Kyeong-Jin Ban

An Object Representation System Using Virtual Space Coordinates

Conventional Augmented Reality has used data gloves or markers for smooth interaction between objects and background. This causes inconvenience of use and lower immersion. To build up immersion in Augmented Reality, additional input devices must be removed. For this purpose, accurate recognition of space coordinates is needed even with no attachment of markers. This paper proposes a method to create virtual space coordinates for interaction without wearing additional input devices so as to improve immersion in Augmented Reality. The acquired image was projected to 2D space and vanishing lines were extracted to calculate the virtual space coordinates. Then the sizes of the inserted objects were varied in accordance with the size of the virtual coordinates area based on the image projected onto the 2D coordinates. This resulted in improved immersion. This method can increase the efficiency of object creation by excluding the use of a 3D modeler for creation of 3D objects.

Stabilized UAV flight system design for structure safety inspection

For the small air vehicle-based structure safety inspection, it is very important to collect the images without shaking and the data by manipulating the air vehicle, even though the inspector does not have professional experience. In this article, the method for the stabilized flight system design for the safety inspection of the small air vehicle-based structures.

Outdoor Augmented Reality based 3D Model Visualization System of Cultural Heritage Sites

Recently, at home and abroad cultural content industry has developed as the growing importance of history. Among them, the reconstruction contents area which combined with IT technology is attracting attention. Specially, using augmented reality technology, 3D visualization researches which restore contents of architectural heritage, cultural heritage sites, and artifacts have been performed in cultural content area. The existing cultural site restore contents are mostly made based on the images taken from indoor. In this paper, efficiently visualize the restore contents in indoor, but outdoors is limited. This theses presents the cultural heritage sites 3D model visualization system using augmented reality in outdoor. Proposed system augments 3D model to cultural heritage site in outdoor by using Smart Phone.

One-to-One Embedding between Hyper Petersen and Petersen-Torus Networks

Once a designed network is embedded into a newly designed network, a developed algorithm in the designed network is reusable in a newly designed network. Petersen-Torus has been designed recently, and Hyper Petersen has already been designed as a well-known interconnection network. In this study, it was proven that Hyper Petersen network whose degree increases with the increased number of nodes can be embedded into a Petersen-Torus network having fixed degree. Hyper Petersen log2 n 2 + 3 was embedded into Petersen-Torus PT(n,n) with expansion 1, dilation 1.5n+2, and congestion 5n. The embedding algorithm was designed for expansion 1, and congestion and dilation are in proportion to O(n) owing to the aspect of Hyper Petersen that the degree increases.

Design and Implementation of Flocking System for Increasing System Capacity with Hybrid Technique

Due to spread of movies or online games which are applied with computer animation techniques, we can easily see scenes where numerous characters appear. In the case of large-scale crowd animation, if one were to increase reality of the scene, features of system would be lowered, and if one were to increase functioning of system, reality of the scene would be lowered. In realizing large-scale crowd animation with seafloor environment as background, the paper analyzed and applied elements that affect behavioral types of fishes; and by using concept of crowd, the paper enabled each group or object to control their behavioral type; by comparing and contrasting real-time calculation method as calculation method for animation and hybrid calculation method which is mixed calculation method, the paper seeks to find a method that increases functioning of the system while also expresses natural scenes.

3D Panorama Generation Using Depth-MapStitching

As the popularization and development of 3D display makes common users easy to experience a solid 3D virtual reality, the demand for virtual reality contents are increasing. In this paper, we propose 3D panorama system using vanishing point locationbased depth map generation method. 3D panorama using depthmap stitching gives an effect that makes users feel staying at real place and looking around nearby circumstances. Also, 3D panorama gives free sight point for both nearby object and remote one and provides solid 3D video.

Object recognition based power plant management system in smart grid using smart device

Today, the world is facing diverse problems such as energy saving, climate change and economic growth etc. To overcome those problems, an introduction of a smart grid is considered to be dispensable for satisfying future energy requirements such as rationalization of power consumption, stimulation of low-carbon energy technologies through less consumption of fossil fuel, greater use of renewable energy like photovoltaic and wind power, and a need of next-generation growth engine. In this paper, an object recognition based smart grid photovoltaic power facility management system is proposed. Using the proposed system, maintenance and repairs required due to regular inspection or faults can be carried out more efficiently in a remote site. Additionally, the proposed system takes an object recognition based technology instead of using QR code when recognizing the facility. It implies that this approach can be applied straight away to an existing system because it does not require any need of attaching an additional equipment to an existing smart grid power facility. Furthermore, the proposed system applies a markerless-based object recognition technique. Therefore it is expected that this service can be easily extended to recognizing other types of facilities such as smart grid transmission and distribution facilities in the future.

An object expression system using depth-maps

The current of Augmented Reality are data gloves or markers used for interactions between object and background. But, this results in the inconvenience in use and reduced immersiveness. To reinforce immersiveness in AR, added input devices should be removed. To this end, spatial coordinates should be accurately perceived even when a marker has been attached. In this paper, an object expression system was proposed that uses depth-maps for interactions without any additional input devices in order to improve immersiveness. Immersiveness was improved by projecting obtained images on 2D spaces, extracting vanishing lines, calculating the virtual spatial coordinates of the projected images, and varying the sizes of the inserted objects in accordance with the sizes of the areas of virtual coordinates, based on the images projected on the 2D coordinates. By using this system, the use of 3D modelers could be excluded when 3D objects were created; thus, the efficiency of object creation could be improved.

Improved Fuzzy Single Layer Supervised Learning Algorithm

In this paper, we improve the convergence prevented from vibrating decision boundary with bias term and suggest a linear activation function. We propose an enhanced fuzzy single layer perceptron which reduces the learning time introducing the rate of learning and the concept of momentum. We applied to Exclusive OR problem and pattern recognition of letters to analyze the performance of learning through enhanced fuzzy single layer perceptron and precedent fuzzy single layer perceptron. After the number of epoch and the convergence of enhanced fuzzy single layer perceptron were compared with those of precedent one, we found that enhanced one had far less time for learning and improved the convergence.

An Object Expression System using Depth-maps

In existing Augmented Reality (AR), data gloves or markers are used for smooth interactions between objects and backgrounds. This results in inconvenience in use and reduced immersiveness. To reinforce immersiveness in AR, added input devices should be removed. To this end, spatial coordinates should be accurately perceived even when a marker has been attached. In this paper, an object expression system was proposed that uses depth-maps for interactions without any additional input devices in order to improve immersiveness. Immersiveness was improved by projecting obtained images on two-dimensional (2D) spaces, extracting vanishing lines, calculating the virtual spatial coordinates of the projected images, and varying the sizes of the inserted objects in accordance with the sizes of the areas of virtual coordinates, based on the images projected on the 2D coordinates. By using this system, the use of three-dimensional (3D) modelers could be excluded when 3D objects were created, thus, the efficiency of object creation could be improved.