• Smart Media Journal
• /
• v.9 no.4
• /
• pp.134-143
• /
• 2020

Vehicle License Plate Recognition is one of the approaches for transportation and traffic safety networks, such as traffic control, speed limit enforcement and runaway vehicle tracking. Although it has been studied for decades, it is attracting more and more attention due to the recent development of deep learning and improved performance. Also, it is largely divided into license plate detection and recognition. In this study, experiments were conducted to improve license plate detection performance by utilizing various object detection methods and WPOD-Net(Warped Planar Object Detection Network) model. The accuracy was improved by selecting the method of detecting the vehicle(s) and then detecting the license plate(s) instead of the conventional method of detecting the license plate using the object detection model. In particular, the final performance was improved through the process of removing noise existing in the image by using the Fast-SRGAN model, one of the Super-Resolution methods. As a result, this experiment showed the performance has improved an average of 4.34% from 92.38% to 96.72% compared to previous studies.

• Journal of Satellite, Information and Communications
• /
• v.7 no.3
• /
• pp.99-104
• /
• 2012

The United States will proceed with the effort to modernize the GPS system, and one of its main content is to provide L5 signal. L5 will be transmitted in a radio band reserved exclusively for aviation safety services. And, L5, in combination with L1, will improve the position accuracy via ionospheric correction and robustness via signal redundancy. However, The acquisition processing time of L5 takes longer than that of L1 as the code length of L5 is 10 times longer than that of L1. To reduce this acquisition processing time, a higher number of correlators in the aquisition module should be used. However, there is a problem that this causes increase in the complexity of the correlator configuration and the computation power. So, in this paper, we propose L5 signal tracking scheme using tracking results in the GPS L1/L5 receiver. The proposed scheme could reduce the hardware complexity as the GPS L5 signal acquisition module is not needed, and provide fast and stable tracking of L5 signal by aiding L1 tracking results such as PRN, the code phase synchronization, and the Doppler frequency. The feasibility of the proposed scheme is demonstrated through simulation results.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.34-39
• /
• 2002

Road information is very important for topographic mapping, transportation application, urban planning and other related application fields. Therefore, automatic detection of road networks from spatial imagery, such as aerial photos and satellite imagery can play a central role in road information acquisition. In this paper, we use least squares correlation matching alone for road center tracking and show that it works. We assumed that (bright) road centerlines would be visible in the image. We further assumed that within a same road segment, there would be only small differences in brightness values. This algorithm works by defining a template around a user-given input point, which shall lie on a road centerline, and then by matching the template against the image along the orientation of the road under consideration. Once matching succeeds, new match proceeds by shifting a matched target window further along road orientation at the target window. By repeating the process above, we obtain a series of points, which lie on a road centerline successively. A 1m resolution IKONOS images over Seoul and Daejeon were used for tests. The results showed that this algorithm could extract road centerlines in any orientation and help in fast and exact he ad-up digitization/vectorization of cartographic images.

• Journal of Korean Society of Water and Wastewater
• /
• v.24 no.6
• /
• pp.713-722
• /
• 2010

This paper has assessed the flow patterns and settling efficiency in the sedimentation basin using the particle tracking method of the CFD code and has reached the following conclusions: In the original design where no baffle is installed in the sedimentation basin, a large recirculating area where the flow stagnates is created in the right side of the sedimentation basin, with most of the particles moving to the left side of the sedimentation basin following the flow. This biased flow structure in the sedimentation basin reduces the residence time of particles and thereby undermines settling efficiency. The biased flow toward the left side of the sedimentation basin is alleviated by installing a baffle in the sedimentation basin, promptly reducing the fast flow of over 0.7 m/s in the inlet of the sedimentation basin to the rate below 0.2 m/s. In this paper's simulation conditions, if a one-sided baffle is to be installed in the sedimentation basin, placing it 15 meters away from the basin's inlet leads to the best settling efficiency; it has also been analyzed that installing a two-sided baffle-rather than a one-sided one-is a better option in terms of settling efficiency. The highest settling efficiency of 96.2% is achieved when the underwater length of the two-sided baffle is set at 8 meters.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.3
• /
• pp.195-200
• /
• 2012

To steer a camera is done based on system parameters of the vision system. However, the system parameters when they are used might be different from those when they were measured. As one method to compensate for this problem, this research proposes a gaze-steering method based on LMI(Linear Matrix Inequality) that is robust to variations in the system parameters of the vision system. Simulation results show that the proposed method produces less gaze-tracking error than a contemporary linear method and more stable gaze-tracking error than a contemporary nonlinear method. Moreover, the proposed method is fast enough for realtime processing.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.865-870
• /
• 2004

Development of new information and traffic technology causes fast-growing in the field of information-based system. At recent, development of LBS(Location Based Service) makes a remarkable growth of industry as GPS(Global Positioning System) becomes wide-spread and location information becomes more important. However, there is a problem like infringement of privacy when location information is used improperly［1］. In this paper, LBS platform is proposed in order to prevent infringement of privacy. To implement, we classify user path as pattern in a zone of user life. Thereupon, location information is provided according to user' specific situation.

• Journal of Power Electronics
• /
• v.17 no.1
• /
• pp.172-180
• /
• 2017

The repetitive control (RC) strategy is widely used in AC power systems because of its high performance in tracking period signal and suppressing steady-state error. However, the dynamic response of RC is determined by the fundamental period delay $T_0$ existing in the internal model. In the current study, a ($nk{\pm}i$)-order harmonic RC structure is proposed to improve dynamic performance. The proposed structure has less data memory and can improve the tracking speed by n/2 times. $T_0$ proves the effectiveness of the ($nk{\pm}i$)-order RC strategy. The simulation and experiments of ($6k{\pm}1$)-order and ($4k{\pm}1$)-order RC strategy used in the voltage source inverter is conducted in this study to control the harmonic current source, which shows the validity and advantages of the proposed structure.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.10
• /
• pp.587-594
• /
• 2005

An adaptive observer for rotor resistance is designed to estimate rotor flux for the a-b model of an induction motor assuming that rotor speed and stator currents are measurable. A singularly perturbed model of the motor is used to design an Adaptive sliding mode observer which drives the estimated stator currents to their true values in the fast time scale. The adaptive observer on the sliding surface is based on the equivalent switching vector and both the estimated fluxes and the estimated rotor resistance converge to their true values. A speed controller considering the effects of parameter variations and external disturbance is proposed in this paper. First, induction motor dynamic model at nominal case is estimated. based on the estimated model, speed controller is designed to match the prescribed speed tracking specifications. Then a dead-time compensator and a robust controller are designed to reduce the effects of parameter variations and external disturbances. the desired speed tracking control performance can be preserved under wide operating range, and good speed load regulating performance. Some simulated results are provided to demonstrate the effectiveness of the Proposed controller.

• Journal of Electrical Engineering and Technology
• /
• v.5 no.4
• /
• pp.606-613
• /
• 2010

This paper proposes a novel current-based maximum power point tracking (CMPPT) method for a single-phase photovoltaic power conditioning system (PV PCS) by using a modified incremental conductance method. The CMPPT method simplifies the entire control structure of the power conditioning system and uses an inherent current source characteristic of solar cell arrays. Therefore, it exhibits robust and fast response under a rapidly changing environmental condition. Digital phase locked loop technique using an all-pass filter is also introduced to detect the phase of grid voltage, as well as the peak voltage. Controllers of dc/dc boost converter, dc-link voltage, and dc/ac inverter are designed for coordinated operation. Furthermore, a current control using a pseudo synchronous d-q transformation is employed for grid current control with unity power factor. A 3 kW prototype PV PCS is built, and its experimental results are given to verify the effectiveness of the proposed control schemes.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.4
• /
• pp.263-269
• /
• 2012

The ability to characterize feature objects from radar readings is often limited by simply looking at their still frame reflectivity, differential reflectivity and differential phase data. In many cases, time-series study of these objects' reflectivity profile is required to properly characterize features objects of interest. This paper introduces a novel technique to automatically track multiple 3D radar structures in C,S-band in real-time using Doppler radar and profile their characteristic reflectivity distribution in time series. The extraction of reflectivity profile from different radar cluster structures is done in three stages: 1. static frame (zone-linkage) clustering, 2. dynamic frame (evolution-linkage) clustering and 3. characterization of clusters through time series profile of reflectivity distribution. The two clustering schemes proposed here are applied on composite multi-layers CAPPI (Constant Altitude Plan Position Indicator) radar data which covers altitude range of 0.25 to 10 km and an area spanning over hundreds of thousands $km^2$. Discrete numerical simulations show the validity of the proposed technique and that fast and accurate profiling of time series reflectivity distribution for deformable 3D radar structures is achievable.