• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.70-74
• /
• 1999

Remote sensing (RS) data show the surfaces of the earth only but cannot provide the shape data of building sides. The proposed method recovers a 3D shape of building sides from stereo images. Its result shows a higher possibility for recovering a large shaped object by overcoming the difficulties of traditional stereo matching techniques. The urban area will be visualized more realistically than the current model based on graphic and vector data.

• Asia pacific journal of information systems
• /
• 제11권2호
• /
• pp.181-203
• /
• 2001

As the Internet is used extensively, multimedia information becomes more prevailing and accessible. However, legacy decision support systems rarely mention how to put such multimedia contents into practical use for decision making and support. In particular, no proposals have yet been made on how to integrate the decision technologies and multimedia databases in model management systems. Hence, the aim of this paper is to propose a new model management method to integrating decision technologies and an image database management system to create a multimedia decision support. For this purpose, extended ARG and structured modeling techniques are adopted, to represent image contents and mathematical models respectively. A web-based prototype system is presented to illustrate the feasibility and usability of the methodology.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.907-908
• /
• 2006

We describe a method for localizing a mobile robot in its working environment using a vision system and Virtual Reality Modeling Language (VRML). The robot identifies landmarks in the environment, using image processing and neural network pattern matching techniques, and then its performs self-positioning with a vision system based on a well-known localization algorithm. After the self-positioning procedure, the 2-D scene of the vision is overlaid with the VRML scene. This paper describes how to realize the self-positioning, and shows the overlap between the 2-D and VRML scenes. The method successfully defines a robot's path.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2950-2952
• /
• 1999

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) method and OpenGL. The final result image is helpful for the understanding of depth information visually.

• Annual Conference of KIPS
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.323-324
• /
• 2013

본 논문에서는 2차원 X-ray 영상을 이용하여 3차원 영상을 얻기 위한 전처리 과정으로 2차원 X-ray 영상에서 원하는 뼈 영상을 분할하기 위한 능동적 대퇴골 분할 기법에 대해 제안하고 구현하였다. X-ray 영상의 주된 화질 저하 요인인 잡음을 제거하고 에지 및 밝기 검출을 통하여 정확하고 빠른 뼈 영상 분할 기법을 구현하였고 대퇴골 영상을 통해 검증하였다. 이를 통해 최소한의 2차원 X-ray 영상을 이용하여 3차원 뼈 모델링을 구현하는데 필요한 뼈 영상을 획득하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• 제15권4호
• /
• pp.103-109
• /
• 2007

Ortho images and Digital Elevation Model (DEM) have been applied in various fields. It is necessary to acquire Ground Control Points (GCPs) for processing high resolution satellite images. However surveying GCPs require many time and expense. This study was performed to investigate whether GCPs automatically extracted from ortho images and DTED Level 2 can be applied to sensor modeling for high resolution satellite images. We analyzed the performance of the sensor model established by GCPs extracted automatically. We acquired GCPs by matching satellite image against ortho images. We included the height acquired from DTED Level 2 data in these GCPs. The spatial resolution of the DTED Level 2 data is about 30m. Absolution accuracy of this data is below 18m above MSL. The spatial resolution of ortho image is 1m. We established sensor model from IKONOS images using GCPs extracted automatically and generated DEMs from the images. The accuracy of sensor modeling is about $4{\sim}5$ pixel. We also established sensor models using GCPs acquired based on GPS surveying and generated DEMs. Two DEMs were similar. The RMSE of height from the DEM by automatic GCPs and DTED Level 2 is about 9 m. So we think that GCPs by DTED Level 2 and ortho image can use for IKONOS sensor modeling.

• Archives of design research
• /
• 제16권2호
• /
• pp.405-414
• /
• 2003

The modeling analysis for objects placed in a given space can be described objectively when their visual image structure is grasped. It can't be answered without first analyzing the basic program, visual expression. And when the whole aspect of the visual image of the desired interior utensils is presented, the mindset of its designer can be deduced from that. Therefore, the study was based on the lemon juice squeezer, one of the interior kitchen utensils that Philippe Starck designed for Italy ALESSI company. For the study method, putting'The Elements of Dynamic Symmetry' by Prof. Jay Hambidge into practice, 'paradigm' analysis containing the whole'lemon juice squeezer'image was attempted. And to describe it, the visual mark description method by Prof. Bok-Young Kim was used. In conclusion, henceforth, the relationship between interior space and articles, the relationship between object and user, the modeling critique or analysis of the production itself shoud not be intended to be emotional. On the contrary, the study presented an art analyic methodology that can analyze and describe the visual image structure numerically, and confirm the relationship between form and content.

• Journal of Korean Society of Rural Planning
• /
• 제19권4호
• /
• pp.177-189
• /
• 2013

3D modeling and rendering technologies are getting more attention from landscape planners and architects because the virtual reality based on 3D graphic technology could give more realistic experience to landscape simulation users and boost promotional effects. The 3D landscape simulation, however, not only requires a lot of cost and time in production, but also demands efforts to distribute to consumers due to various computing environment of them. The purpose of this study is to suggest a process for developing an interactive 3D landscape simulator with low-cost, which can support multi-platform functionality in high quality through reviewing related current software and web services. We select GIMP for 2D image texturing, SketchUpfor 3D modeling, Unity for real-time rendering, and Google Earth for terrain modeling considering price and workability and apply the developed process for Windows, Web, and Android versions to test the applicability for Sangji-ri, Gosam-myeon, Gyeonggi-do, Korea.

• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1162-1164
• /
• 2003

The methods of the geometric reconstruction and sensor calibration of satellite linear pushbroom images are investigated. The model of the sensor used is based on the SPOT model that is developed by Kraiky. The satellite trajectory is a Keplerian trajectory in the approximation. Four orbit parameters, longitude of the ascending node(${\omega}$), inclination of the orbit plan(I), latitude argument of the satellite(W) and distance between earth center and satellite, are used for the camera modeling. Time-dependent orbit parameters are expressed by quadratic polynomials. SPOT-5 images have been used for validation tests. The results are that the RMSE acquired from 20 GCPs is 1.763m and the RMSE of 5 checking points 2.470m. Because the ground resolution of SPOT-5 is 2.5m, the result obtained in this study has a good accuracy. It demonstrates that the sensor model developed by this study can be used to reconstruct the geometry of satellite image using pushbroom camera.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.97-99
• /
• 2021

As the aging society continues in recent years, interest in dementia is increasing. Among them, Alzheimer's disease is a degenerative brain disease that accounts for the largest percentage of all dementia patients, with the medical community currently not offering clear prevention and treatment for Alzheimer's disease, and the importance of early treatment and early prevention is emphasized. In this paper, we intend to find the most efficient activation function by combining various activation functions centering on convolutional neural networks using MRI datasets of normal people and patients with Alzheimer's disease. In addition, it is intended to be used as a dementia classification modeling suitable for the medical field in the future through Alzheimer's dementia classification modeling.