• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.73-82
• /
• 2011

Recent advancement in traffic surveillance systems has allowed the researchers to obtain more detailed vehicular movement such as individual vehicle trajectory data. Understanding the characteristics of interactions between leading and following vehicles in the traffic flow stream is a backbone for designing and evaluating more sophisticated traffic and vehicle control strategies. This study proposes a methodology for estimating rear-end crash potential, as a probabilistic measure, in real-time based on the analysis of vehicular movements. The methodology presented in this study consists of three components. The first predicts vehicle position and speed every second using a Kalman filtering technique. The second estimates the probability for the vehicle's trajectory to belong to either 'changing lane' or 'going straight'. A binary logistic regression (BLR) is used to model the lane-changing decision of the subject vehicle. The other component calculates crash probability by employing an exponential decay function that uses time-to-collision (TTC) between the subject vehicle and the front vehicle. The result of this study is expected to be adapted in developing traffic control and information systems, in particular, for crash prevention.

• Journal of Korea Game Society
• /
• v.21 no.2
• /
• pp.67-78
• /
• 2021

Since the release of and in 2017, business models for collection mobile games have been changing. Collection Mobile games are composed mainly of characters, and the business model is also highly related to user preference factors. The Delphi method and the AHP analysis were used on ten experts in each field of game production to identify preference factors, and five collection mobile games were selected for business model analysis. The result shows that 'moe' characters are a major preference factor, and accordingly, business models are also changing to focus on the completion of character collection and products such as character skins.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.5
• /
• pp.176-182
• /
• 2003

The researches for autonomous vehicle have been implemented in many studies, but most studies were confined to the lane fol1owing and changing. This paper addresses a problem of autonomous lane following parking a nonholonomic vehicle. The algorithm for image processing by the hough transform and controlling a steering angle and speed to park a nonholonomic vehicle is developed. The developed system which integrated the control algorithm for parking and vision algorithm for line traction tested with RC car and verified by the performance of the detection of parking area and the reactive parking without collisions.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.215-224
• /
• 2013

This paper proposes a robust lane detection algorithm for bumpy or slope changing roads by estimating extrinsic camera parameters, which represent the pose of the camera mounted on the car. The proposed algorithm assumes that two lanes are parallel with the predefined width. The lane detection and the extrinsic camera parameter estimation are performed simultaneously by utilizing B-snake in motion compensated and merged feature map with consecutive sequences. The experimental results show the robustness of the proposed algorithm in various road environments. Furthermore, the accuracy of extrinsic camera parameter estimation is evaluated by calculating the distance to a preceding car with the estimated parameters and comparing to the radar-measured distance.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.

• International Journal of Highway Engineering
• /
• v.18 no.3
• /
• pp.95-107
• /
• 2016

PURPOSES : This study compared two measures of traffic flow effectiveness on roads with roundabouts and signalized intersections and determined the more appropriate measure. METHODS : In addition to average delay time, the conventionally used measure, average travel time was introduced to measure traffic flow effectiveness because it is able to be obtained through field survey and reflect different travel distances and speed limits of roundabouts and signalized intersections. Using the two measures, roundabouts and signalized intersections were compared through simulations in terms of traffic flow effectiveness. RESULTS : For one-way single-lane roads, the two measures indicated consistent results that roundabouts were more effective than were signalized intersections when the traffic volume was less than 300 vphpl but vice versa when it exceeded 450 vphpl; however, the measures yielded inconsistent results when the volume was 350~400 vphpl. For one-way double-lane roads, the two measures indicated consistent results that roundabouts were more effective than were signalized intersections when the volume was less than 200 vphpl but vice versa when it exceeded 400 vphpl; however, the measures yielded inconsistent results when the volume was 250~350 vphpl. The results obtained using the two measures differed substantially for double-lane roads because behaviors such as weaving and lane changing at roundabouts are more common in double-lane roads than in single-lane roads. CONCLUSIONS : The average delay time would be lower on roads with roundabouts, but average travel time would be lower on roads with signalized intersections. Thus, evaluating the relative effectiveness of roads with roundabouts and signalized intersections by using average delay time alone would be inappropriate, whereas using average travel time as the evaluation index would yield fairer results.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6D
• /
• pp.785-791
• /
• 2011

Two-lane and two-way traffic flow shows various dynamic relationships according to the behaviors of low-speed vehicle and overtaking. And it is essential to develop a vehicle model which simultaneously explains the behaviors of low-speed vehicle and overtaking using opposite lane in order to microscopically analyze various two-lane and two-way traffic flows by traffic flow simulation. In Korea, some studies for car-following and lane-changing models for freeway or signalized road have been reported, but few researches for the development of vehicle model for two-lane and two-way highway have been done. Hence, a microscopic two-lane and two-way vehicle model was, in this study, developed with the consideration of overtaking process and is based on CA (Cellular Automata) which is one of discrete time-space models. The developed model is parallel combined with an adjusted CA car-following model and an overtaking model. The results of experimental simulation showed that the car-following model explained the various macroscopic relationships of traffic flow and overtaking model reasonably generated the various behaviors of macroscopic traffic flows under the conditions of both opposite traffic flow and stochastic parameter to consider overtaking. The vehicle model presented in this study is expected to be used for the simulation of more various two-lane, two-way traffic flows.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.5
• /
• pp.463-470
• /
• 2015

When a camera installed on a vehicle is used, estimation of the camera pose including tilt, roll, and pan angle with respect to the world coordinate system is important to associate camera coordinates with world coordinates. Previous approaches using huge calibration patterns have the disadvantage that the calibration patterns are costly to make and install. And, previous approaches exploiting multiple vanishing points detected in a single image are not suitable for automotive applications as a scene where multiple vanishing points can be captured by a front camera is hard to find in our daily environment. This paper proposes a camera pose estimation method. It collects multiple images of lane markings while changing the horizontal angle with respect to the markings. One vanishing point, the cross point of the left and right lane marking, is detected in each image, and vanishing line is estimated based on the detected vanishing points. Finally, camera pose is estimated from the vanishing line. The proposed method is based on the fact that planar motion does not change the vanishing line of the plane and the normal vector of the plane can be estimated by the vanishing line. Experiments with large and small tilt and roll angle show that the proposed method outputs accurate estimation results respectively. It is verified by checking the lane markings are up right in the bird's eye view image when the pan angle is compensated.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.11
• /
• pp.19-26
• /
• 2012

Reversible lanes in urban intersections is used to efficiently control vehicles, reduce traffic congestion and increase the capacity of a roadway. But by far traffic control systems in urban intersections are simple and manually operated by police officers. In this study, we present a hybrid algorithm that intelligently resolve the moving direction of reversible lanes to efficiently manage the flow of traffic at intersection. The proposed algorithm consists of three stages:(i) fuzzy inference method to get the efficiency of moving direction, (ii) a provisional decision whether to change the reversible lane to different direction, (iii) a final evaluation criterion for changing the directions of the reversible lanes. The fuzzy inference results of efficiency are shown by using matlab application.

• Journal of Korean Society of Transportation
• /
• v.31 no.4
• /
• pp.58-66
• /
• 2013

Due to the characteristics of urban freeways such as heavy traffic and high speed, work zone on urban freeways causes the increase of not only the likelihood of crash occurrence but also traffic congestion caused by lane drop, lane change, acceleration/deceleration, and etc. This paper aims to determine the proper length of transition area that satisfies two criteria, mobility and safety, to make the operation of work zone more efficient. For the analysis, three different scenarios were developed by the number of lanes and the proper length of transition area were determined by changing the length from 100m to 500m in 100m increments. The results showed that the proper length of transition area for 3- and 4-lane freeways is 300m, whereas the proper length of 2-lane freeways is 200m. The results indicated that the different length of transition area based on the number of lanes is more desirable and efficient.