• 한국도로학회:학술대회논문집
• /
• 한국도로학회 2003년도 학술발표회 논문집
• /
• pp.327-332
• /
• 2003

• 대한인간공학회지
• /
• 제35권3호
• /
• pp.135-142
• /
• 2016

Objective: Objective of this study is to provide characteristics of injury frequency and severity by driving condition in large truck-related traffic collisions. Background: Traffic accidents involving large trucks draw a lot of attention in accident prevention and management policies since they bring about severe human and financial damages. Method: In order to identify the major risk factors of accidents by driving condition, 255 recognized traffic accidents by large truck drivers were analyzed in terms of time of the day, road type, and shape of the road. Results: The driving conditions in the results are represented by the following form of combination, "Road Type (Non-expressway or Express) - Shape of Roads (Straight, Curved, Downhill, or Intersection) - Time of Accidents (Day or Night)". In the analysis of injury frequency, Non-expressway-Straight-Day condition was the most frequent one. Meanwhile, Expressway-Curved-Day, Non-expressway-Curved-Night and Non-expressway-Intersection-Night were evaluated as high level in view of injury severity. Also, Expressway-Straight-Night is the driving condition that is the highest in risk among the conditions that have to be managed as grade "High". Non-expressway-Straight-Night, Non-expressway-Downhill-Day, and Non-expressway-Curved-Day are also categorized as grade "High". Conclusion and Application: Safety managers in the fields require basic information on accident prevention that can be easily understood. The research findings will serve as a practical guideline for establishing preventive measures for traffic accidents.

• 인터넷정보학회논문지
• /
• 제23권2호
• /
• pp.53-59
• /
• 2022

3단계 자율주행 차량 이후, 4, 5단계의 자율주행 기술은 차량의 완벽한 주행뿐만 아니라 탑승객의 상태를 최적으로 유지하기 위해 노력하고 있다. 그러나 현재 자율주행 기술은 LiDAR, 전방 카메라 등 시각적 정보에 과하게 의존하기 때문에 지정된 도로 이외의 도로에서 완벽하게 자율주행을 실행하기 힘들다. 따라서 본 논문은 차량이 시각 정보 외의 데이터를 사용하여 도로의 상태를 분류하고, 도로 상태와 주행 상태에 따라 최적의 제동 강도를 계산하는 BSCS (Braking Strength Calculation System)를 제안한다. 본 논문에서 제안하는 BSCS는 KNN 알고리즘을 기반으로 도로의 상태를 분류하는 RCDM (Road Condition Definition Module)과 RCDM의 결과와 현재 주행 상태를 통해 주행 중 최적의 제동 강도를 계산하는 BSCM (Braking Strength Calculation Module)로 구성된다. 본 논문의 실험 결과, KNN 알고리즘에 가장 적합한 K의 수를 찾을 수 있었고, 비지도 학습인 K-means 알고리즘보다 본 논문에서 제안한 RCDM이 더 정확한 것이 증명되었다. 해당 논문의 BSCS는 시각 정보뿐만 아니라 서스펜션에 가해지는 진동 데이터를 사용함으로써, 시각 정보가 제한되는 여러 환경에서 자율주행 차량의 제동을 더 원활하게 만들 수 있다.

• 한국도로학회논문집
• /
• 제13권3호
• /
• pp.121-129
• /
• 2011

본 연구는 이상적인 실험환경이 아닌 실제 일반국도(국도 3호선)를 분석 대상으로 실시간으로 수집된 교통자료와 NOx 대기 오염 측정 자료를 이용하여 이들 사이의 관계를 규명하고 그 특성을 분석하고자 한다. 또한 이러한 관계를 이용하여 현장에서 실제 적용이 가능하며 대기오염도를 모니터링을 할 수 있는 일반국도의 차량배출가스로 인한 NOx 대기오염도 추정 모형을 개발하고자 한다. 모형의 구축에 있어서 측정 장비 및 기타 변동요인으로 인한 특이점을 제거하기 위하여 로버스트 분석을 이용하였고 바람의 영향을 고려하지 않은 경우와 바람의 영향을 고려한 경우에 대해서 모형을 구축하였다. 본 연구의 결과는 교통정책 시행에 따른 차량배출가스로 인한 대기오염 현황을 파악하고 교통정책의 환경적 효과를 평가하는데 활용될 수 있을 것이다.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2008년도 추계학술대회논문집
• /
• pp.654-655
• /
• 2008

In order to investigate the availability of tire airborne noise for vehicle road noise development, We measured the noise in condition of smooth road and coarse road. The correlation coefficient was analyzed using the articulation index of the tire airborne noise and the vehicle road noise. It has been found that the correlation between the tire airborne noise and the vehicle road noise is positively strong.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2010년도 춘계 학술대회 제22권1호
• /
• pp.391-392
• /
• 2010

도로의 결빙은 겨울철 차량사고의 큰 원인으로 작용하며, 특히 고속도로에서의 노면결빙은 대형사고로 이어질 수 있다. 이러한 노면결빙으로 인한 사고는 노면상태를 파악하여 사전에 결빙을 방지함으로서 효과적으로 감소시킬 수 있다. 따라서 본 연구에서는 고속도로에 적용된 콘크리트 포장체의 노면상태를 평가하기 위하여 상습결빙구간에 포장체 깊이별로 온도센서를 설치하였다. 이 결과는 향후 결빙 사전예측을 위한 노면상태판정의 기초자료로 효과적으로 활용될 것이다.

• 교육시설
• /
• 제10권4호
• /
• pp.31-41
• /
• 2003

The purpose of this study is to analyze the Characteristic of Block Plans related to site types of Elementary Schools in Kangju city. With analysis of 17 elementary school plans, we reached same conclusions. First, there is a possibility of seeing 4 examples that contiguity road condition and proportion of site, neighborhood park location, district units planning, which as classification the condition to feature of location. But the condition which is considered actually from Block Plan appeared with only contiguity road condition and district units planning two onlines. Second, despite there are elements having the possibility effecting to Block Plan, some arrangement forms are repeatedly used. There is a possibility of searching for that cause that it falls in mannerism of space form, type and place when it follows the arrangement form of existing defined as school.

• 한국자동차공학회논문집
• /
• 제18권1호
• /
• pp.8-13
• /
• 2010

Many vehicles have significantly under-inflated tires, primarily because drivers infrequently check their vehicles' tire pressure. When a tire is used while significantly under-inflated, its sidewalls flex more and the tire temperature increases, increasing stress and the risk of failure. In this study we evaluated tire safety and economical efficiency at various inflation pressure. For tire safety we performed FMVSS indoor durability test, measurement of rolling tire temperature, braking performance at dry/wet road condition, and rolling resistance test for economical efficiency. Results show that low pressure decreases tire durability of both speed-increase condition and load-increase condition. Heat temperature of rolling tire increases as pressure decreases and significantly under-inflated tires cause increase of vehicle's stopping distance at wet road condition. Also Under-inflation increases the rolling resistance of a tire and, correspondingly, decreases vehicle's fuel economy.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.221-224
• /
• 2007

MMS(Mobile Mapping System) generates a efficient image data for mapping and facility management. However, this image data of MMS has many difficulties in a practical use because of huge data volume. Therefore the important information likes road sign post must be extracted from huge MMS image data. In Korea, there is the HMS(Highway Management System) to manage a national road that acquire the line and condition of road from the MMS images. In the HMS each road sign information is manually inputted by the keyboard from moving MMS. This manually passive input way generate the error like inaccurate position, mistaking input in this research we developed the automatic road sign identifying technique using the image processing and the direct geo-referencing by GPS/INS data. This development brings not only good flexibility for field operations, also efficient data processing in HMS.