• Journal of KIISE
• /
• v.41 no.11
• /
• pp.927-934
• /
• 2014

In this paper, we propose an effective method for recognizing daily human activities from a stream of three dimensional body poses, which can be obtained by using Kinect-like RGB-D sensors. The body pose data provided by Kinect SDK or OpenNI may suffer from both the view variance problem and the scale variance problem, since they are represented in the 3D Cartesian coordinate system, the origin of which is located on the center of Kinect. In order to resolve the problem and get the view-invariant and scale-invariant features, we transform the pose data into the spherical coordinate system of which the origin is placed on the center of the subject's hip, and then perform on them the scale normalization using the length of the subject's arm. In order to represent effectively complex internal structures of high-level daily activities, we utilize Hidden state Conditional Random Field (HCRF), which is one of probabilistic graphical models. Through various experiments using two different datasets, KAD-70 and CAD-60, we showed the high performance of our method and the implementation system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2048-2054
• /
• 2013

Due to the development of the digital technology, the territories of broadcasting and telecommunications are being converged and there have been the efforts to eliminate the spatial and/or temporal restrictions in utilizing the services (usually implemented as applications) via various devices (e.g. smart-phone, smart TV, pad-computer, etc). In the circumstances, Web is coming to the fore as a common running platform of the services and the digital broadcasting receivers are pressed to run Web applications as well as Java applications, which are the standard of data service of the digital broadcasting. The paper introduces a platform for running HTML5-based Web applications, which is equipped with a Web kernel (an engine for running HTML5 Web applications), a Web desktop (the facilities (with an UI similar to Window OS) for managing Web applications), and SDK (a set of API's for Web application developers).

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.1
• /
• pp.13-19
• /
• 2008

This study considers the development of plug-in, which enables backup save using Maya SDK, API and MEL technologies. It also considers its realization in Maya program and the other various application programs. The various ways of backup save have been found by analyzing the difficulties of file management and storage when using many kinds of plug-in of Maya. An objective has been set as to increase the efficiency of the developer preventing the unintentional modification of the existing and overlapping file by using backup save plug-in. Based on a such objective, this study considers if a backup save is helpful to a graphic developer to use Maya program in more efficient way and if it improves the data maintenance. Currently, it can function as a backup save only within the Maya Program, but such plug-ins to be applied within various application programs are developed for giving more freedom to computer graphic designers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.12
• /
• pp.2312-2317
• /
• 2017

Museums are converging with digital technology to convey information to viewers in various ways. Augmented reality technology enhances virtual objects seamlessly in the real world, and provides a high sense of immersion and realism because it can use various senses of users in combination with information providing role of exhibits. However, the location-based augmented reality may cause the inaccurate registration of the virtual object with the real world due to the error of the GPS information, and the vision-based augmented reality can be enhanced at the position where the marker is placed. To solve this problem, we implemented the exhibition contents that interact with the real world by using the developed project tango. The exhibited contents were based on Lenovo Phab 2 Pro and Project Tango SDK in Unity 3D. Visitors were able to improve immersion and realism in exhibition contents, and it would be able to combine with various exhibition fields such as shopping malls as well as museums.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.72-77
• /
• 2017

This paper focuses on the development of a supporting S/W tool for the automated design of an automotive press trim die. To define the die design process based on automation, we analyze the press die design process of the current industry and group repetitive works in the 3D modeling process. The proposed system consists of two modules, namely the template models of the trim steel parts and UI function for their auto-positioning. Four kinds of template models are developed to adapt to various situations and the rules of the interaction formula which are used for checking and correcting the directions of the datum point, datum curve, datum plane are implemented to eliminate errors. The system was developed using CATIA Knowledgeware, CAA(CATIA SDK) and Visual C++, in order for it to function as a plug-in module of CATIA V5, which is one of the major 3D CAD systems in the manufacturing industry. The developed system was tested by applying it to various panels of current automobiles and the results showed that it reduces the time-cost by 74% compared to the traditional method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.69-75
• /
• 2014

Existing People Counting System using a single overhead mounted camera has limitation in object recognition and counting in various environments. Those limitations are attributable to overlapping, occlusion and external factors, such as over-sized belongings and dramatic light change. Thus, this paper proposes the new concept of People Counting System by Facial Age Group using two depth cameras, at overhead and frontal viewpoints, in order to improve object recognition accuracy and robust people counting to external factors. The proposed system is counting the pedestrians by five process such as overhead image processing, frontal image processing, identical object recognition, facial age group classification and in-coming/out-going counting. The proposed system developed by C++, OpenCV and Kinect SDK, and it target group of 40 people(10 people by each age group) was setup for People Counting and Facial Age Group classification performance evaluation. The experimental results indicated approximately 98% accuracy in People Counting and 74.23% accuracy in the Facial Age Group classification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.797-801
• /
• 2008

This paper describes technical method about remote control and monitoring of local system by use personal mobile device in anytime and anywhere. Therefore, the user don't need to stay in operation room of local system. The PC server environment for the mobile connection are constructed with Apache web server, PHP and MySQL ODBC. The mobile internet homepage for the remote mobile connection is designed by Anybuilder software and mobile simulator, Openwave SDK 6.2 is used for the development. The mobile internet program can be applicate to all of domestic communication companies LGT, SKT and KTF. We use KTF mobile contains WAP browser for the test. We used NI Labview software to control and monitoring of local system. The local system, which will be controlled remotely have constructed with analog/digital signal acquisition device, signal control board and their software. By experiments, we confirmed remote control by mobile device are possible.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.8C
• /
• pp.788-799
• /
• 2007

This paper presents a watermarking method for copyright protection and illegal copy prevention of mobile 3D contents. The proposed method embeds copyright information and user's phone number into spatial domain and encryption domain of mobile animation data based on Buyer-Seller watermarking protocol. Furthermore, we insert user's operation key so that only authorized user can play 3D animation game in mobile device. We implemented the proposed method by using mobile animation tool, G3-SDK. From experimental results, we verified that the proposed method is capable of copyright protection and illegal copy prevention since the watermark can be well extracted against geometrical attacks, such as noise addition, data accuracy variableness and data up/down scaling.

• Journal of Korea Game Society
• /
• v.10 no.1
• /
• pp.135-146
• /
• 2010

The development of image technologies in such area as broadcasting and movies has recently increased our attention to 3D stereoscopic images. In addition, the development of stereoscopic image representation technologies in 3D contents becomes more active over time due to the representational limitations of 2D images. Without limitation to the above-mentioned area, stereoscopic image technologies have been developed and studied so that they can be widely accessed in diverse areas including medical services and education. Due to the refined production, however, required to represent a three dimensional effects and the fatigue caused by the perception of a three dimensional effects, the stereoscopic image technologies are not combined into real time systems such as games where environments change unforeseeably. In this study we design a technique to adjust the depth scaling that will enable efficient management of a three dimensional effects and to relieve fatigue through automatic view point interval adjustment in accordance with situations based on the geometrical structure of the DirectX SDK graphic pipeline. Through this, we would like to suggest a new alternative idea to activate the production of games combined with stereoscopic image technologies.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.5
• /
• pp.1153-1161
• /
• 1997

In this paper, we propose Teloemedicine system on CBM(Computer Based Multimedia) based collaborative multimedia which supports special medicine and collaborative medicine with DB, face-to-face dffedt.This system is an application developed by SDK (Software Development Kit) of DooRae(Distributed Objected Oriented Multimedia Application Crafting Environment for Collaborative)framework.And this system is devel-Oriented Multimedia Applecation Crafting Environment for Collaborative) framework, And this system is devel-oped on windows 95 and windows NT.The scenario of this system is limited within only hospital(LAN), but it is possibloe to support many applications development in various nerwork(MAN, PSYN, WAN)on DooRae.This system has a smoth interaction by video and audio, multiple session, multiple participation, application sharing, toolbox including ICON and whiteboard.Also this system supports realo or non-real type without con-straint of the and space.