• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.93-104
• /
• 2023

Currently, the permanent road traffic volume surveys under Road Act are conducted using a intrusive Automatic Vehicle Classification (AVC) equipments to classify 12 categories of vehicles. However, intrusive AVC equipment inevitably have friction with vehicles, and physical damage to sensors due to cracks in roads, plastic deformation, and road construction decreases the operation rate. As a result, accuracy and reliability in actual operation are deteriorated, and maintenance costs are also increasing. With the recent development of ITS technology, research to replace the intrusive AVC equipment is being conducted. However multiple equipments or self-built DB operations were required to classify 12 categories of vehicles. Therefore, this study attempted to prepare a method for classifying 12 categories of vehicles using vehicle specification information of the Vehicle Management Information System(VMIS), which is collected and managed in accordance with Motor Vehicle Management Act. In the future, it is expected to be used to upgrade and diversify road traffic statistics using vehicle specifications such as the introduction of a road traffic survey system using Automatic Number Plate Recognition(ANPR) and classification of eco-friendly vehicles.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.12
• /
• pp.1237-1244
• /
• 2016

Vehicle classification system in domestic tollgates is usually to use treadle sensor for calculating wheel width and tread of the vehicle. Due to the impact that occurs when the wheels of the vehicle contact, treadle sensor requires high durability. Recently, KHC(Korea Highway Corporation) began operating high-speed lane for cargo truck. High-speed cargo truck generate more impact the design criteria of previous treadle. Therefore, an increase in the maintenance and management costs of the treadle damage is concerned. In this paper, we propose an algorithm to classify vehicles using non-contact treadle sensors for improving durability from physical impacts. This was based on the KHC's classification criteria and showed a classification accuracy of 99.5 % in one experiment with 1892 vehicles through Changwon tollgate in 1020 local road. Therefore, it shows that vehicle classification system using non-contact treadle sensor could be applied to domestic toll tollgates, effectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.410-413
• /
• 2011

본 논문에서는 도로 영상에서 검출된 자동차 영상을 종류별 분류를 위해 효과적인 질감 특징정보 기반의 자동차 종류별 분류 방안을 제안한다. 제안한 연구에서는 운전자의 안전운전지원을 위해 도로상에서 검출된 자동차 영역과 자신의 차량과 거리를 추정하기 위해 검출된 자동차의 종류를 인식할 필요가 있다. 즉, 인식된 자동차의 종류에 따라 차량 간 거리를 추정에 필요한 파라미터로 사용할 수 있기 때문이다. 따라서 본 연구에서는 검출된 자동차 영상들로부터 GLCM(gray-level co-occurrence matrix)의 7가지의 특징정보들을 추출하고 SVM을 사용하여 학습 한 후 자동차의 종류(승용, 화물, 버스)를 분류하는 방법을 제안한다. GLCM은 영상이 가진 질감 정보를 효율적으로 분석함으로써 영역의 밝기 변화 정도, 거침 정도, 픽셀 분포 정도 등을 표현하기 때문에 영상내의 포함된 영역을 분류하는데 효과적이다. 제안한 방법을 실제 자동차 규모별 분류에 적용한 결과 약 83%의 분류 성공률을 제시하였다.

• 한국도로학회:학술대회논문집
• /
• 2008.03a
• /
• pp.89-96
• /
• 2008

• 한국도로학회:학술대회논문집
• /
• 2006.10a
• /
• pp.353-358
• /
• 2006

• Journal of Cadastre & Land InformatiX
• /
• v.44 no.1
• /
• pp.127-138
• /
• 2014

It can be effective to extract and apply the updated information from the newly updated map data for updating road data of topographic map. In this study, update target data and update reference data are overlaid and the update objects are explored using network matching technique. And the network objects are classified into five matching and update cases and the update processes for each case are applied to the test data. For this study, road centerline data of digital topographic map is used as an update target data and road data of Korean Address Information System is used as an update reference data. The buffer-based network matching method is applied to the two data and the matching and update cases are classified after calculating the overlaid ratio of length. The newly updated road centerline data of digital topographic map is generated from the application of update process for each case. As a result, the update information can be extracted from the different map dataset and applied to the road network data updating.

• International Journal of Highway Engineering
• /
• v.13 no.2
• /
• pp.175-185
• /
• 2011

Geometric information is a key element for evaluating traffic safety and road maintenance. This study developed an algorithm to identify horizontal alignment using global positioning system(GPS) and inertial navigation system(INS) data. Roll and heading information extracted from GPS/INS were utilized to classify horizontal alignment into tangent, circular curve, and transition curve. The proposed algorithm consists of two components including smoothing for eliminating outlier and a heuristic classification algorithm. A genetic algorithm(GA) was adopted to calibrate parameters associated with the algorithm. Both freeway and rural highway data were used to evaluate the performance of the proposed algorithm. Promising results, which 90.48% and 88.24% of classification accuracy were obtainable for freeway and rural highway respectively, demonstrated the technical feasibility of the algorithm for the implementation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.3
• /
• pp.17-28
• /
• 2024

In this study, the capacity of the tunnel and the general section was calculated and compared using the VDS detector data, and the decrease rate in capacity of the tunnel section was analyzed by tunnel type. To compare the capacity of the tunnel and the general section, the Product Limit Method (PLM) was applied to the VDS detector data. As a result of comparing the capacity of the tunnel and general section, the capacity of the tunnel section decreased by about 6.5% compared to the general section. To classify the tunnel type, the tunnel extension and the number of lanes were used as variables, and there was a difference in the decrease rate of capacity by tunnel group classified by each criterion.

• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.582-590
• /
• 2015

Road type classification and K-factors are important role when design of number of lane. In this study not only classifies road type and estimating of K-factor but also economic evaluation tries for feasibility verification. Road type analysis results, time of day traffic volume variation, weekend-factor and vacation-factor are large in recreation roads. Weekday traffic volume and weekend traffic volume are similar patterns in provincial roads. AADT is high and time of day traffic volume variation is small in urban roads. In this study compares with economic analysis that designing of number of lane between KHCM's K-factor and this study K-factor. Economic analysis results, designed roads by this study's K-factor reduce cost about 4,708 hundred million won. So this study's K-factor is economical on provincial 4 lane roads.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.2
• /
• pp.289-297
• /
• 2009

In the paper, we propose the methodology to extract training dataset automatically for supervised classification of road networks. For the preprocessing, we co-register the airborne photos, LIDAR data and large-scale digital maps and then, create orthophotos and intensity images. By overlaying the large-scale digital maps onto generated images, we can extract the initial training dataset for the supervised classification of road networks. However, the initial training information is distorted because there are errors propagated from registration process and, also, there are generally various objects in the road networks such as asphalt, road marks, vegetation, cars and so on. As such, to generate the training information only for the road surface, we apply the Expectation Maximization technique and finally, extract the training dataset of the road surface. For the accuracy test, we compare the training dataset with manually extracted ones. Through the statistical tests, we can identify that the developed method is valid.