• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.1
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.711-720
• /
• 2012

In this paper, we introduce the implementation of driver fatigue monitering system and its result. Input video device is selected commercially available web-cam camera. Haar transform is used to face detection and adopted illumination normalization is used for arbitrary illumination conditions. Facial image through illumination normalization is extracted using Haar face features easily. Eye candidate area through illumination normalization can be reduced by anthropometric measurement and eye detection is performed by PCA and Circle Mask mixture model. This methods achieve robust eye detection on arbitrary illumination changing conditions. Drowsiness state is determined by the level on illumination normalize eye images by a simple calculation. Our system alarms and operates seatbelt on vibration through controller area network(CAN) when the driver's doze level is detected. Our algorithm is implemented with low computation complexity and high recognition rate. We achieve 97% of correct detection rate through in-car environment experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.693-698
• /
• 2018

This paper proposes a vehicle detection method for parking areas using unmanned aerial vehicles (UAVs) and using YOLOv2, which is a recent, known, fast, object-detection real-time algorithm. The YOLOv2 convolutional network algorithm can calculate the probability of each class in an entire image with a one-pass evaluation, and can also predict the location of bounding boxes. It has the advantage of very fast, easy, and optimized-at-detection performance, because the object detection process has a single network. The sliding windows methods and region-based convolutional neural network series detection algorithms use a lot of region proposals and take too much calculation time for each class. So these algorithms have a disadvantage in real-time applications. This research uses the YOLOv2 algorithm to overcome the disadvantage that previous algorithms have in real-time processing problems. Using Darknet, OpenCV, and the Compute Unified Device Architecture as open sources for object detection. a deep learning server is used for the learning and detecting process with each car. In the experiment results, the algorithm could detect cars in a dense area using UAVs, and reduced overhead for object detection. It could be applied in real time.

• Journal of Korean Society of Rural Planning
• /
• v.11 no.1 s.26
• /
• pp.1-8
• /
• 2005

The purpose of this study is to develop a simulation model of rural road path for infrastructure of green-tourism and public service in rural areas. This study makes an objective function for moving cost minimization considering car travel time according to road characteristics, which can route the optimal shortest road paths between the center places and all rear villages, based on GIS coverages of road-village network for connecting between center places and rural villages as input data of the model. In order to verify the model algorithm, a homogeneous hexagonal network, assuming distribution of villages with same population density and equal distance between neighborhood villages on a level plane area, was tested to simulate the optimal paths between the selected center nodes and the other rear nodes, so that the test showed reasonable shortest paths and road intensity defined in this study. The model was also applied to the actual rural area, Ucheon-myun, which is located on Hoengsung-gun, Kangwon-do, with 72 rural villages, a center village (Uhang, 1st center place) in the area, a county conte. (Hoengsung-eup, 2nd center place), and a city (Wonju, 3rd center place), as upper settlement system. The three kinds of conte. place, Uhang, Hoengsung-eup, and Wonju, were considered as center places of three scenarios to simulate the optimal shortest paths between the centers and rural villages, respectively. The simulation results on the road-village network with road information about pavement and width of road show that several spans having high intensity of road are more important that the others, while some road spans have low intensity of road.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.665-668
• /
• 2020

When a node in automotive CAN bus is hacked, such node should be blocked to prevent severe danger in the car. In order to do that, such node should be uniquely identified. However, there is no way to identify individual nodes in a CAN bus. In this paper, a physical layer security method is proposed where individual nodes are identified by assigning unique ID to the nodes during booting process. The proposed method was implemented in a CAN controller using Verilog HDL, and it is verified that the node ID auto-setting and internal attack defense are successfully performed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.59-68
• /
• 2022

We propose the vehicle maintenance support system to alarm consumable replacement reminders to the vehicle owner. Since the delayed replacement of the consumables makes the condition of the vehicle worse, it is crucial to replace consumables in a recommended period. The vehicle maintenance support system alarms the replacement time, which is set by the vehicle owner, based on the mileage of the installed vehicle. It integrates speed information acquired from the Controller Area Network interface for communication between Electronic Control Unit and instrument panel, exposed at the On Board Diagnostics-II port, to calculate the vehicle mileage. By this, there is no additional wiring required for the system. We verify the system has only 0.28% error by comparing the mileage on the system with the instrument cluster on the vehicle. It automatically enters low-power mode consuming 15mW, which is a negligible amount for the typical conditions of the car, to prevent the vehicle battery from discharging when the ignition is off.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.353-359
• /
• 2020

In this study, the controller structure and control algorithm of medical robot bed developed for pressure ulcer prevention and healing are described. The existing pressure ulcer prevention mattress is operated manually and the remaining maximum body pressure exceeds the pressure of ulcer generation, so there is always room for pressure ulcers. However, the system developed in this study does not generate the pressure ulcers because the body pressure drops to zero when the keyboard of the bed descends using the active electric driving keyboard. In addition, even if the bed is raised and the pressure above the critical body ulcer pressure is abnormal, the device and the control algorithm are designed so that the lasting time is within the pressure ulcer generation critical time and the pressure ulcer itself is not generated. The bed key board motor is a motor designed with the BLDC servos suitable for medical use and these can communicate each other easily through CAN(Car Area Network). The system is new medical robot bed that is effective in preventing pressure ulcers and will be distributed to many patients suffering from pressure ulcers.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.10
• /
• pp.86-93
• /
• 2004

This paper presents the remote measurement of the ECU signals adopted with KWP 2000 protocol using the wireless communication technique of bluetooth. The bluetooth technology will be the most promising network paradigm which can open the new area in the information technology. Especially, bluetooth module is able to link all the electrical products and personal computers to cellular phone or PDA. This research has a try to design a wireless measurement model of ECU signal based on the car telemery system using bluetooth device. In order to measure the ECU signals, we designed the interface circuits which is able to communicate between the ECU system and the terminal circuits according to the ISO, SAE regulation of communication protocol standard. A microprocessor S3c341 OX is used for the system control and communication of ECU signals. The embedded system software is programmed to measure the ECU signals using the ARM compiler and ANCI C based on Micro/OS-II kernel to communicate between two bluetooth modules using bluetooth stack. The remote measurement of ECU signals using the bluetooth was designed and implemented to evaluate the performance of wireless network to the transmit measurement data. The possibility for the remote measurement of the self diagnosis signals of ECU adopted with KWP2000 protocol verified through the developed systems and algorithms in embedded system.

• Journal of information and communication convergence engineering
• /
• v.8 no.3
• /
• pp.289-294
• /
• 2010

In the vehicle communication system, transferred information is needed to be detected as possible as fast in order to inform car status located in front and rear side. Through the moving vehicle information, we can avoid the crash caused by sudden break of front one or acquire to real time traffic data to check the detour road. To be connecting the wireless communication between the vehicles, fast timing synchronization can be a key factor. Finding out the sync point fast is able to have more marginal time to compensate the distorted signals caused by channel variance. Thus, we introduce the combination method which helps find out the start of frame quickly. It is executed by auto-correlation and cross-correlation simultaneously using only short preambles. With taking the absolute value at the implemented synch block output, the proposed method shows much better system performance to us.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.151-156
• /
• 2006

Accurate vessel traffic observation is indispensable to carry out vessel traffic management, design of vessel traffic route, planning of port construction, etc. In order to observe the vessel traffic accurately without many efforts such as the use of a ship or car equipped with special radar observation system and the preparation of observation staff, the authors have been developing completely automated remote radar/AIS network system covering the main traffic area in Tokyo Bay. The composite radar image observed at Yokosuka and Kawasaki radar stations with AIS information can be seen on web site of Internet. In addition to the development of radar/AIS observation system, the software to analyze observed vessel traffic flow has been developed. This software has various functions such as automatic tracking of ship's positions, automatic estimation of ship's size, automatic integration of radar image and AIS data, animation of ships' movements, extraction of dangerous ship encounters, etc. The configuration and functions of the developed remote radar/AIS network system are shown first in this paper. Then various functions of the software to analyze vessel traffic are introduced, and some analyzed results on the vessel traffic in Tokyo Bay are described demonstrating the effectiveness of the developed system.