• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.39-54
• /
• 2018

Recently, augmented reality(AR) based building information applications using a smart phone provide information in the static form irrespective of the distance between a user and a target building. If many target buildings are located close to each other, discrimination of information is reduced due to overlapping information objects. Furthermore, it is difficult to intuitively grasp the current position of the user in the previous AR-based applications. In this paper, to solve these limitations, we have designed and implemented a novel building information system in which the location and size of information objects are adaptively displayed according to locations of a user and target buildings, and which allows users to intuitively understand their location by providing a 3D map that displays the user's location and all target buildings within a given distance in real-time. The AR-based building information application proposed in this paper focuses on the building guide in Deoksu Palace in Jung-gu, Seoul.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1031-1043
• /
• 2013

Extracting hand region from images is the first part in the process to recognize hand posture and gesture interaction. Therefore, a good segmenting method is important because it determines the overall performance of hand recognition systems. Conventional hand segmentation researches were prone to changing illumination conditions or limited to the ability to detect multiple people. In this paper, we propose a robust technique based on the fusion of skin-color data and depth information for hand segmentation process. The proposed algorithm uses skin-color data to localize accurate seed location for region-growing from a complicated background. Based on the seed location, our algorithm adjusts each detected blob to fill up the hole region. A region-growing algorithm is applied to the adjusted blob boundary at the detected depth image to obtain a robust hand region against illumination effects. Also, the resulting hand region is used to train our skin-model adaptively which further reduces the effects of changing illumination. We conducted experiments to compare our results with conventional techniques which validates the robustness of the proposed algorithm and in addition we show our method works well even in a counter light condition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.6
• /
• pp.1194-1199
• /
• 2009

Stereo vision system is useful method for inferring 3D depth information from two or more images. So it has been the focus of attention in this field for a long time. Stereo matching is the process of finding correspondence points in two or more images. A central problem in a stereo matching is that it is difficult to satisfy both the computation time problem and accuracy at the same time. To resolve this problem, we proposed a new stereo matching technique using weighted cost aggregation. To begin with, we extract the weight in given stereo images based on features. We compute the costs of the pixels in a given window using correlation of weighted color and brightness information. Then, we match pixels in a given window between the reference and target images of a stereo pair. To demonstrate the effectiveness of the algorithm, we provide experimental data from several synthetic and real scenes. The experimental results show the improved accuracy of the proposed method.

• The KIPS Transactions:PartD
• /
• v.13D no.6 s.109
• /
• pp.789-796
• /
• 2006

Context-aware is the core in ubiquitous environment of sensor network to support intelligent and contextual adaptation service. The new context information model is demanded to support context-aware applications. The model should not depend on a specified application and be shareable between applications in the same environment. Also, it should support various context representation and complex context-aware. In this paper, we define the context information according to context-aware process. Also we design the knowledge of domain as well as applications using ontologies and rules. The domain spatial ontology and application knowledge are represented using the spatial object model and the rules of expanded ontologies, respectively. The expression of abundant spatial ontology represents the context information about distance between objects and adjacent object as well as the location of the object. The proposed context information model which is able to exhibit various spatial context and recognizes complex spatial context through the existing GIS. This model shows that it can adapt to a large scale outdoor context-aware applications such as air pollution and prevention of disasters as well as various context-aware applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.2
• /
• pp.114-122
• /
• 2014

Beacon transmission is one of the fundamental mechanisms in vehicular ad hoc networks. Variety services including context awareness can be embodied by exchanging beacons in each vehicle. In this paper, we propose dual beacon transmission instead of traditional single beacon transmission for beaconing mechanism. dual beacon transmission divides beacon into two functions and operates two beaconing process independently. We verified the superiority of dual beacon transmission by comparing beacon packet delivery ratio with single beacon transmission. In conclusion, dual beacon transmission can reduce channel load and have both wider communication range and effective context awareness. In addition, implementing dual beacon transmission has less complexity and appliable with conventional adaptive beaconing schemes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.1-8
• /
• 2017

This paper presents the development of an adaptive cruise control (ACC) system, which is one of the typical advanced driver assist systems, for 4-wheel drive hybrid in-wheel electric vehicles. The front wheels of the vehicle are driven by a combustion engine, while its rear wheels are driven by in-wheel motors. This paper proposes an adaptive cruise control system which takes advantage of the unique driveline configuration presented herein, while the proposed power distribution algorithm guarantees its tracking performance and fuel efficiency at the same time. With the proposed algorithm, the vehicle is driven only by the engine in normal situations, while the in-wheel motors are used to distribute the power to the rear wheels if the tracking performance decreases. This paper also presents the modeling of the in-wheel motors, hybrid in-wheel driveline, and integrated ACC control system based on a commercial high-precision vehicle dynamics model. The simulation results obtained with the model are presented to confirm the performance of the proposed algorithm.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.7
• /
• pp.340-353
• /
• 2008

A computational color palette extraction model is introduced to describe paint brush objectively and efficiently. In this model, a color palette is defined as a minimum set of colors in which a painting can be displayed within error allowance and extracted by the two step processing of color grouping and major color extraction. The color grouping controls the resolution of colors adaptively and produces a basic color set of given painting images. The final palette is obtained from the basic color set by applying weighted k-means clustering algorithm. The extracted palettes from several famous painters are displayed in a 3-D color space to show the distinctive palette styles using RGB and CIE LAB color models individually. And the two experiments of painter classification and color transform of photographic image has been done to check the performance of the proposed method. The results shows the possibility that the proposed palette model can be a computational color analysis metric to describe the paint brush, and can be a color transform tool for computer graphics.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.225-228
• /
• 2011

동영상을 고효율로 압축할 수 있는 중요한 기술 중의 하나가 움직임 추정 기술이다. 움직임 추정 기술에서 가장 널리 사용되는 탐색 방식과 정합오차를 판단하는 기준은 각각 전역 탐색(FS: Full Search)알고리듬과 Sum of Absolute Differences(SAD)이다. 하지만, FS와 SAD를 사용한 움직임 추정기술은 인코더 전체 계산량의 50%이상을 차지하게 된다. 무선 통신 및 인터넷 환경에서 사용되는 응용프로그램에 대해서는 많은 계산량이 실시간 전송을 어렵게 만든다. 이러한 이유로, 동영상 압축 기술에서 계산량을 줄이는 방법이 중요하게 되었다. 그 결과로, SAD대신 다른 정합 오차 기준을 사용하여 움직임 추정기술의 계산량을 줄이는 알고리듬들이 제안되었다. 본 논문에서는 계산량을 줄이면서 하드웨어 구현 시 많은 이점을 가진 1비트 변환 (One-bit Transform, 1BT)알고리듬과 1비트 변환의 성능을 향상시킨 제한된 1비트 변환(Constrained one-bit transform, C-1BT)을 소개하고 C-1BT방법에 있어서 기존 방식의 빠른 인코딩속도를 유지하면서 PSNR을 증가시키는 알고리듬을 제안한다. 제안하는 알고리듬에서는 기존 C-1BT에서 고정해서 사용한 파라미터 D값을 대신에 현재블록과 동일한 위치에 있는 참조영역의 블록과 그 주변블록의 움직임벡터 정보를 이용해서 블록의 움직임 정도를 판단하고, 블록단위로 D값을 적응적으로 결정한다. 실험결과는 제안하는 알고리듬이 기존의 알고리듬과 비교하여 평균 0.11dB PSNR 증가를 보여 준다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2C
• /
• pp.188-195
• /
• 2012

Many systems are developing for the realization of NCW(Network Centric Warfare). UAV(Unmanned Aerial Vehicle) Network is attracting attention in a lot of military applications. In general, UAVs have the potential to create an ad-hoc network and greatly reduce the hops from source to destination. However, UAV networks exhibit unique properties such as high mobility, high data rate, and real time service. The routing protocols are required to design the multi-hop routing protocols that can dynamically adapt to the requirements of UAV network. In this paper we analyse Geographic Routing Protocol is based on geographical distance between source and destination for efficient and reliable transmission. Geographic Routing Protocol is evaluated in video service scenarios with TDMA model in our simulation. The simulation results show that the performance of Geographic Routing Protocol is better than the MANET Routing Protocol in terms of packet received ratio, end to end delay, and routing traffic sent.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7C
• /
• pp.544-553
• /
• 2012

A vehicle localization technology is an essential component to support many smart-vehicle applications, e.g. collision warning, adaptive cruise control, and so on. In this paper, we present a new vehicle localization algorithm based on the fusion of the sensing estimates from the local sensors and the GPS estimates from the inter-vehicle communications. The proposed algorithm consists of the greedy location data mapping algorithm and the position refinement algorithm. The former maps a sensing estimate with a GPS estimate based on the distance between themselves, and then the latter refines the GPS estimate of the subject vehicle based on the law of large numbers. From the numerical results, we demonstrate that the accuracy of the proposed algorithm outperforms that of the existing GPS estimates by at least 30 % in the longitudinal direction and by at least 60% in the lateral direction.