• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.67-77
• /
• 2022

An automatic freeway bus-only lane enforcement system was developed and assessed in a real-world environment. Observation of a bus-only lane on the Youngdong freeway, South Korea, revealed that approximately 99% of the vehicles violated the high-occupancy vehicle (HOV) lane regulation. However, the current enforcement by the police not only exhibits a low enforcement rate, but also induces unnecessary safety and delay concerns. Since vehicles with six passengers or higher are permitted to enter freeway bus-only lanes, identifying the number of passengers in a vehicle is a core technology required for a freeway bus-only lane enforcement system. To that end, infrared cameras and the You Only Look Once (YOLOv5) deep learning algorithm were utilized. For assessment of the performance of the developed system, two environments, including a controlled test-bed and a real-world freeway, were used. As a result, the performances under the test-bed and the real-world environments exhibited 7% and 8% errors, respectively, indicating satisfactory outcomes. The developed system would contribute to an efficient freeway bus-only lane operations as well as eliminate safety and delay concerns caused by the current manual enforcement procedures.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.97-105
• /
• 2011

This paper presents how one can investigate the effects on crash occurrence of freeway geometric design elements including the horizontal, vertical alignment and road environment. At present, the available research results for the most part involve geometric data analysis that are obtained along a relatively long section of freeway, and, because of the long section's diverse geometric conditions, the results tend to miss the specific local geometric impacts on vehicle crashes. In this regard, this research attempts to establish vehicle crash models based on a set of freeway geometric patterns whose crash generating characteristics are identical because they are homogeneous in terms of producing the same vehicle operating speeds, and subsequently their actual relationships are described by providing statistical analysis made in this research. Also each standard is comprised of part of straight, curve and continuous curve. This research has revealed that each type of model has different relation between accident and geometry structure. This research results should be useful for doing more reasonable highway designs and safety audit analysis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3D
• /
• pp.215-222
• /
• 2010

Average speed denotes a travel speed based on the average travel time of vehicles to traverse a segment of roadway, and average travel speed is used as a measure of effectiveness (MOE) suggested in the highway capacity manual (HCM) for evaluating the level of service (LOS) of roadway. Most of the urban freeways in our country are having congestion problem regardless of the rush hours as a high-speed highway with a speed limit of 80km/h or less. Especially traffic congestion within the ramp junction areas is becoming worse by the increased traffic and lack of links with the arterials around the urban freeway. So, the purpose in this study is to identify the traffic characteristics within the ramp junction areas of urban freeway, predict the average speed within the ramp junction areas based on the traffic characteristics identified, and finally prove the validity of the average speed predicted.

• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.151-159
• /
• 2010

This paper presents a research result that was performed to develop a more accurate freeway crash prediction model than existing models. While the existing crash models only focus on developing crash relationships associated with highway geometric conditions found on a short section of a crash site, this research applies a different approach considering the upstream highway geometric conditions as well. Theoretically, crashes occur while motorists are in motion, and particularly at freeways vehicle speed at one specific point is very sensitive to upstream geometric conditions. Therefore, this is a reasonable approach. To form the analysis data base, this research gathers the geometric conditions of the West Seaside Freeway 269.3 km and six years crash data ranging 2003-2008 for these freeway sections. As a result, it is found that crashes fit well into Negative Binomial Distribution, and, based on the developed model, total number of crashes is inversely proportional to highway curve length and radius. Contrarily, crash occurrences are proportional to tangent length. This result is different from existing crash study results, and it seems to be resulted from this research assumption that a crash is influenced greatly by upstream geometric conditions. Also, this research provides the expected effects on crash occurrences of the length of downgrade sections, speed camera placements, and the on- and off- ramp presences. It is expected that this research result is useful for doing more reasonable highway designs and safety audit analysis, and applying the same research approach to national roads and other major roads in urban areas is recommended.

• International Journal of Highway Engineering
• /
• v.16 no.5
• /
• pp.83-90
• /
• 2014

PURPOSES : The purpose of this study is to identify the factors affecting the effectiveness of speed limit change that is defined as the amount of increased travel speed. METHODS : A ordered logit model was adopted to analyze the relationship between the change in travel speed and contributing factors. A stretch of Kyungbu freeway was selected for the analysis because the Korea expressway corporation has raised speed limit from 100km/h to 110km/h since September 1st in 2010. RESULTS : The results showed that geometric design elements, speeding cameras, and section length were identified as factors contributing the effectiveness. Contributing geometric design elements include the number of horizontal curves and vertical curves that do not meet the design requirement with 110km/h speed limit. CONCLUSIONS : The outcome of this study will be used for establishing various traffic operations and control strategies for freeway speed management.

• International Journal of Highway Engineering
• /
• v.17 no.6
• /
• pp.85-95
• /
• 2015

PURPOSES : The objective of this study is to analyze factors affecting traffic accident severity for determining countermeasures on freeway climbing lanes. METHODS : In this study, an ordered probit model, which is a widely used discrete choice model for categorizing crash severity, was employed. RESULTS : Results suggest that factors affecting traffic accident severity on climbing lanes include speed, drowsy driving, grade of uphill 3%, gender (male offender and male victim), and cloud weather. CONCLUSIONS : Several countermeasures are proposed for improving traffic safety on freeway climbing lanes based on the analysis of crash severity. More extensive analysis with a larger data set and various modeling techniques are required for generalizing the results.

• International Journal of Highway Engineering
• /
• v.16 no.4
• /
• pp.127-134
• /
• 2014

PURPOSES : To operate more efficient traffic management system, it is utmost important to detect the change in congestion level on a freeway segment rapidly and reliably. This study aims to develop classification method of congestion change type. METHODS: This research proposes two classification methods to capture the change of the congestion level on freeway segments using the dedicated short range communication (DSRC) data and the vehicle detection system (VDS) data. For developing the classification methods, the decision tree models were employed in which the independent variable is the change in congestion level and the covariates are the DSRC and VDS data collected from the freeway segments in Korea. RESULTS : The comparison results show that the decision tree model with DSRC data are better than the decision tree model with VDS data. Specifically, the decision tree model using DSRC data with better fits show approximately 95% accuracies. CONCLUSIONS : It is expected that the congestion change type classified using the decision tree models could play an important role in future freeway traffic management strategy.

• 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.

• International Journal of Highway Engineering
• /
• v.17 no.5
• /
• pp.123-133
• /
• 2015

PURPOSES : This study aimed to develop a new highway capacity estimation method and provide comparative results among traditional capacity estimation methods and the recommended values in the latest version of KHCM. METHODS : The limitations of the existing methods, such as inconsistency and underestimation of the capacity value, are summarized through an extensive literature review. To overcome these limitations, a new method is introduced by adopting a definition of capacity and traffic flow characteristics at or near breakdown points. This method can produce the capacity value by searching a point corresponding to the maximum traffic flow through analysis of gradient changes (point of inflection) of the traffic flow and speed distribution. Comparative results of capacity values from each method are also presented to validate the new method by using data collected from detectors on freeways. RESULTS: From the analysis results, it is shown that a consistent capacity value can be estimated by applying the new method. In addition, the resulting capacity values are 3%-4% higher than those recommended in KHCM. CONCLUSIONS : The capacity values listed in the current KHCM tend to produce underestimated results. The new method presented in this paper may be included in the future edition of KHCM.

• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.405-418
• /
• 2016

Recently, many researchers have studied the VSL decision method using traffic information in multiple detector zones. However, this method selects incorrect VSL starting points, leading to the selection of the wrong speed control zone and calculation of the wrong VSL, causing traffic congestion. Eventually, the Unstable VSL system causes more congestion on the freeway. This paper proposes an improved VSL algorithm stably operated in multiple detector zones on the Korea highway. The proposed algorithm selects a preliminary VSL start station (VSS) expected to end the congestion using the acceleration of stations. It also determines the VSS at each congestion area. Finally, it calculates the VSL relative to the determined VSS and controls the vehicles that enters the traffic congestion zone. The developed strategy is compared with Real-time Variable Speed Limits for Urban Freeway (RVSL) to test the stability and efficiency of the proposed algorithm. The results show that the proposed algorithm resolves the problems of the existing algorithm, demonstrated by the correct VSS decision and the reduction of total travel time by 1-2 minutes.