• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.116-125
• /
• 2014

Road conditions can provide important information for driving safety in driving assistance systems. The input images usually include unnecessary information and they need to be analyzed only in a region of interest (ROI) to reduce the amount of computation. In this paper, a vision-based road ROI determination algorithm is proposed to detect the road region using the positional information of a vanishing point and line segments. The line segments are detected using Canny's edge detection and Hough transform. The vanishing point is traced by a Kalman filter to reduce the false detection due to noises. The road ROI can be determined automatically and adaptively in every frame after initialization. The proposed method is implemented using C++ and the OpenCV library, and the road ROIs are obtained from various video images of black boxes. The results show that the proposed algorithm is robust.

• The Journal of Korea Robotics Society
• /
• v.7 no.3
• /
• pp.205-215
• /
• 2012

A GPS sensor is widely used in many areas such as navigation, or air traffic control. Particularly, the car navigation system is equipped with GPS sensor for locational information. However, when a car goes through a tunnel, forest, or built-up area, GPS receiver cannot get the enough number of satellite signals. In these situations, a GPS receiver does not reliably work. A GPS error can be formulated by sum of bias error and sensor noise. The bias error is generated by the geometric arrangement of satellites and sensor noise error is generated by the corrupted signal noise of receiver. To enhance GPS sensor accuracy, these two kinds of errors have to be removed. In this research, we make the road database which includes Road Database File (RDF). RDF includes road information such as road connection, road condition, coordinates of roads, lanes, and stop lines. Among the information, we use the stop line coordinates as a feature point to correct the GPS bias error. If the relative distance and angle of a stop line from a car are detected and the detected stop line can be associated with one of the stop lines in the database, we can measure the bias error and correct the car's location. To remove the other GPS error, sensor noise, the Kalman filter algorithm is used. Additionally, using the RDF, we can get the information of the road where the car belongs. It can be used to help the GPS correction algorithm or to give useful information to users.

• Tribology and Lubricants
• /
• v.33 no.6
• /
• pp.303-308
• /
• 2017

Most automobile tire companies have not yet considered the geometric information of a road at the design stage of a tire because the topographical characterization of a road surface is very difficult owing to its vastness and randomness. A road surface shows variable surface roughness values according to magnification, and thus, the contact force between the road and tire significantly fluctuates with respect to the scale. In this study, we make an attempt to define a representative value for surface topographical information at multi-scale levels. To represent surface topography, we use a statistical method called power spectral density (PSD). We use the fast Fourier transform (FFT) and PSD to analyze the height profiles of a random surface. The FFT and PSD of a surface help in obtaining a fractal dimension, which is a representative value of surface topography at all length scales. We develop three surfaces with different fractal dimensions. We use finite element analysis (FEA) to observe the contact forces between a tire and the road surfaces with three different fractal dimensions. The results from FEA reveal that an increase in the fractal dimension decreases the contact length between the tire and road surfaces. On the contrary, the average contact force increases. This result indicates that designing and manufacturing a tire considering the fractal dimension of a road makes safe driving possible, owing to the improvement in service life and braking performance of the tire.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.149-155
• /
• 2022

This paper proposes a method for estimating the road surface condition and tilt angle using an inertial measurement unit (IMU) to improve the safety in the use of mobility aids for the elderly. The measurements of the accelerometers of the IMU usually include the accelerations caused by not only the gravitational force but also linear and rotational motions. Thus, the gravitational accelerations are first extracted using several physical constraints and then incorporated into the Kalman filter to estimate the tilt angle. In addition, because the magnitudes of the accelerations produced by the rotational motions (roll and pitch motions) vary with the road surface condition, a criterion based on such accelerations is presented to classify the condition of the road surface. The obtained road surface condition and tilt angle are finally combined to provide the safety information (e.g., safe, warning, and danger) for the user to improve the walking safety. Experiments were carried out and the results showed that the proposed method can provide the condition of the road surface, the tilt of the road surface, and the safety information correctly.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.673-674
• /
• 2023

도로교통의 안전 확보와 사고 예방을 목적으로 운전자나 보행자에게 필요한 정보를 제공하기 위해 경찰청에서 규격 또는 지침으로 제정하여 노변에 설치되는 교통안전시설 장치는 교통신호정보를 받기 위한 통신선과 함께 장치 구동을 위한 전원선을 개별로 시공해야 하기에 시공 비용의 절감과 함께 다종·다형의 장치에 대하여 통합적인 관제, 확장성, 유연성에 대응할 필요성이 제기되고 있다. 이에 본 논문에서는 이더넷 통신을 기반으로 전원 공급이 하나의 케이블로 가능한 이더넷 전원장치(PoE) 기술과 IoT 프로토콜인 MQTT를 이용하여 다종·다형의 교통안전시설 장치를 통합관제하고, 확장성과 유연성을 가지는 교통안전시설 장치 통합 시스템을 제안한다.

• Journal of Auto-vehicle Safety Association
• /
• v.10 no.1
• /
• pp.32-37
• /
• 2018

This paper proposes autonomous speed control strategy for an Electric Vehicle on urban road. SNU campus road is used to reperesent urban road situation. Motor efficiency of driving on campus circulation road can be improved by controlling velocity properly. Given information of campus road, especially slope of road, acceleration is selected from candidate, considering consumed power, human factor and driving time. To apply urban situation, preceding vehicle is also considered. With preceding vehicle, acceleration is defined according to clearance and relative velocity. Acceleration is bounded in normal range. Proposed acceleration control method is activated with proper velocity range for campus circulation road. With acceleration control, motor efficiency becomes better than driving with constant vehicle. To evaluate the performance of proposed acceleration controller, simulation study is conducted via MATLAB.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.98.3-98
• /
• 2002

Vision-based systems for finding road lanes have to operate robustly under a wide variety of environ-mental conditions including large amount of scene clutters. This paper presents a method for finding the lane boundaries by combining a local line extraction method and dynamic programming as a search tool. The line extractor obtains an initial position estimation of road lane boundaries from the noisy edge fragments. Dynamic programming then improves the initial approximation to an accurate configuration of lane boundaries. Input image frame is divided into a few sub-regions along the vertical direction. The local line extractor then performs to extract candidate lines of road lanes in the...

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.656-657
• /
• 2008

Light Detection and Ranging (LiDAR) data has been used to detect the objects of earth surface from huge point clouds gotten from the laser scanning system equipped on airplane. According to the precision of 3~5 points per square meter, objects like buildings, cars and roads can be easily described and constructed. Many various areas, such as hydrological modeling and urban planning adopt this kind of significant data. Researchers have been engaging in finding accurate road networks from LiDAR data recent years. In this paper, A novel algorithm with regard to extracting road points from LiDAR data has been developed based on the continuity and structural characteristics of road networks.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.208-214
• /
• 2014

Vehicle dynamic states used in various advanced driving safety systems are influenced by road geometry. Among the road geometry information, the vehicle pitch angle influenced by road slope and acceleration-deceleration is essential parameter used in pose estimation including the navigation system, advanced adaptive cruise control and others on sag road. Although the road slope data is essential parameter, the method measuring the parameter is not commercialized. The digital map including the road geometry data and high-precision DGPS system such as DGPS(Differential Global Positioning System) based RTK(Real-Time Kinematics) are used unusually. In this paper, low-cost cascade extended Kalman filter(CEKF) based road slope estimation method is proposed. It use cascade two EKFs. The EKFs use several measured vehicle states such as yaw rate, longitudinal acceleration, lateral acceleration and wheel speed of the rear tires and 3 D.O.F(Degree Of Freedom) vehicle dynamics model. The performance of proposed estimation algorithm is evaluated by simulation based on Carsim dynamics tool and T-car based experiment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.164-169
• /
• 2009

This paper proposes a road detection method using BP(Back-Propagation) neural network based on texture information of the each candidate road region segmented for satellite images. To segment the candidate road regions, the histogram-based binarization method proposed by N.Otsu is firstly performed and the neighboring regions surrounding road regions are then removed. And after extracting the principal color using the histogram of the segmented foreground, the candidate road regions are classified into the regions within ${\pm}25$ of the principal color. Finally, the road regions are segmented using BP neural network based on texture information of the candidate regions. The texture information in this paper is calculated using co-occurrence matrix and is used as an input data of the BP neural network. The proposed method is based on the fact that the road has the constant intensity and shape. The experiment demonstrated the validity of the proposed method and showed 90% detection accuracy for the various images.