• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.19-26
• /
• 2022

With the recent development of intelligent transportation systems, car license plate recognition systems are being used in various fields. Such systems need to guarantee real-time performance to recognize the license plate of a driving car. Also, they should keep a high recognition rate even in problematic situations such as small license plates in low-resolution and unclear image due to distortion. In this paper, we propose a real-time car license plate recognition system that improved processing speed using object detection algorithm based on anchor-free method and text recognition algorithm based on Convolutional Neural Network(CNN). In addition, we used Spatial Transformer Network to increase the recognition rate on the low resolution or distorted images. We confirm that the proposed system is faster than previously existing car license plate recognition systems and maintains a high recognition rate in a variety of environment and quality images because the proposed system's recognition rate is 93.769% and the processing speed per image is about 0.006 seconds.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.5
• /
• pp.145-159
• /
• 2004

The conventional method for assessment of liquefaction potential proposed by Seed and Idriss has been widely used in most countries because of simplicity of tests. Even though various data such as stress, strain, stress path, and excess pore water pressure can be obtained from the dynamic test, especially, two simple experimental data such as the maximum deviatoric stress and the number of cycles at liquefaction have been used in the conventional assessment. In this study, a new detailed assessment for liquefaction potential to reflect both characteristics of real earthquake motion and dynamic soil resistance is proposed and verified. In the assessment, the safety factor of the liquefaction potential at a given depth of a site can be obtained by the ratio of a resistible cumulative plastic shear strain determined through the performance of the conventional cyclic test and a driving cumulative plastic shear strain calculated from the shear strain time history through the ground response analysis. The last point to cumulate the driving plastic shear strain to initiate soil liquefaction is important for this assessment. From the result of cyclic triaxial test using real earthquake motions, it was concluded that liquefaction under the impact-type earthquake loads would initiate as soon as a peak loading signal was reached. The driving cumulative plastic shear strain, therefore, can be determined by adding all plastic shear strains obtained from the ground response analysis up to the peak point. Through the verification of the proposed assessment, it can be concluded that the proposed assessment for liquefaction potential can be a progressive method to reflect both characteristics of the unique soil resistance and earthquake parameters such as peak earthquake signal, significant duration time, earthquake loading type, and magnitude.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.179-187
• /
• 2014

As an Accident data recorder (ADR) is a system to record a vehicle's status and dynamics information on the before and after of accident, Traffic accident investigation agencies and parts developers have a lot of interest to analyze an accident objectively and develop automotive safety devices by using real accident data, This study is to analyze an accident objectively and scientifically on the basis of traffic accident reconstruction with the use of output data of an event data recorder. This study is conducted double lane change test six times and slalom test one time as a field driving test and simulation. Based on the vehicle speed, the longitudinal and transverse acceleration, steering angle, driving path, and other kinds of information obtained from the field driving test, this study performed a simulation with PC-Crash program of reenacting and analyzing a traffic accident. The simulation was performed twice in the acceleration-steering angle input method and in the acceleration-driving path input method. By comparing the result of the field driving test with the results of the two simulations, we drew an analysis method with the optimal path reconstruction.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.7
• /
• pp.153-161
• /
• 2015

In the present study, as part of the technology development (Quality of Life Technology, QoLT) to improve the socio-economic status of people with disabilities as an extension of these studies, we propose the development of the smart wheelchair system and navigation technology for stable and safe driving in various environments. For the disabled and the elderly make driving easy and convenient with manual/autonomous driving condition, we firstly develop the user-oriented smart wheelchair system with optimized sensors for environment recognition, and then we propose a navigation framework of a hierarchical structure to ensure real-time response, as well as driving stability when traveling to various environmental changes, and to enable a more efficient operation. From the result of several independent experiments, we ensure efficiency and safety of smart wheelchair and its navigation system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3086-3103
• /
• 2017

Video images captured by vehicle cameras often contain blurry or dithering frames due to inadvertent motion from bumps in the road or by insufficient illumination during the morning or evening, which greatly reduces the perception of objects expression and recognition from the records. Therefore, a real-time electronic stabilization method to correct fuzzy video from driving recorders has been proposed. In the first stage of feature detection, a coarse-to-fine inspection policy and a scale nonlinear diffusion filter are proposed to provide more accurate keypoints. Second, a new antiblurry binary descriptor and a feature point selection strategy for unintentional estimation are proposed, which brought more discriminative power. In addition, a new evaluation criterion for affine region detectors is presented based on the percentage interval of repeatability. The experiments show that the proposed method exhibits improvement in detecting blurry corner points. Moreover, it improves the performance of the algorithm and guarantees high processing speed at the same time.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.1701-1703
• /
• 2006

Here we describe a novel driving scheme in the form of negative AC bias stress (NAC) to compensate shift in the threshold voltage for hydrogenated amorphous silicon (${\alpha}$-Si:H) thin film transistor (TFT) for AMOLED applications. This scheme preserves the threshold voltage shift of ${\alpha}$-Si:H TFT for infinitely long duration of time(>30,000 hours) and thereby overall performance, without using any additional TFTs for compensation. We briefly describe about the possible driving schemes in order to implement for real time AMOLED applications. We attribute most of the results based on concept of plugging holes and electrons across the interface of the gate insulator in a controlled manner.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.2
• /
• pp.211-217
• /
• 2014

This paper addresses an algorithm of path planning for autonomous driving of a ground vehicle in waypoint navigation. The proposed algorithm is flexible in utilization under a large GPS positioning error and generates collision-free multiple paths while pursuing minimum traveling time. An optimal path reduces inefficient steering by minimizing lateral changes in generated waypoints along a path. Simulation results compare the proposed algorithm with the A* algorithm by manipulation of the steering wheel and traveling time, and show that the proposed algorithm realizes real-time obstacle avoidance by quick processing of path generation, and minimum time traveling by producing paths with small lateral changes while overcoming the very irregular positioning error from the GPS.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.135-136
• /
• 2017

When driving at night time environment, the whole body of transports does not visible to us. Due to lack of light conditions, there are only two options, which is clearly visible their taillights and break lights. To improve the recognition correctness of vehicle detection, we present an approach to vehicle detection and tracking using finding contour of the object on binary image at night time. Bilateral filtering is used to make more clearly on threshold part. To remove unexpected small noises used morphological opening. In verification stage, paired tail lights are tracked during their existence in the ROI. The accuracy of the test results for vehicle detection is about 93%.

• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.587-590
• /
• 2005

In this paper, the PWM inverter-motor drive system including sensor is controlled through the network. The algorithm to compensate for the time delay of ac current and ac voltage sensors due to the network is proposed. The delay time of sensors is kept nearly constant, using the synchronous signal and timers. The error between the real and estimated ac signals can be reduced by using two slopes for estimating the value of at signals. The proposed algorithms are verified with the simulation studies and experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.12
• /
• pp.2665-2674
• /
• 2012

This paper propose the method to recognize the lanes and distance between cars in real-time which detects dangerous situations and helps safe driving in the actual road environment. First of all, it extracts the area of interest corresponding to roads and cars from the road image photographed by using the forward-looking camera. Through the hough transform for the area of interest, this study detects linear components and also selects the lane and conducts filtering by calculating probability. And through the shadow threshold analysis of the cars in front within the area of interest, it extracts the objects of cars in front and calculates the distance from cars in front. According to the result of applying the suggested technology to recognize the lane and distance between cars to the road situation for testing, it showed over 95% recognition rate; thus, it has been proved that it can respond to safe driving.