• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1337-1346
• /
• 2005

In this paper, we describe an algorithm which can automatically recognize human gesture for Human-Robot interaction. In early works, many systems for recognizing human gestures work under many restricted conditions. To eliminate these restrictions, we have proposed the method that can represent 3D and 2D gesture information simultaneously, APM. This method is less sensitive to noise or appearance characteristic. First, the feature vectors are extracted using APM. The next step is constructing a gesture space by analyzing the statistical information of training images with PCA. And then, input images are compared to the model and individually symbolized to one portion of the model space. In the last step, the symbolized images are recognized with HMM as one of model gestures. The experimental results indicate that the proposed algorithm is efficient on gesture recognition, and it is very convenient to apply to humanoid robot or intelligent interface systems.

• Journal of Korea Multimedia Society
• /
• v.13 no.9
• /
• pp.1373-1381
• /
• 2010

Current flight maneuver diagram used by pilots is based on 2D spatial presentation, so it has limitation on display 3D flight information and hard to understand it instinctively. Flight animation authoring tools for this diagram are complex to use and lack useful features like non-linear editing of flight path and real-time interactivity on multiple aircrafts. This research focuses on 3D flight path generation method in the animation system for flight maneuver education. This research combines initial sketch input on 2D diagram with the thrust of an aircraft to generate 3D linear spline as close as to real flight. Using suggested linear spline creation method, the flight path can be visualized, edited, and animated in real-time at the flight maneuver briefing and debriefing.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.986-993
• /
• 2011

In this paper we consider the problem of the existing TCAS-II systems that fail to be satisfactory solution to mid-air collisions (MACs) and near mid-air collisions (NMACs or near misses). This is attributed to the fact that the earlier studies on the collision avoidance mainly have focused on determination logic of avoidance direction and vertical speed, reversal of the avoidance direction, multiple aircraft geometry, and availability in certain air spaces. But, the influence of sensor measurement errors on the performance of collision avoidance was not properly taken into account. Here we propose a new TCAS algorithm by using Kalman filter instead of '${\alpha}-{\beta}$' tracker to improve the avoidance performance under the influence of barometric sensor errors due to air-temperature, pressure leaks, static source error correction, etc.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.8
• /
• pp.455-476
• /
• 2006

An avatar script language consists of commands set which is used to control avatar behaviors in cyberspace. The script language should be abstract from complex low-level concepts, so that a user can write down a scenario script easily without concerning about physical motion parameters. Also, the script should be defined in a standard format and structure to allow reusing in various implementation tools. In this paper, a layered script language is proposed for avatar behavior representation and control, which consists of task-level behavior, high-level motion and primitive motion script language. The script language of each layer represents behavior elements for a scenario scripting interface, an avatar motion sequence, and geometric information of implementation environment, respectively. Therefore, a user can create a scenario script by abstract behavior interface and a script can be applied to various implementations by the proposed translating process. A presentation domain is chosen for applying the proposed script language and the implementation result shows that the script is flexibly applied in several applications.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.4
• /
• pp.207-220
• /
• 2007

Recording to development of info-communication, recent educational paradigm asks not for a passive transmitter but an active constructor who can solve the various complicated problems in real situations. Such a change asks for the educational setting which includes sharing ideas and information rather than possessing them by themselves. Learning through presentation has many problems which are few chances of presentation as well as reusing of presentation data. etc. This study suggested the strategy which are promoting interactions through presentation class and using practically. For this, role of the presentation data provider and learner was suggested, also strategies to implement of the presentation learning support system step by step. Through the strategy of this paper could maintain the active communicating relationship between the learners. Without the limitation of the time and space, the real time communication is made while looking at the presentation data of the other party, the teaming effect by the presentation teaming strategy is expected to be high.

• Journal of Korea Multimedia Society
• /
• v.4 no.5
• /
• pp.396-405
• /
• 2001

Usually it is difficult to extract facial regions in a complex image by using only a predetermined skin color. Expecially, it is more difficult to separate them from background regions that contains the skin color. This paper proposes a face detection method by using gradual range expansion of an initial skin color. By analyzing the skin color distribution several images that are collected in the Web, the range of dense distribution is selected as the range of the initial skin color. In each expanding step, expanded regions in the image are tested whether they can be actual facial regions by using the information of the shape of general face and the location of face organs. The shape of general face is modeled as an ellipse and the aspect ratio of its bounding box is used to define the shape constraint for faces. Only the eyes and lips are used as the face organs, which can be easily detected by extracting horizontal edges in the expanded regions. through several experiments, it is confirmed that the proposed method can detect exactly not only faces having partly distorted regions by highlight but also faces neighboring similar color regions.

• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.542-549
• /
• 2000

This Paper presents the development of multiresolution model for the analysis and visualization of two-dimensional flows over curvilinear grids. Multiresolution analysis provides a useful and efficient tool to represent shape and to analyze features at multiple level of detail. Applying multiresolution analysis to vector field visualization is very useful and powerful as the vector field's data sets are usually huge and complex. Using approximation at lower resolution, brief outline of topology can be extracted in short periods of time. Local reconstruction allows the user to zoom in or out, only by reconstructing the portion of interest. This new model is based upon nested spaces of piecewise defined function over nested curvilinear grid domains. The nested domains are selected so as to maintain the original geometry of the inner boundary. This paper presents the refinement and decomposition equations for Haar wavelet over these domains and shows some examples.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1016-1022
• /
• 2010

Far-talking recognition and distributed speech recognition networking techniques are essential to control various and complex home services conveniently with voices. It is possible to control devices everywhere at home by using only voices. In this paper, we have developed the server-client DSP module for distributed speech recognition network system and proposed a new decision rule to decide intelligently whether to accept the recognition results or not by the transferred confidence rate. Simulation results show that the proposed decision rule delivers better performances than the conventional decision by majority rule or decision by first-arrival. Also, we have proposed the new interrupt-polling technique to remedy the defect of existing delay technique which always has to wait several clients' results for a few seconds. The proposed technique queries all client's status after first-arrival and decides whether to wait or not. It can remove unnecessary delay-time without any performance degradation.

• Journal of Navigation and Port Research
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2011

The accuracy of forecasting is remarkably important to reduce total cost or to increase customer services, so it has been studied by many researchers. In this paper, the artificial neural network (ANN), one of the most popular nonlinear forecasting methods, is compared with autoregressive integrated moving average(ARIMA) model through performing a prediction of container traffic. It uses a hybrid methodology that combines both the linear ARIAM and the nonlinear ANN model to improve forecasting performance. Also, it compares the methodology with other models in performance for prediction. In designing network structure, this work specially applies the genetic algorithm which is known as the effectively optimal algorithm in the huge and complex sample space. It includes the time delayed neural network (TDNN) as well as multi-layer perceptron (MLP) which is the most popular neural network model. Experimental results indicate that both ANN and Hybrid models outperform ARIMA model.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.186-200
• /
• 2010

In order to render global illumination realistically, we need to accurately compute the direct and indirect illumination that represents the light information incoming through complex light paths. In this process, the indirect illumination at given point is greatly affected by surrounding geometries. Harmonic mean distance is a mathematical tool which is often used as a metric indicating the distance from a surface point to its visible objects in 3D space, and plays a key role in such advanced global illumination algorithms as irradiance/radiance caching and ambient occlusion. In this paper, we analyze the accuracy of harmonic mean distance estimated against various environments in the final gathering and photon mapping methods. Based on the experimental results, we discuss our experiences and future directions that may help develop an effective harmonic mean distance computation method in the future.