• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.5
• /
• pp.2009-2019
• /
• 2013

Traffic volumes are the important basic data which are directly used for transportation network planning, highway design, highway management and so forth. They are collected by two types of collection methods, one of which is the continuous traffic counts and the other is the short duration traffic counts. The continuous traffic counts are conducted for 365 days a year using the permanent traffic counter and the short duration traffic counts are conducted for specific day(s). In case of the continuous traffic counts the missing of data occurs due to breakdown or malfunction of the counter from time to time. Thus, the diverse imputation methods have been developed and applied so far. In this study the applied exponential smoothing method, in which the data from the days before and after the missing day are used, is proposed and compared with other imputation methods. The comparison shows that the applied exponential smoothing method enhances the accuracy of imputation when the coefficient of traffic volume variation is low. In addition, it is verified that the variation of traffic volume at the site is an important factor for the accuracy of imputation. Therefore, it is necessary to apply different imputation methods depending upon site and time to raise the reliability of imputation for missing traffic values.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.3D
• /
• pp.205-212
• /
• 2012

The national highway traffic counts system consists of short duration counts and continuous counts. Unlike continuous counts, short duration counts are performed by collection of a few days period and thus, the magnitude of deviation of collected data from AADT varies depending upon when data collection takes place. Therefore, this study was done to find out the best months and days of data collection of each highway classification in order to enhance the accuracy of AADT estimation. Continuous counts, another type of the national traffic counts system, are performed by collection of 365-day period using a permanent traffic counter. Therefore, it is necessary to keep the number of days for which the counter malfunctions to a minimum in order to enhance the accuracy of data. However, from time to time the permanent traffic counter malfunctions due to various causes and thus, cannot collect data. Therefore, this study was done to find out whether the age of counter, the ratio of heavy vehicle volume to total traffic volume, etc. could be the direct causes of counter's malfunction based on the number of maintenance for a certain time period.

• 한국ITS학회:학술대회논문집
• /
• 2003.11a
• /
• pp.56-61
• /
• 2003

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.277-283
• /
• 2021

Traffic data by vehicle classification are important data used as basic data in various fields such as road and traffic design. Traffic data is collected through permanent and temporary surveys and is provided as an annual average daily traffic (AATD) in the statistical yearbook of road traffic. permanent surveys are collected through traffic collection equipment (AVC), and the AVC consists of a loop sensor that detects traffic volume and a piezo sensor that detects the number of axes. Due to the nature of the buried type of traffic collection equipment, missing data is generated due to failure of detection equipment. In the existing method, it is corrected through historical data and the trend of traffic around the point. However, this method has a disadvantage in that it does not reflect temporal and spatial characteristics and that the existing data used for correction may also be a correction value. In this study, we proposed a method to correct the missing traffic volume by calculating the axis correction coefficient through the accumulated number of axes acquired by using a piezo sensor that can detect the axis of the vehicle. This has the advantage of being able to reflect temporal and spatial characteristics, which are the limitations of the existing methods, and as a result of comparative evaluation, the error rate was derived lower than that of the existing methods. The traffic volume correction system using axis count is judged as a correction method applicable to the field system with a simple algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2575-2580
• /
• 2013

In this paper, we watch out key measure of the level of transportation service about travel time and delay time. And we measured vehicle traffic by moving vehicle method using CCTV which is one of the travel time measure. We should be measured in place of continuous traffic flow characteristics with wide traffic light interval. In addition, traffic flow on the other side of the interval must be sufficiently identifiable and at the end of this section must be possible U-turn. This method it requires only the driver of the vehicle because of the CCTV measure. In addition, We cannot require time, distance, and traffic equipment that can be recorded. Because equipped with the software to do that. In addition to traffic, average travel time, average space speed, traffic density are also available.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.2
• /
• pp.1-13
• /
• 2015

Traffic volume data is basic information that is used in a wide variety of fields. Existing missing traffic volume data imputation method did not take the effect on the rainfall. This research analyzed considering of the rainfall effect in missing traffic volume data imputation method. In order to consider the effect of rainfall, established the following assumption. When missing of traffic volume data generated in rainy days it would be more accurate to use only the traffic volume data of the past rainy days. To confirm this assumption, compared for accuracy of imputed results at three kinds of imputation method(Unconditional Mean, Auto Regression, Expectation-Maximization Algorithm). The analysis results, the case on consideration of the rainfall effect was more low error occurred.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.105-106
• /
• 2014

본 논문에서는 통행 시간의 측정 방법 중 하나인 CCTV를 활용한 주행 차량 조사법을 이용하여 교통량을 측정한다. 교통망의 서비스 수준을 측정하는 주요 기준인 통행 시간과 지체 시간에 대하여 알아본다. 신호등 간격이 넓어서 연속적인 교통류 특성을 갖는 곳에서 측정을 하도록 한다. 반대편의 교통류가 충분히 식별 가능한 구간이어야 하고, 구간의 끝부분에서는 유턴이 가능해야 한다. 이 방법은 측정차량의 운전수만 있으면 CCTV와 프로그램이 알아서 측정하고, 시간, 거리, 교통량을 기록할 수 있는 장비도 필요 없다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.266-268
• /
• 2016

우리나라는 항만운영의 효율성 및 선박 안전운항을 위하여 1993년 포항을 시작으로 전국 18개의 VTS 시스템을 설치 운영하고 있으나, 최근 선박 교통량의 증가와 더불어 해양사고의 증가 원인으로 인적요인에 대해 연구 필요성이 대두되고 있다. 특히 해상교통관제 업무는 고도의 주의력과 예측능력을 요구하므로 이를 저해하는 인적요인을 분석 및 관리할 필요성이 있다. 따라서 본 연구에서는 VTS 관제실의 근무환경에 대해 설문조사를 통한 요구사항 분석과 함께 현장조사를 시행하여 분석함으로서 VTS 관제장비 및 관제석의 최적 배치방안을 제시하여 최상의 해상교통관리 체제 구축에 대하여 고찰해 보았다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.269-279
• /
• 2020

Traffic estimation mainly involves surveying equipment such as automatic vehicle classification, vehicle detection system, toll collection system, and personnel surveys through CCTV (Closed Circuit TeleVision), but this requires a lot of manpower and cost. In this study, we proposed a method of estimating traffic volume using deep learning and stereo CCTV to overcome the limitation of not detecting the entire vehicle in case of single CCTV. COCO (Common Objects in Context) dataset was used to train deep learning models to detect vehicles, and each vehicle was detected in left and right CCTV images in real time. Then, the vehicle that could not be detected from each image was additionally detected by using affine transformation to improve the accuracy of traffic volume. Experiments were conducted separately for the normal road environment and the case of weather conditions with fog. In the normal road environment, vehicle detection improved by 6.75% and 5.92% in left and right images, respectively, than in a single CCTV image. In addition, in the foggy road environment, vehicle detection was improved by 10.79% and 12.88% in the left and right images, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.3
• /
• pp.13-22
• /
• 2012

Estimating directional design hourly volume (DDHV) is an important aspect of traffic or road engineering practice. DDHV on highway without permanent traffic counters (PTCs) is usually determined by the annual average daily traffic (AADT) being multiplied by the ratio of DHV to AADT (K factor) and the directional split ratio (D factor) recommended by Korea highway capacity manual (KHCM). However, about the validity of this method has not been clearly proven. The main intent of this study is to develop more accurate and efficient DDHV estimation models for national highway in Korea. DDHV characteristics are investigated using the data from permanent traffic counters (PTCs) on national highways in Korea. A linear relationship between DDHV and AADT was identified. So DDHV estimation models using AADT were developed. The results show that the proposed models outperform the KHCM method with the mean absolute percentage errors (MAPE).