• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.11
• /
• pp.521-528
• /
• 2015

Road-view object classification methods are mostly influenced by weather and illumination conditions, thus the most of the research activities are based on dataset in clean weathers. In this paper, we present a road-view object classification method based on color segmentation that works for all kinds of weathers. The proposed method first classifies the weather and illumination conditions and then applies the weather-specified color models to find the road traffic signs. Using 5 different features of the road-view images, we classify the weather and light conditions as sunny, cloudy, rainy, night, and backlight. Based on the classified weather and illuminations, our model selects the weather-specific color ranges to generate Gaussian Mixture Model for each colors, Green, Yellow, and Blue. The proposed method successfully detects the traffic signs regardless of the weather and illumination conditions.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.228-241
• /
• 2021

This study verified the performance change of a LiDAR when it detects road signs, which are potential cooperation targets for an autonomous vehicle. In particular, road signs of different colors and materials were produced and tested in controlled rainfall on the real road environment. The NPC and intensity were selected as the performance indicators, and a T-Test was used for comparison. The study results show that the performance of LiDAR for the detection of road signs was reduced with the increase of rainfall. The degradation of performance in retroreflective sheets was lesser than painted road signs, but at the amount of 40 mm/h or more, the detection performance of retroreflective sheets deteriorates to an extent that data cannot be collected. The performance level of black paint was lower than that of other colors on a clear day. In addition, the white sheet was most sensitively degraded with the increase in precipitation. These performance verification results are expected to be utilized in the manufacturing of road facilities that improve the visibility of sensors in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.192-202
• /
• 2021

In the past, various studies have been conducted on safety facility installation standards and road safety indices. But there are limitations in applying them to the field, such as using many survey items and variables that are difficult to use. Therefore, this study attempted to develop road safety judgment indicators considering the applicability of the research results and to prepare criteria for installing safety facilities. As part of the study, data of related systems were reviewed, and the use of variables already in use was figured out. Furthermore, the road safety judgment indicators reflecting traffic, road, and accident factors were developed through correlation and factor analysis. Later, the criteria score for determining the installation of safety facilities was derived through cluster analysis. The analyses suggested, that the installation judgment criterion score at the intersection was lower than that of the single road(crosswalk), and the road risk at the intersection was higher.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.310-319
• /
• 2020

Korea estimates the traffic noise by measuring the total traffic noise when the traffic passes (SPB; Statistical Pass-By). Another method (CPX; Close Proximity) directly measures the tire/road noise by installing a microphone near the tire. The CPX method is not a formal test method in Korea. There has been little research between CPX and SPB. This study proposes a method for estimating SPB, using the CPX, which is easy to measure. This study used the results of a large-scale test conducted by Korea Expressway Corporation (KEC) and a research paper on CPX in this section. The results by the KEC showed that the low noise pavement has a noise reduction of 10.4dB. In CPX research, the noise reduction was 10.7dB and was similar to 10.4dB in SPB. This study shows why the noise reduction is the same regardless of the position, the reason that the amount of noise reduction is similar, the difference of the noise according to the position of the microphone using the concept of noise summation and distance reduction. This study shows that including the CPX as a variable in the traffic noise prediction program is very important to improve noise prediction reliability.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.4
• /
• pp.190-211
• /
• 2022

This study investigated the effect of the shape and height of road signs on detection performance when detecting road signs with LiDAR, which is recognized as an essential sensor for autonomous vehicles. For the study, four types of road signs with the same area and material and different shapes were produced, and a road driving test was performed by installing a 32Ch rotating LiDAR on the upper part of the vehicle. As a result of comparing the shape of the point cloud and the NPC according to the shape of the road sign, It is expected that a distance of less than 40m is required to recognize the overall shape of a road sign using 32Ch LiDAR, and shapes such as triangles and rectangles are more advantageous than squares in securing the maximum point cloud from a long distance. As a result of the study according to the height of the road sign, At short distances (within 20m), if the height of the sign is raised to more than 2m, it deviates from the vertical viewing angle of the LiDAR and cannot express the complete point cloud shape. However, it showed a negligible effect compared to the near-field height change. These research results are expected to be utilized in the development of road facilities dedicated to LiDAR for the commercialization of autonomous cooperative driving technology.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.394-396
• /
• 2007

본 논문은 레이더를 통해 입력받은 데이터를 분석하여 같은 물체에 관한 데이터를 구분하는 방법을 제시한다. 큰 영역을 감시하는 레이더에 비해 영역이 좁을 때 레이더는 한 물체에 대해서 물체 형태에 따라 데이터가 들어오게 된다. 이 데이터들은 같은 물체인지 아닌지 구분이 없어서 응용된 알고리즘을 적용하기 힘들다. 따라서 응용된 알고리즘을 적용하기 전 하나의 물체에 대한 데이터의 그룹핑 작업이 필요하다. 본 논문에서 그룹핑 방법을 제시하며 실제 도로에서 취득한 데이터를 가지고 시뮬레이션을 하였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.11a
• /
• pp.430-433
• /
• 2007

무선 센서 네트워크는 감지, 연산 그리고 무선 통신 능력을 갖는 수많은 작은 센서 노드들로 구성된다. 센서 네트워크에는 전장 감시, 침입자 추적, 그리고 고속 도로 감시 등과 같은 많은 응용분야가 있다. 이러한 분야에서는 사용자의 관심 대상이 되는 지역에서 발생 하는 사건들을 감시하기 위하여, 제한적인 에너지 자원과 연산 능력을 가진 세서 노드들로부터 감지된 데이터를 수집한다. 그러므로 센서 네트워크 응용분야에서의 데이터 수집과 전달, 센서 노드의 효율적인 에너지 소모는 매우 중요하며, 이를 위하여 센서 네트워크를 위한 라우팅, 전력관리, 그리고 데이터 보급 프로토콜들의 설계에서는 이러한 제약 사항들이 반드시 고려되어야 한다. 본 논문에서는 무선 센서 네트워크에서 효율적인 데이터 전달을 위한 라우팅 방법을 제안한다. 제안된 방법은 센서 노드의 트래픽 량, 잔여 에너지 량, 그리고 베이스 스테이션가지의 최단경로를 고려하여 데이터 전송 경로를 결정하여, 센서 네트워크에서의 에너지 효율적이면서도 안정적인 감지 데이터 전송을 가능하게 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.176-179
• /
• 2013

본 연구는 최근 활성화된 스마트폰 내비게이션의 교통정보를 이용 시 상대적으로 품질이 취약한 지방지역의 빠른길 및 통행시간 정확도를 개선하는 방안에 대한 연구이다. 본 연구에서는 Hadoop기술을 이용하여 교통데이터에 대한 방대한 양의 데이터를 분석 처리한다. 특히, 실시간 교통정보가 제대로 수집되지 않는 지역의 도로 속도 정보에 대한 개선 방안으로 고객 단말로부터 올라오는 위치 데이터를 실시간으로 수집하여 전자지도 기본 속성값을 실시간 통계 데이터로 교체 반영하여 상대적으로 취약한 지방지역의 경로 품질 및 경로 탐색을 개선하는 방안을 제시하였다. 단말로부터 올라오는 많은 양의 GPS 위치정보등 대용량 데이터 처리를 위해 오픈소스프로젝트인 Hadoop플랫폼 환경에서 빅데이터 처리용 오픈소스를 활용하여 고가의 RDBMS를 대체하는 효과와 시간 단축의 효과를 기대할 수 있게 되었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.497-499
• /
• 2020

자율주행 차량이 많아지고 차량의 ECU가 고도화되면서 정확한 차량의 데이터를 획득하고 분석하여 활용하는 것이 중요해지고 있다. 현재에는 내연 기관 차량의 ECU 데이터를 얻기 위해서 OBDII 포트(규격)에 기반한 CAN동선을 주로 이용하고 있다. 하지만 OBDII 규격을 통해서 연비와 같은 중요한 차량 정보를 얻는 경우, 변환식 (MAF 센서(흡입 공기량 센서)와 공기/연료 비율을 이용)의 오차 범위가 커서 데이터의 정확도가 낮다. 본 연구에서는 머신 러닝 기법 중에 하나인 회귀 기법을 통해서 기존의 계산보디 더 정확한 연비를 구할 수 있는 모델을 개발하였다. 이러한 모델 개발을 통하여 차량의 RAW 데이터를 기반으로 필요한 차량 데이터를 정확하게 구할 수 있게 되었으며 20회가 넘는 실 도로주행을 통해서 본 모델의 정확도를 검증하였다.

• Journal of the Korean GEO-environmental Society
• /
• v.18 no.6
• /
• pp.31-37
• /
• 2017

In recent years, the increasing trend of ground subsidence in major cities has caused social problems. Aged sewer pipeline as a main attribute for the subsidence is simply replaced and maintained according to a survey result with related to its buried period. However, other attributes and risk analysis for the subsidence have not been well studied yet. In this point, this study proposed various environmental and structural attributes with related to sewer pipelines and, then, a method of ground subsidence risk evaluation with a certain level of reliability. In order to find effective attributes to ground subsidence near to sewer, the nearest sewerage data were extracted at the location of subsidence in the City of Seoul, and a level of correlation was analyzed between subsidence and individual attribute. The effective weight factors for the proposed attributes was estimated through AHP analysis and its applicability was verified by comparing the actual subsidence data to the risk evaluation in the pilot study district of Seoul.