• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.14-21
• /
• 2019

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

• Journal of Korea Multimedia Society
• /
• v.22 no.4
• /
• pp.432-442
• /
• 2019

Most current human action recognition methods based on deep learning methods. It is required, however, a very high computational cost. In this paper, we propose an action change detection method to reduce repetitive human action recognition tasks. In reality, simple actions are often repeated and it is time consuming process to apply high cost action recognition methods on repeated actions. The proposed method decides whether action has changed. The action recognition is executed only when it has detected action change. The action change detection process is as follows. First, extract the number of non-zero pixel from motion history image and generate one-dimensional time-series data. Second, detecting action change by comparison of difference between current time trend and local extremum of time-series data and threshold. Experiments on the proposed method achieved 89% balanced accuracy on action change data and 61% reduced action recognition repetition.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.52.2-52.2
• /
• 2019

Global map of solar surface magnetic field, such as the synoptic map or daily synchronic frame, does not tell us real-time information about the far side of the Sun. A deep-learning technique based on Conditional Generative Adversarial Network (cGAN) is used to generate farside magnetograms from EUVI $304{\AA}$ of STEREO spacecrafts by training SDO spacecraft's data pairs of HMI and AIA $304{\AA}$. Farside(or backside) data of daily synchronic frames are replaced by the Ai-generated magnetograms. The new type of data is used to calculate the Potential Field Source Surface (PFSS) model. We compare the results of the global field with observations as well as those of the conventional method. We will discuss advantage and disadvantage of the new method and future works.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.4
• /
• pp.19-26
• /
• 2019

In this study, we study the development and control of motion of 3D character animation and discuss the development direction of technology. Character animation has been developed as a data-based method and a physics-based method. The animation generation technique based on the keyframe method has been made possible by the development of the hardware technology, and the motion capture device has been used. Various techniques for effectively editing the motion data have appeared. At the same time, animation techniques based on physics have emerged, which realistically generate the motion of the character by physically optimized numerical computation. Recently, animation techniques using machine learning have shown new possibilities for creating characters that can be controlled by the user in real time and are expected to be developed in the future.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.243-248
• /
• 2021

Although many different types of covert channels have been suggested in the literature, there are little work in directly applying game theory to building up covert channel. This is because researchers have mainly focused on tailoring game theory for covert channel analysis, identification, and covert channel problem solving. Unlike typical adaptation of game theory to covert channel, we show that game theory can be utilized to establish a new type of covert channel in IoT devices. More specifically, we propose a covert channel that can be constructed by utilizing the Nash Equilibrium with sensor data collected from IoT devices. For covert channel construction, we set random seed to the value of sensor data and make payoff from random number created by running pseudo random number generator with the configured random seed. We generate I × J (I ≥ 2, J ≥ 2) matrix game with these generated payoffs and attempt to obtain the Nash Equilibrium. Covert channel construction method is distinctly determined in accordance with whether or not to acquire the Nash Equilibrium.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.4
• /
• pp.47-52
• /
• 2010

This paper describes a visualization technique that animates geometrical defect data that are extracted using a magnetic flux leakage (MFL) operating system on nondestructive evaluation (NDE). Since data are collected from different locations and often not regular, the data must be converted to the standard format that is used within the pipeline in visualization procedures. In order to navigate inside of the pipeline, 3D virtual objects are generated and are able to explore the pipeline continuously. The major objectives of this paper are to characterize, generate general shape of defects, and enable computer interaction in virtual environment. Pipeline navigation system (PNS) has introduced the framework for interactive visual applications based upon the principles of modeling 3D objects. PNS presents some preliminary efforts to enable the user to interact human and computer with each other.

• Journal of Information Technology Applications and Management
• /
• v.30 no.6
• /
• pp.143-155
• /
• 2023

Procedural generation methods based on physical-based materials generate data by algorithms rather than manual through combinations with artist-generated assets based on computer-generated randomness algorithms. For this reason, the procedural generation method is mainly used to produce textures of 3D models in the field of computer graphics because it is easy to obtain the desired quality with little data. This study is a study on physical-based materials and procedural generation methods based on them. Physical-based materials are divided into Metallic/Roughness workflows and Specific/Glossiness workflows. These two methods produce the same results, which are more accurate based on the law of conservation of energy. The procedural generation method allows a natural texture to be obtained very quickly by texturing through a combination of a computer-generated random algorithm and an artist-generated asset based on various maps.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.9
• /
• pp.751-756
• /
• 2012

In this paper, we propose a foreground extraction and depth map generation method using a time-of-flight (TOF) depth camera. Although, the TOF depth camera captures the scene's depth information in real-time, it has a built-in noise and distortion. Therefore, we perform several preprocessing steps such as image enhancement, segmentation, and 3D warping, and then use the TOF depth data to generate the depth-discontinuity regions. Then, we extract the foreground object and generate the depth map as of the color image. The experimental results show that the proposed method efficiently generates the depth map even for the object boundary and textureless regions.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.12
• /
• pp.541-554
• /
• 1986

This paper presents the results of driving performance analysis of permanent magnet synchronous motor using a microprocessor based control system. The system consists of three phase power transistor inverters, three phase controlled rectifier, three central processing units, and sensors. The three CPUs are, respectively, used to generate PWM control signals for the inverter generating three phase sine wave, to generate the gate control signals for firing the converter, and to supervise other two CPUs. The supervisor is used to compute PI control algtorithm to three phase reference sine wave for the inverter. It is also used to maintain a constant voltage frequency ratio for the converter operating as a constant torque controller. The inverter CPU retrieves precomputed PWM patterns from look up tables because of computation speed limitations found in almost available microprocessors. The converter CPU also retrieves precomputed gate control patterns from another look-up tables. For protecting the control ststem from any damage by extraordinary over currents, the supervisor receives the data from current sensor, CT, and break down the CB to isolate the circuits from source. A resolver has a good performance characteristics of overall speed range, especially on low speed range. Therefor the speed control accuracy is impoved. The microprocessor based PM synchronous motor control system, thus, has many advantages such as constant torque characteristics, improvement of wave, limitation on extraordinary over currents, improvement of speed control accuracy, and fast response speed control using multi-CPU and look-up tables.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.8
• /
• pp.621-627
• /
• 2014

In this paper, a possibility of controlling the motion of a floating wind turbine with the tuned liquid damper(TLD) is numerically investigated. First, motion of the scale model of a floating wind turbine without the TLD is predicted and its results are compared to the measured data. There are reasonably good agreements between two results, which confirms validity of the present numerical methods. Then, the effect of TLD is quantitatively assessed by comparing the prediction results for the floating wind turbine with and without the TLD. It is shown that the motion of the scale model derived by external forces can be reduced by using the TLD. On a basis of this result, a multi-layer TLD is proposed to generate larger reaction force of the TLD at the fixed target frequency. The motions of the scale model with the multi-layer TLDs are computed and compared with that of the single-layer TLD. It is shown that the multi-layer TLD generate stronger reaction force and thus more reduce the motion of the floating body than the single-layer TLD.