and analyzing their performance. In order to solve the RNN's vanishing gradient problem, the LSTM (Long short-term memory) circuits which are a more complicated form of the RNN structure were used. The learning result showed that the RMSE value of the RNN-LSTM model was 0.102 which was lower than the RMSE value of the DNN model, indicating that the performance of the RNN-LSTM model was superior. In addition, high accuracy of the RNN-LSTM model was verified through the comparison between the estimated average road pavement condition and the actually measured road pavement condition of the target section over time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.84-99
• /
• 2021

As the micro-mobility market grows, the demand for route guidance, that includes uphill information as well, is increasing. Since the climbing angle depends on the electric motor uesed, it is necessary to establish an uphill road DB according to the threshold standard. Although road alignment information is a very important element in the basic information of the roads, there is no information currently on the longitudinal slope in the road digital map. The High Definition(HD) map which is being built as a preparation for the era of autonomous vehicles has the altitude value, unlike the existing standard node link system. However, the HD map is very insufficient because it has the altitude value only for some sections of the road network. This paper, hence, intends to propose a method to generate the road longitudinal slope using currently available data. We developed a method of computing the longitudinal slope by combining the digital elevation model and the standard link system. After creating an altitude at the road link point divided by 4m based on the Seoul road network, we calculated individual slope per unit distance of the road. After designating a representative slope for each road link, we have extracted the very steep road that cannot be climbed with personal mobility and the slippery roads that cannot be used during heavy snowfall. We additionally described errors in the altitude values due to surrounding terrain and the issues related to the slope calculation method. In the future, we expect that the road longitudinal slope information will be used as basic data that can be used for various convergence analyses.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2006.06a
• /
• pp.5-8
• /
• 2006

본 논문에서는 3차원 좌표를 얻을 수 있는 카메라 Calibration 알고리듬을 확립하고, View Frustum(V.F.) 모델을 이용하여 도로의 영상을 모델화하였다. 그리고 주행하는 차선 내에 존재하는 선행차량의 위치측정 및 차량까지의 거리를 정확히 인식하기 위해 피칭오차를 보정하며 실시간으로 계측하는 알고리듬을 제안하였다. 기존의 많은 추돌 경보시스템(CWS)들은 도로가 평면이라 가정하여 도로와 차량사이의 기하적인 변화에 따른 오차 특성을 고려하지 않았다. 이를 보완하고자 본 논문에서는 카메라 Calibration 알고리듬을 적용하여 실세계 좌표계와 영상좌표계 사이의 기하해석으로 사영행렬을 추출하였고, V.F. 모델을 이용하여 소실점의 기하적인 해석을 통하여 차량의 피칭변화에 따른 오차특성을 실시간으로 보정하였다. 실험결과 거리의 오차를 2%이하로 줄일 수 있어 피칭변화에 강인함을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1350-1353
• /
• 2013

자동차의 안전성 향상에 대한 연구는 오랜 기간 다양한 분야에서 진행되고 있다. 이 시스템은 단일 카메라를 이용하여 차선을 감지함으로써 차선 침범을 방지한다. 시스템은 파티클 필터를 이용해 도로 모델 파라미터를 조정하고 두 개의 detector가 도로 모델의 일치도를 계산한다. Detector는 차선의 모양과 색이라는 대표적인 특징을 이용한다. 파티클 필터를 전 프레임에서 사용한 모델 파라미터를 이용하여 신속한 처리를 한다.

• Spatial Information Research
• /
• v.17 no.1
• /
• pp.25-37
• /
• 2009

In this paper, we propose techniques for hazard analysis of curved road based on USN. The techniques consist of models and algorithms. Models of curved road, road direction, sensor, vehicle and hazard are proposed. To analyze hazard in curved road and give warning to corresponding vehicle in realtime multi-level algorithms are proposed. An application program implements the models and algorithms to simulate proposed techniques with real-time visualization.

• 한국도로학회:학술대회논문집
• /
• 2004.10a
• /
• pp.17-20
• /
• 2004

• Proceedings of the KSEEG Conference
• /
• 1999.04a
• /
• pp.236-239
• /
• 1999

• International Journal of Highway Engineering
• /
• v.13 no.4
• /
• pp.41-50
• /
• 2011

It is well-known that pavement is easily damaged by several factors including permanent deformation and fatigue crack, causing service life of the pavement to be shorter than expected. It is very important to predict amount of permanent deformation for designing pavement and developing design method of pavement. A new model of permanent deformation of pavement materials based on concept of shear stress ratio has been proposed because the lower pavement materials are highly affected by shear strength of the material. In this study a large repetitive triaxial load test has been adapted for performing test of permanent deformation of crushed subbase materials. The test procedure which includes concept of shear stress ratio has been newly developed. Several important model parameters can be obtained from the test that can be used for making correct permanent deformation model of the material.

• International Journal of Highway Engineering
• /
• v.10 no.1
• /
• pp.63-74
• /
• 2008

Resilient deformation characteristics on unbound pavement materials have been adopted for design and nonlinear analysis of pavement structure under traffic loadings. However, relatively few studies have been done on the nonlinear resilient behavior of unbound pavement materials in Korea. In addition, only the limited information is available for estimating the resilient modulus values on unbound materials. In this study, a laboratory resilient-deformation test under repeated loadings is performed in order to fud a proper constitutive model that correlates the resilient modulus with stress state from field condition. Finally, a finite element analysis is conducted for evaluating the nonlinear characteristics of unbound materials. and the pavement performance respectively.

• International Journal of Highway Engineering
• /
• v.10 no.1
• /
• pp.1-9
• /
• 2008

Five bases for of highways are sight distance, vehicle stability, driver comfort, drainage and aesthetics. Among these bases, the sight distance is the most critical one in the highway alignment design. It is certain that highways and drivers' observation actions are 3-dimensional in nature. But, the highway alignment design and the sight distance analysis have been performed on 2-dimensional planes because of various constraints and complexity of calculating 3-dimensional sight distance. The purpose of this study is to derive a model for determining exact available sight distance in 3-D combined horizontal and vertical alignments. Application of the model is illustrated using numerical examples. The proposed model should be useful in quantifying the criteria for 3-D highway alignments.