• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.3
• /
• pp.636-644
• /
• 2010

A method for the detection of on-road succeeding vehicles using visual characteristic features like horizontal edges, shadow, symmetry and intensity is proposed. The proposed method uses the prominent horizontal edges along with the shadow under the vehicle to generate an initial estimate of the vehicle-road surface contact. Fast symmetry detection, utilizing the edge pixels, is then performed to detect the presence of vertically symmetric object, possibly vehicle, in the region above the initially estimated vehicle-road surface contact. A window defined by the horizontal and the vertical line obtained from above along with local perspective information provides a narrow region for the final search of the vehicle. A bounding box around the vehicle is extracted from the horizontal edges, symmetry histogram and a proposed squared difference of intensity measure. Experiments have been performed on natural traffic scenes obtained from a camera mounted on the side view mirror of a host vehicle demonstrate good and reliable performance of the proposed method.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.8
• /
• pp.233-247
• /
• 1999

Traffic accidents are normally caused by late or faulty judgements due to the driver's inaccurate estimation of the distance, velocity, and acceleration from the surrounding vehicles as well as his carelessness or inattention. Thus, the development of collision avoidance systems is motivated by their great potential for increased vehicle safety. A typical collision avoidance system consists of the forward-looking sensor, the criteria for activation of collision warming and avoidance, the collision avoidance maneuvers, and the user interface. This thesis is concerned with the development of a collision warning algorithm in which the driver is warned of approaching collision with the visual and/or the audible signals . The warning algorithm based on fuzzy logic is presented here based on new warning criteria. It has been newly derived from the conventional warning equation by adding a new input variable of the required deceleration to avoid collision. The algorithm is also able to adapt to the individual driver's taste along with the different road conditions by externally controlling the warning intensity. Finally , the proposed algorithm has been validated using computer simulation.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.142-148
• /
• 2006

Considering the domestic traffic environment and the increase of traffic accidents, we have been asked to exactly analyze the main causes of accidents for the accident-experienced drivers to be rehabilitated. In this thesis we present the development process and results of a driving simulator using the IPDE method in the interest of safe driving and driving rehabilitation. Through this Driving simulation development the rehabilitated driver has the possibility of experiencing the real driving situation with the driving aptitude and examines the reasons of accidents. Through the examinations the driver has the chance to correct the deformities of driving by choosing the explanatory scenes, and through this process the driver is able to develop the capability to react in the real situation. However this driving simulation system is one of the best developed, depending on weather and road condition the braking distance may change. Therefore the fuzzy rule and neural network have been used in this thesis to solve previously mentioned problem. The simulation exactly calculated the road and weather conditions to adjust the breaking intensity.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2009.06a
• /
• pp.449-451
• /
• 2009

Sea level rise and increase of the typhoon/hurricane intensity due to global warming have threaten coastal areas for residential and industrial and have been widely studied. In this study we showed our recent efforts on sea wind which is one of critical factors for safe maritime traffic and prediction for storm surges and waves. Currently, most of numerical weather models in korea do not have sufficient spatial and temporal resolutions, therefore we set up a find grid(about 9km) sea wind prediction system that predicts every 12 hours for three day using Weather Research and Forecasting(WRF). This system covers adjacent seas around korean peninsula Comparisons of two observed data, Ieodo Ocean Research station(IORS) and Yellow Sea Buoy(YSB), showed reasonable agreements and by data assimilation we will improve better accurate sea winds in near future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Korea Water Resources Association
• /
• v.33 no.2
• /
• pp.195-205
• /
• 2000

Many types of factors were devised to calculate time of concentration. Singh(976) derived time of concentration of overland flow using kinematic wave theory for plane, converging, and diverging geometric configurations. The present paper investigated the time of concentration for particularly plane geometric configuration. A theoretical equation of time of concentration is derived based on the assumption of impervious overland flow as in the open channel flow. The study characterized the overland flow by many types of characteristic flow such as rough turbulent flow, smooth turbulent flow, laminar flow, and then suggested a theoretical equation on each flow condition. The present paper further considered the rainfall intensity as a main factor and devised an approximate composite equation reflecting the effect of rainfall intensity given at various return periods.

• Wind and Structures
• /
• v.24 no.6
• /
• pp.579-611
• /
• 2017

Bora is a strong, usually dry temporally and spatially transient wind that is common at the eastern Adriatic Coast and many other dynamically similar regions around the world. One of the Bora main characteristics is its gustiness, when wind velocities can reach up to five times the mean velocity. Bora often creates significant problems to traffic, structures and human life in general. In this study, Bora velocity and near-ground turbulence are studied using the results of three-level high-frequency Bora field measurements carried out on a meteorological tower near the city of Split, Croatia. These measurements are analyzed for a period from April 2010 until June 2011. This rather long period allows for making quite robust and reliable conclusions. The focus is on mean Bora velocity, turbulence intensity, Reynolds shear stress and turbulence length scale profiles, as well as on Bora velocity power spectra and thermal stratification. The results are compared with commonly used empirical laws and recommendations provided in the ESDU 85020 wind engineering standard to question its applicability to Bora. The obtained results report some interesting findings. In particular, the empirical power- and logarithmic laws proved to fit mean Bora velocity profiles well. With decreasing Bora velocity there is an increase in the power-law exponent and aerodynamic surface roughness length, and simultaneously a decrease in friction velocity. This indicates an urban-like velocity profile for smaller wind velocities and a rural-like velocity profile for larger wind velocities. Bora proved to be near-neutral thermally stratified. Turbulence intensity and lateral component of turbulence length scales agree well with ESDU 85020 for this particular terrain type. Longitudinal and vertical turbulence length scales, Reynolds shear stress and velocity power spectra differ considerably from ESDU 85020. This may have significant implications on calculations of Bora wind loads on structures.

• Journal of Korean Society of Transportation
• /
• v.31 no.6
• /
• pp.3-11
• /
• 2013

Under the consumption of bad weather situation affects traffic flows, the study scope is focused on highway capacity and speed variations among other highway traffic flow characteristic changes according to snowfall density. Thus, this study carried out through the data collection and statistical analysis by focusing on capacity and speed changes. Traffic volume, speed and density were selected as factors to explain the property change of a traffic flow for analysis, and 7 basic sections such as 3 highways in Gyeonggi-do and 4 highways near the meteorological observatory were selected as survey points for data collection. Snowfall levels were classified into 3 steps(Light, Medium, Heavy Snow) to analyze the capacity change by snowfall levels. As a result of analysis, the change of capacity depending on snowfall levels decreased 13.2% in case of light snow compared to a good weather, 18.6% in case of medium snow and 32.0% in case of heavy snow, so the capacity reduction rate increased as the snowfall level increased. The worsening weather appeared to have a very big possibility to act as a factor to reduce the operational efficiency of a road, so a road design and operation method considering this should be presented in the future.

• Journal of the Optical Society of Korea
• /
• v.18 no.4
• /
• pp.317-329
• /
• 2014

In vision measurement systems based on structured light, the key point of detection precision is to determine accurately the central position of the projected laser line in the image. The purpose of this research is to extract laser line centers based on a decision function generated to distinguish the real centers from candidate points with a high recognition rate. First, preprocessing of an image adopting a difference image method is conducted to realize image segmentation of the laser line. Second, the feature points in an integral pixel level are selected as the initiating light line centers by the eigenvalues of the Hessian matrix. Third, according to the light intensity distribution of a laser line obeying a Gaussian distribution in transverse section and a constant distribution in longitudinal section, a normalized model of Hessian matrix eigenvalues for the candidate centers of the laser line is presented to balance reasonably the two eigenvalues that indicate the variation tendencies of the second-order partial derivatives of the Gaussian function and constant function, respectively. The proposed model integrates a Gaussian recognition function and a sinusoidal recognition function. The Gaussian recognition function estimates the characteristic that one eigenvalue approaches zero, and enhances the sensitivity of the decision function to that characteristic, which corresponds to the longitudinal direction of the laser line. The sinusoidal recognition function evaluates the feature that the other eigenvalue is negative with a large absolute value, making the decision function more sensitive to that feature, which is related to the transverse direction of the laser line. In the proposed model the decision function is weighted for higher values to the real centers synthetically, considering the properties in the longitudinal and transverse directions of the laser line. Moreover, this method provides a decision value from 0 to 1 for arbitrary candidate centers, which yields a normalized measure for different laser lines in different images. The normalized results of pixels close to 1 are determined to be the real centers by progressive scanning of the image columns. Finally, the zero point of a second-order Taylor expansion in the eigenvector's direction is employed to refine further the extraction results of the central points at the subpixel level. The experimental results show that the method based on this normalization model accurately extracts the coordinates of laser line centers and obtains a higher recognition rate in two group experiments.

• Journal of Service Research and Studies
• /
• v.14 no.3
• /
• pp.172-187
• /
• 2024

This paper deals with asymptotic approximations analysis of M/M/s and M/D/s queues. For M/M/s queue, we observe "economies of scale" under the fixed utilization ρ and the fixed probability α that customer waits in system, how the average system size vary according to the number of servers s increasing. Simulation results show that as s increases, the number of servers who are idling increases, that is, the slack n-E[Q_n] diverges. In addition, through changing the waiting probability α under the M/M/s system, α was not highly sensitive to the behavior of the system size. And, it is shown that using ${\rho}_n\,=\,1-k/\sqrt{n}$ to handle heavy-traffic regime is only appropriate for k = 1 by observing the effect on the performance of the system with different values of k. For the M/D/s queue, two approximations are used to evaluate the expected system size under the fixed ρ and α. Simulations and comparison of these two approximations show that Cosmetatos' approximation performs quite well when the number of servers is small and traffic intensity is heavy, but it overestimates the true value for the large number of servers. Meanwhile, the modified approximation gives good results for the steady state count of the system although the number of servers grows large.