• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.47-79
• /
• 1995

Since the early age of computer graphics, facial animation has been applied to various fields, and nowadays it has found several novel applications such as virtual reality(for representing virtual agents), teleconference, and man-machine interface.When we want to apply facial animation to the system with multiple participants connected via network, it is hard to animate facial expression as we desire in real-time because of the size of information to maintain an efficient communication.This paper's major contribution is to adapt 'Level-of-Detail'to the facial animation in order to solve the above problem.Level-of-Detail has been studied in the field of computer graphics to reperesent the appearance of complicated objects in efficient and adaptive way, but until now no attempt has mode in the field of facial animation. In this paper, we present a systematic scheme which enables this kind of adaptive control using Level-of-Detail.The implemented system can generate speech synchronized facial expressions with various types of user input such as text, voice, GUI, head motion, etc.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.539-554
• /
• 2018

Effective interaction between user and device is considered an important ability of IoT devices. For some applications, it is necessary to recognize human facial expressions in real time and make accurate judgments in order to respond to situations correctly. Therefore, many researches on facial image analysis have been preceded in order to construct a more accurate and faster recognition system. In this study, we constructed an automatic recognition system for facial expressions through two steps - a facial recognition step and a classification step. We compared various models with different sets of data with pixel information, landmark coordinates, Euclidean distances among landmark points, and arctangent angles. We found a fast and efficient prediction model with only 30 principal components of face landmark information. We applied several prediction models, that included linear discriminant analysis (LDA), random forests, support vector machine (SVM), and bagging; consequently, an SVM model gives the best result. The LDA model gives the second best prediction accuracy but it can fit and predict data faster than SVM and other methods. Finally, we compared our method to Microsoft Azure Emotion API and Convolution Neural Network (CNN). Our method gives a very competitive result.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1405-1408
• /
• 2005

An embedded system has been applied to many fields including households and industrial sites. In the past, user interface products with simple functions were commercialized .but now user demands are increasing and the system has more various applicable fields due to a high penetration rate of the Internet. Therefore, the demand for embedded system is tend to rise In this paper, we Implementation of an embedded system for image tracking. This system is used a fixed IP for the reliable server operation on TCP/IP networks. A real time broadcasting of video image on the internet was developed by using an USB camera on the embedded Linux system. The digital camera is connected at the USB host port of the embedded board. all input images from the video camera is continuously stored as a compressed JPEG file in a directory at the Linux web-server. And each frame image data from web camera is compared for measurement of displacement Vector. That used Block matching algorithm and edge detection algorithm for past speed. And the displacement vector is used at pan/tilt motor control through RS232 serial cable. The embedded board utilized the S3C2410 MPU Which used the ARM 920T core form Samsung. The operating system was ported to embedded Linux kernel and mounted of root file system. And the stored images are sent to the client PC through the web browser. It used the network function of Linux and it developed a program with protocol of the TCP/IP.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.52-62
• /
• 1999

This paper presents a system which recognizes dynamic hand gestures on-line for controlling motion of numan avatar in virtual environment(VF). A dynamic hand gesture is a method of communication between a computer and a human being who uses gestures, especially both hands and fingers. A human avatar consists of 32 degree of freedom(DOF) for natural motion in VE and navigates by 8 pre-defined dynamic hand gestures. Inverse kinematics and dynamic kinematics are applied for real-time motion control of human avatar. In this paper, we apply a fuzzy min-max neural network and feature analysis method using fuzzy logic for on-line dynamic hand gesture recognition.

• 전자공학회논문지 IE
• /
• v.48 no.4
• /
• pp.61-68
• /
• 2011

As business management has a high level of dependence on Informational Technology (IT), protecting assets of a company from disaster is one of the most important thing that IT operating managers should consider. Because data or information is a major source of operation of the company, data security is the first priority as an aspect of continuity of business management. Therefore, this paper will realize disaster recovery system, which is suspended because of disaster, based on cloud computing system. Realized High Available Replicate System applied a method of multi thread target database to improve Replicate performance, and real time synchronize technology can improve efficiency of network. From Active to Active operation, it maximizes use of backup system, and it has a effect to disperse load of source database system. Also, High Available Replicate System realized consistency verification mechanism and monitoring technique. For Performance evaluation, High Available Replicate System used multi thread method, which shows more than threefold of replicate performance than single thread method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.208-214
• /
• 2014

Vehicle dynamic states used in various advanced driving safety systems are influenced by road geometry. Among the road geometry information, the vehicle pitch angle influenced by road slope and acceleration-deceleration is essential parameter used in pose estimation including the navigation system, advanced adaptive cruise control and others on sag road. Although the road slope data is essential parameter, the method measuring the parameter is not commercialized. The digital map including the road geometry data and high-precision DGPS system such as DGPS(Differential Global Positioning System) based RTK(Real-Time Kinematics) are used unusually. In this paper, low-cost cascade extended Kalman filter(CEKF) based road slope estimation method is proposed. It use cascade two EKFs. The EKFs use several measured vehicle states such as yaw rate, longitudinal acceleration, lateral acceleration and wheel speed of the rear tires and 3 D.O.F(Degree Of Freedom) vehicle dynamics model. The performance of proposed estimation algorithm is evaluated by simulation based on Carsim dynamics tool and T-car based experiment.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2005.05a
• /
• pp.215-220
• /
• 2005

In order to apply to land mine detection effectively, GPR using an optical electric field sensor as a receiver has been developed. The optical electric field sensor is very small and uses optical fiber instead of metallic coaxial cable. With the combination of these advantages and the bistatic radar system, it can be possible for an operator to measure quite flexible and safely. The sensor has been tested in stepped frequency radar system with frequency which consists of a vector network analyzer, a fixed double ridged horn antenna as transmitter. For considering effectiveness in real field, we applied impulse radar system, which consist of a digital oscilloscope and a impulse generator to produce the impulse. Detection of a PMN2 mine model was carried out by the impulse radar system at a sand pit. The PMN2 were detected clearly with sufficiently high resolution, the target contrast was almost the same while the scanning time decreased down to 1/100.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.5
• /
• pp.11-20
• /
• 2019

With the development of deep learning technology, research is being actively carried out on user-friendly interfaces that are suitable for use in virtual reality or augmented reality applications. To support the interface using the user's hands, this paper proposes a deep learning-based fingertip detection method to enable the tracking of fingertip coordinates to select virtual objects, or to write or draw in the air. After cutting the approximate part of the corresponding fingertip object from the input image with the Grad-CAM, and perform the convolution neural network with Atrous Convolution for the cut image to detect fingertip location. This method is simpler and easier to implement than existing object detection algorithms without requiring a pre-processing for annotating objects. To verify this method we implemented an air writing application and showed that the recognition rate of 81% and the speed of 76 ms were able to write smoothly without delay in the air, making it possible to utilize the application in real time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.6
• /
• pp.235-243
• /
• 2014

In this paper, we propose an efficient control system for intelligent LED indoor lighting. The proposed an efficient control system for intelligent LED indoor lighting were included to elements such as daylight intensity measured through the PIR sensor and illuminance sensor at lighting style by the schedule defined and the occupancy detection. And it was controlled lighting through to the wireless sensor network, and was designed for the energy savings. Also, the lighting control of indoor lighting based on occupancy detection detect fine movements using a PIR sensor. And an unnecessary lighting intensity control of the window-side and the inside were controlled according to daylight level measurement result using the light sensor. In daylight inflow many case, the window-side lighting was to automatically darker, and in daylight inflow less case, was designed to be automatically bright. The efficiency validate results of an efficient control system for intelligent LED indoor lighting, the brightness of the indoor light were to maximize the energy saving by controlling in real time when entering as indoor a little that external lighting or daylight.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.154-162
• /
• 2003

In this paper, Associative Memory with Cellular Neural Networks classifies and recognizes image patterns as an operator applied to image process. CNN processes nonlinear data in real-time like neural networks, and made by cell which communicates with each other directly through its neighbor cells as the Cellular Automata does. It is applied to the optimization problem, associative memory, pattern recognition, and computer vision. Image processing with CNN is appropriate to 2-D images, because each cell which corresponds to each pixel in the image is simultaneously processed in parallel. This paper shows the method for designing the structure of associative memory based on CNN and getting output image by choosing the most appropriate weight pattern among the whole learned weight pattern memories. Each template represents weight values between cells and updates them by learning. Hebbian rule is used for learning template weights and LMS algorithm is used for classification.