• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1496-1504
• /
• 2004

In this paper, we propose an algorithm for initializing a target vehicle detection, tracking the vehicle and estimating the distance from it on the stereo images acquired from a forward-looking stereo camera mounted on a road driving vehicle. The process of vehicle detection extracts road region using lane recognition and searches vehicle feature from road region. The distance of tracking vehicle is estimated by TSS correlogram matching from stereo Images. Through the simulation, this paper shows that the proposed method segments, matches and tracks vehicles robustly from image sequences obtained by moving stereo camera.

• Journal of Power Electronics
• /
• v.15 no.6
• /
• pp.1508-1516
• /
• 2015

A single phase H-bridge inverter is employed in conventional Inductive Power Transfer (IPT) systems as the primary side power supply. These systems may not be suitable for some high power applications, due to the constraints of the power electronic devices and the cost. A high-frequency cascaded multi-level inverter employed in IPT systems, which is suitable for high power applications, is presented in this paper. The Phase Shift Pulse Width Modulation (PS-PWM) method is proposed to realize power regulation and selective harmonic elimination. Explicit solutions against phase shift angle and pulse width are given according to the constraints of the selective harmonic elimination equation and the required voltage to avoid solving non-linear transcendental equations. The validity of the proposed control approach is verified by the experimental results obtained with a 2kW prototype system. This approach is expected to be useful for high power IPT applications, and the output power of each H-bridge unit is identical by the proposed approach.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.2
• /
• pp.113-120
• /
• 2017

In this paper, we present a night-time vehicle detection method using CNN (Convolutional Neural Network) classification. The camera based night-time vehicle detection plays an important role on various advanced driver assistance systems (ADAS) such as automatic head-lamp control system. The method consists mainly of thresholding, labeling and classification steps. The classification step is implemented by existing CIFAR-10 model CNN. Through the simulations tested on real road video, we show that CNN classification is a good alternative for night-time vehicle detection.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.4
• /
• pp.579-589
• /
• 2011

One of the most significant UUV(Unmanned Underwater Vehicle) applications is MCM(Mine Countermeasure), which makes good use of UUV characteristics to provide covert, rapid, controlled and efficient survey of a potential minefield without risking a human operator. In this paper, a survey of the today's MCM missions where UUVs will play a role, the vehicle systems that are either under development or planned in the future are presented. And examines principal technical challenges and outline new enabling technologies. Particularly, this paper analyses current approaches to tacking these technologies and technological limitation of UUVs as a MCM platform, and research efforts to develop the technology necessary to meet the domestic MCM mission needs.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.953-956
• /
• 2017

This paper introduces general applications of vehicle's dynamic pressure information which is estimated during the flight. And a method to estimate the dynamic pressure for a high speed vehicle is suggested to sustain reliability of the flight under a high estimation accuracy of the information. The presented method is straightforward with simple relations of the compressible flow but is a still merited idea employed for the high speed vehicle control scheme with great accuracy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.1
• /
• pp.8-15
• /
• 2011

This paper presents an effective method for detecting vehicles in front of the camera-assisted car during nighttime driving. The proposed method detects vehicles based on detecting vehicle headlights and taillights using techniques of image segmentation and clustering. First, in order to effectively extract spotlight of interest, a pre-signal-processing process based on camera lens filter and labeling method is applied on road-scene images. Second, to spatial clustering vehicle of detecting lamps, a grouping process use light tracking method and locating vehicle lighting patterns. For simulation, we are implemented through Da-vinci 7437 DSP board with visible light mono-camera and tested it in urban and rural roads. Through the test, classification performances are above 89% of precision rate and 94% of recall rate evaluated on real-time environment.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.3
• /
• pp.132-138
• /
• 2011

This paper presents an intelligent control approach for lateral position control of an autonomous four wheel steered snowplowing robotic vehicle. The vehicle is built for removing snow on the highway. Dynamics of the vehicle is derived and linearized for LQR control. Lateral position is controlled by the LQR method first, then the neural network control technique is introduced to improve tracking performances under the presence of load. The feasibility of using four wheel steering control is investigated by simulation studies of lateral position tracking of the Ford F-250 truck model. Performances of a LQR control method and a neural network control method under virtual snowplowing situation are compared.

• Corrosion Science and Technology
• /
• v.18 no.4
• /
• pp.117-120
• /
• 2019

Considering the tendency of development of electrification vehicles, development and verification of new evaluation technology is needed because of new technology applications. Recently, as the battery package is set outdoors of an electric vehicle, such vehicles are exposed to corrosive environments. Among major components connected to the battery package, rust prevention of high-voltage cables and connectors is considered the most important issue. For example, if corrosion of high voltage cable connectors occurs, the corrosion durability assessment of using an electric vehicle will be different from general environmental corrosion phenomena. The purpose of this study is to investigate the corrosion mechanism of high voltage cable connectors of an electric vehicle under various driving environments (road surface vibration, corrosion environment, current conduction by stray current, etc.) and develop an optimal rust prevention solution. To improve our parts test method, we have proposed a realistic test method to reproduce actual electric vehicle corrosion issues based on the principle test.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.85-92
• /
• 2022

Currently, various researches on electric vehicle battery systems have been conducted from the viewpoint of safety and performance for SoC, SoH, etc. However, it is difficult to build a precise electrical model of a battery system based on the chemical reaction and SoC prediction. Experimental measurements and predictions of the battery SoC were usually performed using dynamometers. In this paper, we construct a simulation model of an electric vehicle system using Matlab Simulink, and confirm the response characteristics based on the vehicle test driving profiles. In addition, we show that it is possible to derive the correlation between the SoC, voltage, and current of the battery according to the driving time of the electric vehicle in conjunction with the BMS model.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.71-76
• /
• 2022

In autonomous driving cars, 3D pose estimation can be one of the effective methods to enhance safety control for OOP (Out of Position) passengers. There have been many studies on human pose estimation using a camera. Previous methods, however, have limitations in automotive applications. Due to unexplainable failures, CNN methods are unreliable, and other methods perform poorly. This paper proposes robust real-time multi-human 3D pose estimation architecture in vehicle using monocular RGB camera. Using particle filter, our approach integrates CNN 2D/3D pose measurements with available information in vehicle. Computer simulations were performed to confirm the accuracy and robustness of the proposed algorithm.