• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.7
• /
• pp.1398-1404
• /
• 2009

This paper proposes a vehicle speed detector with anisotropic magnetoresistive (AMR) sensors and addresses experimental results to show the performance of the detector. The detector consists of two AMR sensors and mechanical and electronic apparatuses. The AMR sensor senses disturbance of the earth magnetic field caused by a vehicle moving over the sensor and then produces an output indicative of the moving vehicle. In this paper, vehicle speeds are calculated by using two AMR sensors built on a board. The speed of a vehicle is calculated by dividing the known distance between the two sensors with the time difference between two output signals from each sensor, captured sequentially while the vehicle is driving over the sensors. Some field tests have been carried to show the performance of the proposed detector and its usefulness.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• pp.696-701
• /
• 2000

In this study, a mathematical model fur analyzing the shift characteristics is proposed. The proposed model comprises power transmission system and vehicle system, which are coupled. And On-road car test is carried out in order to extract model parameters. Tile model is composed of a detailed powertrain, an engine/AT housing, a simplified suspension system. tires and a vehicle body model. On the test, the vehicle accelerations and pitch ratio are measured by using accelerometers and gyro sensor. The other data, for example speeds, a throttle position and a brake signal, are taken from sensors which already exist in the vehicle. Using natural frequency and characteristic equation, vehicle model parameters are extracted from experimental data.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.2
• /
• pp.133-139
• /
• 2013

This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle's position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.139-139
• /
• 2000

The subject of this paper is the tole operation for unmanned vehicle. The aim is studied in context of motor control system and algorithms for the mid to low level control of tele operation unmanned vehicle described. Modern, vehicle related researches have been implemented about control, chassis, body and safe쇼 but now is to driving comfort, I.T.S. and human factor, etc. As a result of this fact, unmanned vehicle is main research topic over the world but it is still very expensive and unreasonable. A hierarchical approach is studied in context of motor control system and algorithms for the mid to low level control of tele operation unmanned vehicle described. The real time control and monitoring of longitudinal, lateral, Pitching motion is to be solved by system integration and optimization technique. We show the experimental result about fixed brake range test and acceleration test. And all system is to integrated for driving simulator and unmanned vehicle.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.1
• /
• pp.89-94
• /
• 2018

The electric power system design of the electric vehicle are required to improve the performance. The electric power system on the electric vehicle are consist of a battery, a pedal sensor, an electric motor and a controller. In this paper, Automotive manufacture's various electric vehicle models are investigated and analyzed. The mathematical models for the electric power system are studied, and then important variables are considered. Simulation and experimental test results show the model of the electric power system on the electric vehicle and design parameter decision are effective to the electric vehicle design.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.420-423
• /
• 2003

This paper addresses the results of experimental and analytical study on the effects of dynamic interaction between vehicle and bridge on modal properties of bridge. Based on ambient vibration test and vehicle impact test on a bridge, it is found that the natural frequencies of bridge are varied by vehicle passing. Analytical studies for the effects of vehicle position, speed, damping, mass ratio and frequency ratio on bridge-vehicle interaction are carried out using complex eigenvalue analysis and numerical integration in time domain. The results show that vehicle properties except speed cause significant change of natural frequency as well as damping of bridge.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1092-1099
• /
• 2017

This paper proposes a novel way of vehicle detection and classification based on image features. There are two main processes in the proposed system, which are database construction and vehicle classification processes. In the database construction, there is a tight censorship for choosing appropriate images of the training set under the rigorous standard. These images are trained using Haar features for vehicle detection and histogram of oriented gradients extraction for vehicle classification based on the support vector machine. Additionally, in the vehicle detection and classification processes, the region of interest is reset using a number plate to reduce complexity. In the experimental results, the proposed system had the accuracy of 0.9776 and the $F_1$ score of 0.9327 for vehicle classification.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.663-672
• /
• 2023

Most vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.

• Journal of computational fluids engineering
• /
• v.21 no.1
• /
• pp.30-35
• /
• 2016

In order to investigate effects of grid resolution on large-eddy simulation of flow over a heavy vehicle, large-eddy simulations over the vehicle with coarse grid and fine grid are conducted. In addition, comparison of drag coefficients with the experimental data obtained by a wind tunnel experiment is conducted. Both of the drag coefficients of coarse grid and fine grid large-eddy simulation show good agreement with the experimental data. Flow fields obtained by the coarse and the fine grid large-eddy simulation are compared in the vehicle frontal-face region, the vehicle rear wheel region, and the vehicle base region. Coarse grid large-eddy simulation shows good agreement with the fine grid large-eddy simulation in the vehicle front face region and the vehicle rear wheel region, since the flow over the present vehicle is dominated by flow separation which is geometrically pre-determined, not by the skin friction which is known to be sensitive to grid resolution.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.1
• /
• pp.251-256
• /
• 2019

This paper presents an algorithm for recognizing and tracking a vehicle at a distance using a monocular camera installed at the center of the windshield of a vehicle to operate an autonomous vehicle in a racing. The vehicle is detected using the Haar feature, and the size and position of the vehicle are determined by detecting the shadows at the bottom of the vehicle. The region around the recognized vehicle is determined as ROI (Region Of Interest) and the vehicle shadow within the ROI is found and tracked in the next frame. Then the position, relative speed and direction of the vehicle are predicted. Experimental results show that the vehicle is recognized with a recognition rate of over 90% at a distance of more than 100 meters.