• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.125-131
• /
• 2019

A vanishing point is a point on an image to which parallel lines projected from a real space gather. A vanishing point in a road space provides important spatial information. It is possible to improve the position of an extracted lane or generate a depth map image using a vanishing point in the road space. In this paper, we propose a method of detecting vanishing points on images taken from a vehicle's point of view using Deep Neural Network (DNN) and Histogram of Oriented Gradient (HoG). The proposed algorithm is divided into a HoG feature extraction step, in which the edge direction is extracted by dividing an image into blocks, a DNN learning step, and a test step. In the learning stage, learning is performed using 2,300 road images taken from a vehicle's point of views. In the test phase, the efficiency of the proposed algorithm using the Normalized Euclidean Distance (NormDist) method is measured.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.438-444
• /
• 2019

With the increasing supply of vehicles, construction of new roads and expansion of existing roads are growing and this is leading to a proportional rise in diverse hazards on a road. These hazards are classified into fixed hazards and variable hazards. Currently, drivers receive information of fixed hazards, such as overspeed, frequent accidents, and rock fall through navigations. However, variable hazards are more hazardous than fixed hazards. Map companies frequently enter information of variable hazards manually, but it is less real-time and hard to deal with unforseen hazards. This paper is intended to implement a road hazard warning system for making a contribution to pubic interests by improving this problem and delivering real-time information of hazards to drivers, and suggest a direction for using information of hazards on a road.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.4
• /
• pp.50-61
• /
• 2022

Snow, rain, fog, and particulate matter interfere with the vehicle driver's vision, which causes a non-secure safety distance and an increase in speed deviation, causing repetitive large-scale traffic accidents. This study developed a road environment sensor capable of measuring 11 types of fog, snow, rain, temperature, humidity, direction of wind, speed of wind, Insolation, atmospheric pressure, fine particles, rainfall, etc. and compared the visibility measured by the infrared signal value of the development sensor. The relationship between the existing fog visibility sensor and the development sensor measurement was derived from data measured at a visibility of 500m or less that directly affects road safety.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.2
• /
• pp.42-48
• /
• 2023

In recent years, automated vehicles have garnered attention in the multidisciplinary research field, promising increased safety on the road and new opportunities for passengers. High-Definition (HD) maps have been in development for many years as they offer roadmaps with inch-perfect accuracy and high environmental fidelity, containing precise information about pedestrian crossings, traffic lights/signs, barriers, and more. Demonstrating autonomous driving requires verification of driving on actual roads, but this can be challenging, time-consuming, and costly. To overcome these obstacles, creating HD maps of real roads in a simulation and conducting virtual driving has become an alternative solution. However, existing HD maps using high-precision data are expensive and time-consuming to build, which limits their verification in various environments and on different roads. Thus, it is challenging to demonstrate autonomous driving on anything other than extremely limited roads and environments. In this paper, we propose a new and simple method for implementing HD maps that are more accessible for autonomous driving demonstrations. Our HD map combines the CARLA simulator and OpenStreetMap (OSM) data, which are both open-source, allowing for the creation of HD maps containing high-accuracy road information globally with minimal dependence. Our results show that our easily accessible HD map has an accuracy of 98.28% for longitudinal length on straight roads and 98.42% on curved roads. Moreover, the accuracy for the lateral direction for the road width represented 100% compared to the manual method reflected with the exact road data. The proposed method can contribute to the advancement of autonomous driving and enable its demonstration in diverse environments and on various roads.

• Journal of Game and Entertainment
• /
• v.2 no.1
• /
• pp.35-44
• /
• 2006

Objective of this study is to develop a 3D car navigation system that shows the driving direction to a destination through real-time 3-D panoramic views of the route. For the purpose, a new searching process was established to find the optimal driving direction based on the driver's current location and the real-time traffic situation and the TIP (tour into the picture) method was extended to implement a wide virtual environment. A virtual environment was built up by applying the extended TIP method to the panoramic images taken at a constant distance from a real road, and then, displayed 3-D navigation as clear as the real images. The car navigation system developed in this study provides the optimal driving direction and real-time traffic situation using 2-D navigation module and 3D navigation module.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.950-956
• /
• 2014

In this paper, the real-time detection method of a DDP (Driving Direction Point) is proposed for an unmanned vehicle to safely follow the center of the road. Since the DDP is defined as a center point between two lanes, the lane is first detected using a web camera. For robust detection of the lane, the binary thresholding and the labeling methods are applied to the color camera image as image preprocessing. From the preprocessed image, the lane is detected, taking the intrinsic characteristics of the lane such as width into consideration. If both lanes are detected, the DDP can be directly obtained from the preprocessed image. However, if one lane is detected, the DDP is obtained from the inverse perspective image to guarantee reliability. To verify the proposed method, several experiments to detect the DDPs are carried out using a 4 wheeled vehicle ERP-42 with a web camera.

• Journal of the Korean Society of Safety
• /
• v.19 no.3 s.67
• /
• pp.70-77
• /
• 2004

A Reasonable lighting should be provided for doing night work. All works far construction site can be exposed to potential hazard at night work The purpose of this study is to provide a standard of the lighting against accidents due to insufficient lighting at site. one pilot tea one at building work site, one at mad work site of it have been conducted for figuring out illumination change depending worker's activity direction, using lux checker to show it as numerical indication. The direction are changed with a range of 30, 60, 90, and 135 degree to be checked at site. Tests results show that $10\%\;and\;15\%$ of lighting could be decreased by changing the working direction of works at site. Therefore, steep slope place, cave work and backside of structural elements such as a column, deep beam should be considered for keeping sufficient and reasonable lighting. It is found that $50\%more$ illumination Lux needs f3r civil work than for building work.

• Journal of Sensor Science and Technology
• /
• v.22 no.4
• /
• pp.292-296
• /
• 2013

The ultrasonic wind sensor that pass through the air, beating the delivery of ultrasonic wind speed increases or decreases by the physical characteristics of the wind speed and the direction of the sensor, the transmission and reception of ultrasonic time difference measured by a two-axis vector wind and wind speed measured by calculating a device that converts the digital signal is Anemometer and wind direction meteorological facilities management, management of the ship sail used for various purposes, including, but used the existing 3-cup (mechanical) anemometer wind rotor caused by mechanical wear parts replacement due to the short-term, the reliability of the product is low, parts replacement, and according to the characteristics caused the car, there is a problem in high maintenance costs. In addition, because the bearings use of the marine environment and the cryogenic environment was constrained. In this study, the excellent long-term reliability, using ultrasonic-type environment that is not constrained to produce wind anemometer located $90^{\circ}$ conformal road using four piezoelectric sensors were fabricated structures, the piezoelectric oscillator circuit produces a rash and receiving transmit and receive speeds the car through the two-axis vector calculation to measure wind velocity processor firmware programming, and its characteristics were tested.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.1-11
• /
• 2006

This study conducts a theoretical research on road traffic noise. Also, the domestic road noise forecast models were compared each other and analyzed with advanced countries' models to indicate the application possibility and problems. For the establishment of a general formula, we compared the forecasted value with the actual value applied in the formula proposed by the National Environment Institute, and examined the necessary improvement of the domestic road traffic noise forecast model. Also, a regression model was built to examine the relationship between traffic factors and noise. The traffic volume and speed are the main traffic factors used in this formula to affect the noise. From the results, it was found that the speed had a closer relationship with the noise rather than the traffic volume. Therefore, to decrease road noise, it is more important to control traffic speed. The spatial effect of road traffic noise within the apartment complexes was used in the case study to derive location-specific adjustment values. We surveyed the road traffic noise of three apartment complexes, and found that the road traffic noise within each complex was affected at plane level as well as at three-dimensionally. In other words, as the distance from the sound origin grows farther, noise level decreases. Also, it was found that noise increases as heigt goes up, but drops when the height goes beyond a certain level, and that the effect of noise decreases if there are obstacles along the path of the noise direction. Therefore, apartment site design should be done with consideration of the effects of noise in the future.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.1
• /
• pp.106-111
• /
• 2012

Recently the usage of bicycle has increased steeply in Korea owing to traffic culture of well- being. In a car to bicycle accident investigation, the throw distance of bicycle is very important factor for reconstructing of the accident. The variables that influence on the throw distance of bicycle can be classified into the factors of vehicle and bicycle. Simulations and collision tests in actual car to bicycle accident were executed for obtaining throw distance of bicycle. The simulations were done by PC-$CRASH^{TM}$ and for actual crash tests sand bags were used for the behavior of bicyclist instead of dummy. Factors considered were vehicle velocity and the moving angles of bicycle, also the types of bicycle and vehicle were fairy cycle and automobile, respectively. From the results, the throw distances of a head-on tire collision of $0^{\circ}$ direction was longer than that of tire crash test of $45^{\circ}$ direction, and the throw distances of a head -on frame crash test of $90^{\circ}$ direction was longer than that of frame crash test of $45^{\circ}$ direction. In addition restitution coefficient between vehicle and bicycle was estimated as about 0.1 with based on actual crash tests. Finally the increaser vehicle velocity the longer the throw distances of bicycle, and the results of simulation were relatively good agreement to the experimental results.