• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.54-62
• /
• 2018

According to evolution of technologies, many devices related to various applications were researched. The advanced driver assistance system is a famous technique effected from the evolution. The technique of driver assistance uses image recognition methods to collect exactly information around the vehicle. The computing power of driver assistance device has become more improved than in the past. However, it's difficult that processed various recognition methods at real-time. We propose new frame skip method to process various recognition methods at real-time in the limited hardware. In the previous researches, frame skip rate was set up static values, thus the number of processed frames through recognition methods was smaller. We set up the frame skip rate dynamically using a driving condition of vehicle through speed and acceleration value, in addition, the number of processed frames was maximized. The performance is improved more 32.5% than static frame skip method.

• Journal of the Korean Society for Railway
• /
• v.18 no.1
• /
• pp.15-24
• /
• 2015

In magnetic levitation vehicles, the clearance between the magnet and track should be maintained within an allowable range through a feedback control loop. The flexibility of the guideway would introduce additional modes in the overall suspension system, resulting in dynamic interaction between the guideway vibration and the electromagnetic suspension control system. This dynamic interaction can be a serious problem, particularly at very low speeds or standstill, and may cause airgap instability. To optimize the overall system dynamics, an integrated dynamic model including mechanical and electrical parts and a flexible guideway as well as a control loop was developed. With the proposed model, airgap simulations at standstill were performed while varying the control gains, specifically with the aim of understanding the effects of gains of the PID controller on the airgap variation. The findings may be used to achieve a stable levitation controller design.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.241-250
• /
• 2016

AVM(Around View Monitoring) is a function of ADAS(Advanced Driver Assistance Systems), which provides a bird's eye view of the surroundings of a vehicle to the user. AVM systems require large bandwidth since they are composed of four input images and require real-time processing for vehicle-embedded environments. Also, the memory bandwidth requirement increases greatly when the resolution of the input data is higher. In this paper, we propose four basic hardware models of AVM systems. The models are decided by whether or not there is a valid data extraction module and an image processing purpose LUT generation module. We analyze the required bandwidth and hardware resource for each model. For verification of the proposed models, we implemented an AVM system using XC7Z045 FPGA and DDR3 memory for VGA and FHD resolution. All four of the proposed hardware model is executed below 33ms, which shows that it can operate in real-time.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.358-367
• /
• 2017

Advanced Driver Assistance Systems(ADAS), such as Front Collision Warning System (FCWS) are currently being developed. FCWS require high processing speed because it must operate in real time while driving. In addition, a low-power system is required to operate in an automobile embedded system. In this paper, FCWS is implemented in CPU-FPGA architecture in embedded system to enable real-time processing. The lane detection enabled the use of the Inverse Transform Perspective (IPM) and sliding window methods to operate at fast speed. To detect the vehicle, a Convolutional Neural Network (CNN) with high recognition rate and accelerated by parallel processing in FPGA is used. The proposed architecture was verified using Intel FPGA Cyclone V SoC(System on Chip) with ARM-Core A9 which operates in low power and on-board FPGA. The performance of FCWS in HD resolution is 44FPS, which is real time, and energy efficiency is about 3.33 times higher than that of high performance PC enviroment.

• KEPCO Journal on Electric Power and Energy
• /
• v.1 no.1
• /
• pp.33-38
• /
• 2015

Energy storage systems (ESSs) have been utilized widely in the world to optimize the power operation system and to improve the power quality. As lithium secondary batteries are the main power supplier for ESSs, it is very important to predict its cycle and power degradation behavior. In particular, the power, one of the hardest electrochemical properties to measure, needs lots of resources such as time and facilities. Due to these difficulties, computer modelling of lithium secondary batteries is applied to predict the DC-IR and power value during charging and discharging as a function of state of charge (SOC) by using pulse-based measurement methods. Moreover, based on the hybrid pulse power characteristics (HPPC) and J-Pulse (JEVS D 713, Japan Electric Vehicle Association Standards) methods, their electrochemical properties are also compared and discussed.

• Design & Manufacturing
• /
• v.12 no.3
• /
• pp.25-30
• /
• 2018

Recently The automotive industry is trying to increase the energy efficiency by reducing the weight of the car body and engine components as a way to achieve high energy efficiency. In particular, the reduction of the weight of the vehicle through the weight reduction of the vehicle body has the advantage that the fuel consumption and the output can be improved. But at the same time, there is the disadvantage that the strength becomes weak due to the reduction of the material thickness. Therefore, in order to overcome these disadvantages, materials with high strength according to the unit thickness have been actively developed, and researches for applying them have also been increasing. In this study, we will investigate the application of cold rolled steel sheet, which is a lightweight material, to a horn bracket that secures a installed in an automobile engine room. The horn bracket secures the horn on the car engine and is bolted to the outer wall of the engine. The momentum is acted on the bracket due to the distance between the bolt fastening part and the car horn installed on the bracket end side. Therefore, the body part of the bracket is more likely to be destroyed by the influence of the continuous stress. In this paper, design optimization for weight reduction and strength enhancement was performed to solve this problem, and possibility of applying the rolled steel sheet material as lightweight material by tensile test and fabrication was confirmed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.48-55
• /
• 2021

The 3-coil magnetic resonance wireless power transmission system was analyzed using an equivalent circuit model, and the |S21| of the system was expressed as the equation of the Q of the three coils, the coupling coefficient k between the transmitting coil and the relay coil, the relay coil and the receiving coil. It is suggested that the maximum efficiency can be obtained when the relay coil is located in the center of the transmitting and the receiving coil. When the distance between the transmitting and the receiving coil is 30 cm and the two coils are aligned, maximum efficiency of 9 % is obtained with the relay coil centered between the coils. If the transmitting coil and the receiving coil are misaligned during a wireless charging of an electric vehicle, the efficiency is expected to decrease significantly compared to the aligned case. It is expected that the efficiency can be increased by using a relay coil and by rotating the coil.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.2
• /
• pp.30-34
• /
• 2021

Electrical failures and reliability problems of electronic components by ionic migration between adjacent device terminals have become an issue in automotive electronics. Especially unlike galvanic corrosion, ionic migration is occurred at high temperature and high humidity under applied electric field condition. Until now, although extensive studies of the ionic migrations dealing with PCBs, electrodes, and solders were reported, there is no study on the effect of insulation polymers and metallic fillers for ionic migration. In this research, therefore, ionic migration induced by the types and contents of polymers and metallic fillers, and variety conditions of temperature, humidity, and applied voltage was studied in detail. Ester and amide types of liquid crystal polymer (LCP) and poly (phthalamide) (PPA) were used as base polymers, respectively and compounded with the metallic fillers of Copper iodide (CuI), Zinc stearate (Zn-st), or Calcium stearate (Ca-st) in various compositions. The compounding polymers were fabricated in IPC-B-24 of SIR test coupon according to ISO 9455-17 with Cu electrodes for ionic migration test. While there is no change in LCP-based samples, ionic migration in PPA compounding sample with a high water absorption property was accelerated in the presence of 0.25 wt% or above of CuI at the environmental conditions of 85℃, 85% RH and 48V. The dendritic short-circuit growth of Cu caused by ionic migration between the electrodes on the surface of compounded polymers was systematically observed and analyzed by using optical microscopy and SEM (EDX).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1124-1129
• /
• 2021

The application area based on UAV (Unmanned Aerial Vehicle) is continuously increasing as time passing by. In particular the UAVs which consist of more than four horizontal propellers and the functionality of VTOL (Vertical Take-Off and Landing) are utilized in diverse platforms and the application products due to their safety and aerodynamically simpler design and architectures. The most UAV missions are controlled by GCSs (Ground Control System). The GCSs are generally connected to the internet and get electrical map and environmental information such as temperature, humidity, wind speed, wind direction and so on. In this paper, we design a system for UAV system to have capability of approaching to a certain ship and monitoring her efficiently by using AIS (Auto Identification System) information. Furthermore we verify that adapting AIS on GCS side is more efficient through experiments.