• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.1
• /
• pp.1-14
• /
• 2013

Annual average daily traffic (AADT) serves the important basic data in transportation sector. Despite of its importance, AADT is estimated through permanent traffic counts (PTC) at limited locations because of constraints in budget and so on. At most of locations, AADT is estimated using short-term traffic counts (STC). Though many studies have been carried out at home and abroad in an effort to enhance the accuracy of AADT estimate, the method to simplify average STC data has been adopted because of application difficulty. A typical model for estimating AADT is an adjustment factor application model which applies the monthly or weekly adjustment factors at PTC points (or group) with similar traffic pattern. But this model has the limit in determining the PTC points (or group) with similar traffic pattern with STC. Because STC represents usually 24-hour or 48-hour data, it's difficult to forecast a 365-day traffic variation. In order to improve the accuracy of traffic volume prediction, this study used the geostatistical approach called co-kriging and according to their reports. To compare results, using 3 methods : using adjustment factor in same section(method 1), using grouping method to apply adjustment factor(method 2), cokriging model using previous year's traffic data which is in a high spatial correlation with traffic volume data as a secondary variable. This study deals with estimating AADT considering time and space so AADT estimation is more reliable comparing other research.

• 한국도로학회:학술대회논문집
• /
• 2004.10a
• /
• pp.355-362
• /
• 2004

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.147-157
• /
• 2022

Recently, many studies have been conducted to analyze traffic or object recognition that classifies vehicles through artificial intelligence-based prediction models using CCTV (Closed Circuit TeleVision)or drone images. In order to develop an object recognition deep learning model for accurate traffic estimation, systematic data construction is required, and related standardized guidelines are insufficient. In this study, previous studies were analyzed to derive guidelines for establishing artificial intelligence-based training data for traffic estimation using drone images, and business reports or training data for artificial intelligence and quality management guidelines were referenced. The guidelines for data construction are divided into data acquisition, preprocessing, and validation, and guidelines for notice and evaluation index for each item are presented. The guidelines for data construction aims to provide assistance in the development of a robust and generalized artificial intelligence model in analyzing the estimation of road traffic based on drone image artificial intelligence.

• Journal of Korean Society of Transportation
• /
• v.18 no.2
• /
• pp.53-62
• /
• 2000

현재까지 개발된 교통량 기반 O/D 추정기법들은 추정된 O/D의 신뢰성을 평가하는 기준으로 통계적 오차분석을 통한 참O/D(true O/D)와 추정O/D간의 타이를 분석하는 방법이 주류를 이루었다. 문제는 이러한 오차분석기법들이 현실적인 대규모 교통망상에 적용될 때 탐O/D를 알 수 없을 뿐만 아니라, 알 수 있다고 하더라도 추정된 O/D와의 비교 평가시에 그러한 평가방법으로 추정된 O/D의 신뢰성을 부여하기에는 많은 문제점을 가지고 있다는 점이다. 통행조사에 의한 O/D는 비록 포함되어 있는 정보가 과거의 정보라고 할지라도 현재의 통행흐름에 대하여 가장 많은 정보를 가지고 있다고 할 수 있다. 즉, 선행O/D의 정보를 크게 변화시키지 않으면서도 관측교통량으로 O/D를 추정할 수 있는 방법이 이 관점에서 매우 뛰어난 추정방법이라고 할 수 있다. 이러한 관점에서 본 연구에서는 선행O/D정보 중 통행수요예측시 가장 중요한 지표의 하나인 통행시간빈도분포 (TriP Length Frequency Distribution:TLFD)를 이용하여 추정O/D의 신뢰성 지표로 삼았다. TLFD는 4단계 모형에서 통행분포(trip distribution)시 모형을 정산하는 데 사용되는 방법으로써 죤간 통행시간을 단위별로 나누어 조사된 통행시간분포와 추정된 O/D의 통행시간분포가 유사한 지를 살피는 방법이라고 할 수 있다. 조사된 TLFD와 추정O/D의 TLFD가 유사한 모양을 이를 때 추정O/D의 신뢰성이 높다고 인정한다. 또한 TLFD는 전통적으로 조사된 표본O/D를 전 수화하는데 이용되어 그 타당성 또한 많이 검증되어 왔다. 그러나 아직까지 TLFD를 가지고 교통량으로 O/D를 추정하는 모형의 결과를 검증한 연구 결과는 없는 실정이다. 따라서, 본 연구에서는 최종적인 이러한 분석결과를 평가할 수 있을 뿐 아니라, 평가된 지표가 신뢰할 만한 수준이 아니라면, 추정된 결과를 보정할 수 있는 가능성을 제시하고자 한다.

• Journal of Korean Society of Transportation
• /
• v.18 no.4
• /
• pp.117-126
• /
• 2000

Conventional methods for collecting origin-destination trips have been mainly relied on the surveys of home or roadside interview. However, the methods tend to be costly, labor intensive and time disruptive to the trip makers, thus the methods are not considered suitable for Planning applications such as routing guidance, arterial management and information Provision, as the parts of deployments in Intelligent Transport Systems Motivated by the problems, more economic ways to estimate origin-destination trip tables have been studied since the late 1970s. Some of them, which have been estimating O-D table from link traffic counts are generally Entropy maximizing, Maximum likelihood, Generalized least squares(GLS), and Bayesian inference estimation etc. In the Paper, with user equilibrium constraint we formulate GLS problem for estimating O-D trips and develop a solution a1gorithm by using Genetic Algorithm, which has been known as a g1oba1 searching technique. For the purpose of evaluating the method, we apply it to Seoul inner ringroad and compare it with gradient method proposed by Spiess(1990). From the resu1ts we fond that the method developed in the Paper is superior to other.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.83-95
• /
• 2003

This study aims to develop travel time estimation and prediction models on the freeway using measurements from vehicle detectors. In this study, we established a travel time estimation model using traffic volume which is a principle factor of traffic flow changes by reviewing existing travel time estimation techniques. As a result of goodness of fit test. in the normal traffic condition over 70km/h, RMSEP(Root Mean Square Error Proportion) from travel speed is lower than the proposed model, but the proposed model produce more reliable travel times than the other one in the congestion. Therefore in cases of congestion the model uses the method of calculating the delay time from excess link volumes from the in- and outflow and the vehicle speeds from detectors in the traffic situation at a speed of over 70km/h. We also conducted short term prediction of Kalman Filtering to forecast traffic condition and more accurate travel times using statistical model The results of evaluation showed that the lag time occurred between predicted travel time and estimated travel time but the RMSEP values of predicted travel time to observations are as 1ow as that of estimation.

• Journal of Korean Society of Transportation
• /
• v.19 no.1
• /
• pp.77-88
• /
• 2001

Until now, though most of the studies related to demand estimation method using traffic counts use methods based on singleclass, travel demands or flows are made by mixing various vehicles in real networks. In general, existing demand estimation methods based on traffic counts estimate O/D by converting a multiclass O/D matrix and traffic counts into a singleclass O/D matrix and traffic counts through PCE conversion, and analyze a O/D matrix by dividing into a multiclass O/D matrix and traffic counts after multiplying an estimated O/D matrix by the fixed ratio of a singleclass O/D matrix and traffic counts before PCE conversion. However, the merits of a demand estimation method based on multiclass calculate each route choice ratio about multiclass O/D, and maximize the estimation capability of multiclass by calculating each gradient, the reduction direction of objective function. Therefore, this study aims to establish a demand estimation method which considers congestion between vehicle and vehicle by using multiclass instead of singleclass.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.2D
• /
• pp.103-110
• /
• 2012

This study presents O/D based emission estimation model and methodology under cold- and hot-start conditions. Contrasting with existing link-based model, new model is able to estimate cold-start emissions with actual traffic characteristics. The results of the case study with new model show similar amount of emission with existing model under hot-start conditions, but five times much more than existing model under cold-start conditions. The annual social benefit estimated by this model is 56.2 hundred million won, which is 48% higher than the result from existing model. It means current green transportation policies are undervalued in terms of air quality improvement. Therefore, New model is expected to improve the objectivity of air quality evaluation results regarding green transportation policies and be applied in various transportation-environment policies.

• 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).

• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.111-121
• /
• 2010

DHV (Design-Hour Volume) for the estimation of number of lanes is determined by design-hour factor (K). The design-hour factor is defined as the proportion between the 30th highest hourly volume and AADT and determines the level of road planning. However, the K-factor estimated by an existing method has a problem because the hourly volumes on holiday and weekend appear in the relatively low rank in real world in spite of expected high volumes. To improve this problem, this study make use of the concept of traffic demand in estimating the design-hour factor. After the congested hourly volumes transfer to traffic hourly demand, the K-factors are estimated on urban expressways and are compared to the existing K-factors. It is perceived that the new K-factors have more realistic values due to utilizing the traffic demand. reflecting the congested flow.