• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.54-63
• /
• 2007

The purpose of this study is to present a new energy minimization method for image completion with hierarchical approach. The goal of image completion is to fill in missing part in a possibly large region of an image so that a visually plausible outcome is obtained. An exemplar-based Markov Random Field Modeling(MRF) is proposed in this paper. This model can deal with following problems; detection of global features, flexibility on environmental changes, reduction of computational cost, and generic extension to other related domains such as image inpainting. We use the Priority Belief Propagation(Priority-BP) which is a kind of Belief propagation(BP) algorithms for the optimization of MRF. We propose the hierarchical Priority-BP that reduces the number of nodes in MRF and to apply hierarchical propagation of messages for image completion. We show that our approach which uses hierarchical Priority-BP algorithm in image completion works well on a number of examples.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.906-913
• /
• 2022

In this paper, we propose a new deep network architecture using nearest neighbor kernel for the estimation of dense depth map from its sparse map and corresponding color information. First, we propose to decompose the depth map signal into the structure and details for easier prediction. We then propose two separate subnetworks for prediction of both structure and details using classification and regression approaches, respectively. Moreover, the nearest neighboring kernel method has been newly proposed for accurate prediction of structure signal. As a result, the proposed method showed better results than other methods quantitatively and qualitatively.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.255-259
• /
• 2004

본 논문에서는 다목적 위성 2호의 주 탑재체인 MSC (Multi-Spectral Camera)의 영상자료 검보정을 위한 검보정 target 준비 작업에 대해 설명한다. MSC 영상 자료에 대한 검보정 작업은 다목적 위성 2호의 발사 후 초기 운영 기간 (LEOP: Launch and Early Operation Phase)인 3개월 동안 수행될 예정이다. 위성 발사 전까지 MSC 영상 자료에 대한 검보정을 수행하기 위해 필요한 준비 작업들이 현재 한국항공우주연구원에서 진행중이다. LEOP 기간 동안 MSC 영상 자료를 검보정하기 위해서, MSC의 센서 특성에 따라 7가지 정도의 검보정 target에 대한 설계 초안이 완성되었으며, 향후 target에 대한 설계를 완성한 후에 2004년 중에 한 두 부지에 몇 가지 target들을 건설하고, 다목적 위성 2호의 궤도 특성을 고려하여 일부 target은 운반이 가능하도록 제작할 예정이다. 검보정 target이 촬영된 MSC 영상 자료의 분석을 통해, GSD (Ground Sample Distance), Aliasing, Linearity, Edge Slope & Response, MTF (Modulation Transfer Function), FOV & IFOV, Absolute radiometric validation, Position Accuracy 등의 MSC 검보정 요소 값들을 측정할 계획이다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1350-1352
• /
• 2022

본 논문에서는 희소깊이영상과 컬러영상을 이용해 조밀한 깊이영상을 추정하는 깊이 완성(depth completion)을 수행하기위해 최근접 이웃 커널을 추정하는 방식의 네트워크를 제안한다. 회귀방식의 딥러닝 네트워크는 일반적으로 값을 직접 예측하는 것보다 기본 값에 더해질 잔차를 추정하는 방식이 더욱 효율적이다. 본 논문에서는 최근접 이웃 커널을 입력영상에 적용하여 추정하고자 하는 픽셀의 인근 픽셀에서 값을 가져와 기본 값으로 사용하고, 해당 값의 잔차를 회귀방식으로 추정하는 네트워크를 설계했다. 이러한 방식으로 여러 SOTA 알고리즘 대비 좋은 성능을 나타냈고, 특히 이와 유사한 방식인 Plane-residual net 보다 높은 성능을 보여준다.

• Journal of Korea Game Society
• /
• v.20 no.3
• /
• pp.15-24
• /
• 2020

We present a reinforcement learning-based framework for generating 2D Lego puzzle from input pixel art images. We devise heuristics for a proper Lego puzzle as stability and efficiency. We also design a DQN structure and train it to maximize the heuristics of 2D Lego puzzle. In legorization stage, we complete the layout of Lego puzzle by adding a Lego brick to the input image using the trained DQN. During this process, we devise a region of interest to reduce the computational loads of the legorization. Using this approach, our framework can present a very high resolutional Lego puzzle.

• Information and Communications Magazine
• /
• v.27 no.3
• /
• pp.36-41
• /
• 2010

3D 영상과 컨텐츠 제작 기술의 발전에도 불구하고 시청자 친화적인 영상 구현을 위한 기술발전의 여지는 여전히 존재한다. 3D관련 하드웨어 기술과 소프트웨어 기술이 일정 단계에 올라 선 상황에서 3D기술의 완성은 휴먼팩터 분야에서의 문제해결 없이는 불가능할 것이다. 본고는 휴먼팩터 분야의 연구 필요성과 현황 그리고 전망을 제시한다.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.69-80
• /
• 2022

Drone photogrammetry generally acquires images vertically or obliquely from above, so when photographing for the purpose of three-dimensional modeling, image matching for the ground of a building and spatial accuracy of point cloud data are poor, resulting in poor 3D mesh completeness. Therefore, to overcome this, this study analyzed the spatial accuracy of each drone image by acquiring smartphone images from the ground, and evaluated the accuracy improvement and completeness of 3D mesh when the smartphone image is not combined with the drone image. As a result of the study, the horizontal (x,y) accuracy of drone photogrammetry was about 1/200,000, similar to that of traditional photogrammetry. In addition, it was analyzed that the accuracy according to the photographing method was more affected by the photographing angle of the object than the increase in the number of photos. In the case of the smartphone image combination, the accuracy was not significantly affected, but the completeness of the 3D mesh was able to obtain a 3D mesh of about LoD3 that satisfies the digital twin city standard. Therefore, it is judged that it can be sufficiently used to build a 3D model for digital twin city by combining drone images and smartphones or DSLR images taken on the ground.

• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.95-104
• /
• 2007

As the broadcasting system rapidly migrates to the HD contents production, a broadcasting professional training program has increasingly requested, which provides a professional ability keeping up with new demands and a systematic well-organized education program. This paper utilized a DACUM(developing a curriculum) method for a video editor's job analysis and presented a job model of video editing. With a DACUM job analysis, we retrieved 9 essential job duties and 71 tasks, and then examined their importance, difficulty, frequency, and entry level tasks that are required before job hire. We also established a well-form structure of the job analysis results, completed a DACUM research chart, and consequently built a video editor's job model in TV broadcasting and video production areas. The proposed model is expected to be used as a fundamental material for a future job organization of video editors in TV broadcasting and video production areas, a development of the educational curriculum, and a priority decision of on-the-job training programs.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.108-109
• /
• 2015

본 논문은 low-rank 행렬의 truncated nuclear norm 최소화를 이용한 HDR (high dynamic range) 영상 합성 기법을 제안한다. 제안하는 기법에서는 기존의 LDR (low dynamic range) 영상에서 얻은 밝기의 선형 관계에 기반하여 HDR 합성을 low-rank 행렬 완성 문제로 변환한 후, ALM (augmented Lagrange multiplier) 기법을 이용하여 효율적으로 최적의 해를 구한다. 컴퓨터 모의실험을 통해 제안하는 기법이 기존 기법에 비해서 낮은 계산 복잡도를 보이면서도 더 높은 품질의 HDR 영상을 합성하는 것을 확인한다.

• Archives of design research
• /
• v.14
• /
• pp.77-84
• /
• 1996

The aspirations toward newness and uniqueness, which are represented as the main character of modern society and the motivation of the Art, have made the media for the Art, Design and Image varied and developed. As one of those streams, laser technology has stood out for the visual media of mystery and fantasy in the field of Public Entertainment, Image Exhibition and Art, and also it could be accelerated by the advancement of Electronics and Physics. This study focuses on the image creation by the laser technology, as the great product of the state-of-the-art science, whose physical feature produces visual effect of fantasy. As the first approach, the knowledge on the physical feature and technology of laser and system composition should be preceded in the step of planning and creation of laser image. Through the further understanding on graphic feature of laser image which increases the artistic quality of the image, this study hopefully activates the laser image works by the specialists and the artists in the field, and finally the creation of master-pieces.