• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.429-431
• /
• 2021

Recently, as an alternative to replace face-to-face meetings, video conferencing systems between remote locations has increased. However, video conferencing systems have limitations in terms of mismatch of the eyes of remote users. Therefore, it is necessary to apply a technology that can increase the level of immersion in video conferences by matching the gaze information of participants between different remote locations. In this paper, we propose a novel technique to realize video conferencing with the same gaze by estimating the speaker's location based on a multi-microphone. Using our method, it can be applied to various fields such as robot interaction and virtual human interface as well as video conferencing between remote locations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.3876-3881
• /
• 2012

In typical master/slave teleoperation systems, a human operator generally manipulates the master to control the slave through the visual information like camera image. However, the operator may get into trouble due to the limited visual information depending on the camera positions and the delay on the visual information because of low communication bandwidth. To cope with this inherit problem in the camera-based teleoperation system, this paper presents a teleoperation system using a reconstructed graphic model instead of the camera image. The proposed teleoperation system consists of a robot control module, a master module using a force-reflective joystick, and a graphic user interface (GUI) module. The graphic user interface module provides the operator with a 3D model reconstructed using a small set of sensing data received from the remote site. The proposed teleoperation system is evaluated through a peg-in-hole assembly task.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.71-76
• /
• 2018

The technology convergence of television, communication, and computing devices enables the rich social and entertaining experience through Smart TV in personal living space. The powerful smart TV computing platform allows to provide various user interaction interfaces like IR remote control, web based control, body gesture based control, etc. The presently used smart TV interaction user control methods are not efficient and user-friendly to access different type of media content and services and strongly required advanced way to control and access to the smart TV with easy user interface. This paper propose the optical wireless communication (OWC) based remote controller design for Smart TV using smart device Flashlights. In this approach, the user smart device act as a remote controller with touch based interactive smart device application and transfer the user control interface data to smart TV trough Flashlight using visible light communication method. The smart TV built-in camera follows the optical camera communication (OCC) principle to decode data and control smart TV user access functions according. This proposed method is not harmful as radio frequency (RF) radiation does it on human health and very simple to use as well user does need to any gesture moves to control the smart TV.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.155-161
• /
• 2019

Electroencephalography (EEG), a representative method of identifying temporal and spatial changes in brain activity, is a voluntary electrical activity measurable in the human scalp. Various interface technologies have been provided to control EEG activity, and it is possible to operate a machine such as a wheelchair or a robot through brainwaves. The characteristics of EEG data are collected in various types of channels in real time, and a server system for analyzing them is required to have an independent and lightweight system for the platform. In these days, the Spring platform is used as a large business server as an independent, lightweight server system. In this paper, we propose an EEG analysis system using the Spring server system. Using the proposed system, the reliability of EEG control can be enhanced, and analysis and control interface expansion can be provided in various aspects such as game and medical areas.

• The Journal of Korea Robotics Society
• /
• v.3 no.2
• /
• pp.81-90
• /
• 2008

While increasing demand of the service for the disabled and the elderly people, assistive technologies have been developed rapidly. The natural signal of human such as voice or gesture has been applied to the system for assisting the disabled and the elderly people. As an example of such kind of human robot interface, the Soft Remote Control System has been developed by HWRS-ERC in $KAIST^[1]$. This system is a vision-based hand gesture recognition system for controlling home appliances such as television, lamp and curtain. One of the most important technologies of the system is the hand gesture recognition algorithm. The frequently occurred problems which lower the recognition rate of hand gesture are inter-person variation and intra-person variation. Intra-person variation can be handled by inducing fuzzy concept. In this paper, we propose multivariate fuzzy decision tree(MFDT) learning and classification algorithm for hand motion recognition. To recognize hand gesture of a new user, the most proper recognition model among several well trained models is selected using model selection algorithm and incrementally adapted to the user's hand gesture. For the general performance of MFDT as a classifier, we show classification rate using the benchmark data of the UCI repository. For the performance of hand gesture recognition, we tested using hand gesture data which is collected from 10 people for 15 days. The experimental results show that the classification and user adaptation performance of proposed algorithm is better than general fuzzy decision tree.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.355-361
• /
• 2006

In large scale environments like airport, museum, large warehouse and department store, autonomous mobile robots will play an important role in security and surveillance tasks. Robotic security guards will give the surveyed information of large scale environments and communicate with human operator with that kind of data such as if there is an object or not and a window is open. Both for visualization of information and as human machine interface for remote control, a 3D model can give much more useful information than the typical 2D maps used in many robotic applications today. It is easier to understandable and makes user feel like being in a location of robot so that user could interact with robot more naturally in a remote circumstance and see structures such as windows and doors that cannot be seen in a 2D model. In this paper we present our simple and easy to use method to obtain a 3D textured model. For expression of reality, we need to integrate the 3D models and real scenes. Most of other cases of 3D modeling method consist of two data acquisition devices. One for getting a 3D model and another for obtaining realistic textures. In this case, the former device would be 2D laser range-finder and the latter device would be common camera. Our algorithm consists of building a measurement-based 2D metric map which is acquired by laser range-finder, texture acquisition/stitching and texture-mapping to corresponding 3D model. The algorithm is implemented with laser sensor for obtaining 2D/3D metric map and two cameras for gathering texture. Our geometric 3D model consists of planes that model the floor and walls. The geometry of the planes is extracted from the 2D metric map data. Textures for the floor and walls are generated from the images captured by two 1394 cameras which have wide Field of View angle. Image stitching and image cutting process is used to generate textured images for corresponding with a 3D model. The algorithm is applied to 2 cases which are corridor and space that has the four wall like room of building. The generated 3D map model of indoor environment is shown with VRML format and can be viewed in a web browser with a VRML plug-in. The proposed algorithm can be applied to 3D model-based remote surveillance system through WWW.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.677-696
• /
• 2017

Cartoons and consequently animation are an effective way of visualizing futuristic scenarios. Here we look at how animation is becoming ubiquitous and an integral part of this future today: the cybernetic and mediated society that we are being transformed into. Animation therefore becomes a form of speech between humans and this networked reality, either as an interface or as representation that gives temporal form to objects. Animation or specifically animated films usually are associated with character based short and feature films, fiction or nonfiction. However animation is not constricted to traditional cinematic formats and language, the same way that design and communication have become treated as separate fields, however according to $Vil{\acute{e}}m$ Flusser they aren't. The same premise can be applied to animation in a networked culture: Animation has become an intrinsic to design processes and products - as in motion graphics, interface design and three-dimensional visualization. Video-games, virtual reality, map based apps and social networks constitute layers of an expanded universe that embodies our network based culture. They are products of design and media disciplines that are increasingly relying on animation as a universal language suited to multi-cultural interactions carried in digital ambients. In this sense animation becomes a discourse, the same way as Roland Barthes describes myth as a type of speech. With the objective of exploring the role of animation as a design tool, the proposed research intends to develop transmedia creative visual strategies using animation both as narrative and as an user interface.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.4 s.316
• /
• pp.48-54
• /
• 2007

Hand shape is one of important elements in Korean Sign Language (KSL), which is a communication method for the deaf. To express sign motion in a virtual reality environment based on OpenGL, we need an editor which can insert and modify sign motion data. However, it is very difficult that people, who lack knowledge of sign 1anguage, exactly edit and express hand shape using the existing editors. We also need a program to efficiently construct and store the hand shape data because the number of data is very large in a sign word dictionary. In this paper we developed a KSL hand shape editor to easily construct and edit hand shape by a graphical user interface (GUI), and to store it in a database. Hand shape codes are used in a sign word editor to synthesize sign motion and decreases total amount of KSL data.

• Information Systems Review
• /
• v.21 no.4
• /
• pp.143-156
• /
• 2019

Types of innovation can be categorized into simplification, information, automation, and intelligence. Intelligence is the highest level of innovation, and RPA can be seen as one of intelligence. Robotic Process Automation(RPA), a software robot with artificial intelligence, is an example of intelligence that is suited for simple, repetitive, large-scale transaction processing tasks. The RPA, which is already in operation in many companies in Korea, shows what needs to be done to naturally focus on the core tasks in a situation where the need for a strong organizational culture is increasing and the emphasis is on voluntary leadership, strong teamwork and execution, and a professional working culture. The introduction was considered naturally according to the need to find. Robotic Process Automation, or RPA, is a technology that replaces human tasks with the goal of quickly and efficiently handling structural tasks. RPA is implemented through software robots that mimic humans using software such as ERP systems or productivity tools. RPA robots are software installed on a computer and are called robots by the principle of operation. RPA is integrated throughout the IT system through the front end, unlike traditional software that communicates with other IT systems through the back end. In practice, this means that software robots use IT systems in the same way as humans, repeat the correct steps, and respond to events on the computer screen instead of communicating with the system's application programming interface(API). Designing software that mimics humans to communicate with other software can be less intuitive, but there are many advantages to this approach. First, you can integrate RPA with virtually any software you use, regardless of your openness to third-party applications. Many enterprise IT systems are proprietary because they do not have many common APIs, and their ability to communicate with other systems is severely limited, but RPA solves this problem. Second, RPA can be implemented in a very short time. Traditional software development methods, such as enterprise software integration, are relatively time consuming, but RPAs can be implemented in a relatively short period of two to four weeks. Third, automated processes through software robots can be easily modified by system users. While traditional approaches require advanced coding techniques to drastically modify how they work, RPA can be instructed by modifying relatively simple logical statements, or by modifying screen captures or graphical process charts of human-run processes. This makes RPA very versatile and flexible. This RPA is a good example of the application of digital to intelligence(D2I).

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.77-84
• /
• 2012

Face classification has wide applications in intelligent video surveillance, content retrieval, robot vision, and human-machine interface. Pose and expression changes, and arbitrary illumination are typical problems for face recognition. When the face is captured at a distance, the image quality is often degraded by blurring and noise corruption. This paper investigates the efficacy of multi-classifier decision level fusion for face classification based on the photon-counting linear discriminant analysis with two different cost functions: Euclidean distance and negative normalized correlation. Decision level fusion comprises three stages: cost normalization, cost validation, and fusion rules. First, the costs are normalized into the uniform range and then, candidate costs are selected during validation. Three fusion rules are employed: minimum, average, and majority-voting rules. In the experiments, unfocusing and motion blurs are rendered to simulate the effects of the long distance environments. It will be shown that the decision-level fusion scheme provides better results than the single classifier.