• 방송공학회논문지
• /
• 제26권3호
• /
• pp.247-257
• /
• 2021

본 논문에서는 3D(dimensional) 스켈레톤을 이용하여 다시점 RGB-D 카메라를 캘리브레이션 하는 새로운 기법을 제안하고자 한다. 다시점 카메라를 캘리브레이션 하기 위해서는 일관성 있는 특징점이 필요하다. 또한 높은 정확도의 캘리브레이션 결과를 얻기 위해서는 정확한 특징점의 획득이 필요하다. 우리는 다시점 카메라를 캘리브레이션 하기 위한 특징점으로 사람의 스켈레톤을 사용한다. 사람의 스켈레톤은 최신의 자세 추정(pose estimation) 알고리즘들을 이용하여 쉽게 구할 수 있게 되었다. 우리는 자세 추정 알고리즘을 통해서 획득된 3D 스켈레톤의 관절 좌표를 특징점으로 사용하는 RGB-D 기반의 캘리브레이션 알고리즘을 제안한다. 다시점 카메라에 촬영된 인체 정보는 불완전할 수 있기 때문에, 이를 통해 획득된 영상 정보를 바탕으로 예측된 스켈레톤은 불완전할 수 있다. 불완전한 다수의 스켈레톤을 효율적으로 하나의 스켈레톤으로 통합한 후에, 통합된 스켈레톤을 이용하여 카메라 변환 행렬을 구함으로써 다시점 카메라들을 캘리브레이션 할 수 있다. 캘리브레이션의 정확도를 높이기 위해서 시간적인 반복을 통해서 다수의 스켈레톤을 최적화에 이용한다. 우리는 실험을 통해서 불완전한 다수의 스켈레톤을 이용하여 다시점 카메라를 캘리브레이션 할 수 있음을 증명한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국제학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.826-831
• /
• 1988

This paper presents an approach to segment an image into areas of surfaces, and to compute the surface properties from a gray-scale image in order to describe the surfaces for reconstruction of the 3-D shape of the objects. In general, an rigid body has several surfaces and many edges. But if it is not polyhedoron, it is necessary not only to describe the relation between surfaces, i.e. its line drawings but also to represent the surfaces' equations itself. In order to compute the surfaces' equation we use a probability of edge distribution. At first it is extracted edges from a gray-level image as much as possible. These are not only the points that maximize the change of an image intensuty but candidates which can be seemed to be edges. Next, other character of a surface (color, coordinates and image intensity) are extracted. In our study, we call the all feature of a surface as "texture", for example color, intensity level, orientation of an edge, shape of a surface and so on. These features of a surface on a pixel of an image plane are mapped to a point of the feature space, and segmented to each groups by cluster analysis on this space. These groups are considered to represent object surface in an image plane. Finally, the states of object surface in 3-D space are computed from distributional probability of local and overall statistical features of a surface, and from shape of a surface.a surface.

• 한국조경학회지
• /
• 제26권4호
• /
• pp.25-35
• /
• 1999

This thesis is to newly understand the value and the meaning of Chonju Palkyong(全州八景) by the specific gravity in making a counter-proposal in other to improve the landscape identity of modern city and at the same time. I intended to group the grafting device for the preservation and regeneration of modern history cultural environment through the interpretation of landscape construction. The meaning system of Chonju Palkyong showed the symbolic system which a landscape construction, four directions and two places has and exhibited the landscape shape possessing a luxuriant local feature peculiar to Chonju, preserving visual bound language of a classical Palkyong. Especially, it implies the use of the substantial landscape experienced factor, the expressions about natural phenomena and the matter which has melted human living circumstances. The landscape construction and it's form show the system which forms the different time field, a far landscape and a mid distance landscape and a near landscape, etc., under the visual, psychological, scenic influenced area, preserving the feature of the similar and typical type of Sosang Palkyoung（瀟湘八景) which intended to seek the local reappearance of the famous site experienced type and natural matter which famous place and local conduct were combined. The object space of Chonju Palkyong area representing the nature of historical landscape cultural assets, pushed by the greater part of the development based theory, shows injured aspects, but needs to play a part to seek such a up-to-date successive plan as the reconstruction of the destroyed historical landscape area which motivated Palkyong, the establishment of useful area, the embodiment of the cultural identity of Palkyong area and the becoming of the educational cultural life space. The analysis of the landscape construction of Chonju Palkyong and the grouping of the modern successive plan which I considered in this thesis, will be able to become a fundamental data to carry out the preservation of historical landscape and the landscape plan in the city.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.1141-1144
• /
• 2005

본 논문에서는 구조물의 안전성을 목적으로 변위를 감시하는 자동화된 시스템을 제안한다. 사진측량 기법은 서로 다른 각도에서 촬영된 2차원 이미지로부터 대상물의 정밀한 3차원 형상을 얻어내는 기법으로써 구조물의 변형을 분석하기에 매우 정확하면서도 편리하다. 본 논문은 카메라보정, 표정점(coded target)을 이용한 특징점의 획득, 획득된 특징점의 3차원 복원 및 정확도 분석의 과정으로 구성된다. 논문에서 사용되는 다시점 카메라 각각의 카메라는 일정한 거리와 시차로 배치하였다. 카메라 보정은 다시점 카메라로부터 획득된 3장의 영상에서 7개 이상의 대응점들로부터 트라이포컬텐서를 구하고 이로부터 유클리드 카메라를 구하는 자기교정(self-calibration) 방법을 사용하였다. 특히 특징점 획득 과정에서, 정확한 좌표를 구하기 위하여 외곽형상으로부터 중심점의 좌표를 정확하게 계산해내는 서브픽셀 기법을 사용하고 패턴 인식 기법을 이용하여 특징점을 자동으로 검출하였으며, 실세계 좌표상에서의 실측값을 구하기 위하여 스케일 바를 사용한다.

• 한국측량학회지
• /
• 제31권6_2호
• /
• pp.611-623
• /
• 2013

Point cloud data (i.e., LiDAR; Light Detection and Ranging) collected by Airborne Laser Scanner (ALS) system is one of the major sources for surface reconstruction including DEM generation, topographic mapping and object modeling. Recently, demand and requirement of the accurate and realistic Digital Building Model (DBM) increase for geospatial platforms and spatial data infrastructure. The main issues in the object modeling such as building and city modeling are efficiency of the methodology and quality of the final products. Efficiency and quality are associated with automation and accuracy, respectively. However, these two factors are often opposite each other. This paper aims to introduce correction scheme of incorrectly determined Model Key Points (MKPs) regardless of the segmentation method. Planimetric and height locations of the MKPs were refined by surface patch fitting based on the Least-Squares Solution (LESS). The proposed methods were applied to the synthetic and real LiDAR data. Finally, the results were analyzed by comparing adjusted MKPs with the true building model data.

• 디지털콘텐츠학회 논문지
• /
• 제19권6호
• /
• pp.1197-1205
• /
• 2018

본 논문에서는 함정전투체계의 EOTS나 IRST에서 획득한 영상을 초고해상도 영상으로 복원한다. 저해상도에서 초고해상도의 영상을 생성하는 생성 모델과 이를 판별하는 판별 모델로 구성된 생성적 적대 신경망을 이용하고, 다양한 학습 파라미터의 변화를 통한 최적의 값을 제안한다. 실험에 사용되는 학습 파라미터는 crop size와 sub-pixel layer depth, 학습 이미지 종류로 구성되며, 평가는 일반적인 영상 품질 평가 지표에 추가적으로 특징점 추출 알고리즘을 함께 사용하였다. 그 결과, Crop size가 클수록, Sub-pixel layer depth가 깊을수록, 고해상도의 학습이미지를 사용할수록 더 좋은 품질의 영상을 생성한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• 대한기계학회논문집A
• /
• 제20권6호
• /
• pp.1743-1752
• /
• 1996

In this paper, a precision inspection technique using CAD/CAI integration is proposed for the parts having very thin and sharp 3 dimensional curve features. The technique begings with feature reconstruction of turbine blades which have 3 dimensional combined feometry, such as splines, and thin circles. The alifnment procedures consistsb of two phases-rough and fine phases : rough phase alignment is based on the conventional 6 point5s probing on the clear cut surfacef, and fine phase alignment is based on the intial measurement on the 3 dimensional curved parts using an lterative measurement feed-back least sequares technique for alignment. Forf the analysis of profile tolerance of parts, the actual measured points are obtained by finding the closet points on the CAD geometry by the developed subdivision technique and the Tschebycheff norm is applied based on iterative fashion, giving accurate profile tolerance value. The developed inspection technique is applied to practical procedures of blade manufacturing and demonstrated high performance.

• 제어로봇시스템학회논문지
• /
• 제15권11호
• /
• pp.1080-1087
• /
• 2009

This paper presents an algorithm to acquire 3D geometric information using a virtual plane method. The method to measure 3D information on the plane is easy, because it's not concerning value on the z-axis. A plane can be made by arbitrary three points in the 3D space, so the algorithm is able to make a number of virtual planes from feature points on the target object. In this case, these geometric relations between the origin of each virtual plane and the origin of the target object coordinates should be expressed as known homogeneous matrices. To include this idea, the algorithm could induce simple matrix formula which is only concerning unknown geometric relation between the origin of target object and the origin of camera coordinates. Therefore, it's more fast and simple than other methods. For achieving the proposed method, a regular pin-hole camera model and a perspective projection matrix which is defined by a geometric relation between each coordinate system is used. In the final part of this paper, we demonstrate the techniques for a variety of applications, including measurements in industrial parts and known patches images.

• 한국정밀공학회지
• /
• 제29권5호
• /
• pp.554-562
• /
• 2012

Processing of Scanning electron microscope imaging has been analyzed in both secondary electron (SE) imaging and backscattered electron (BSE) image. Because of unique characteristics of both secondary electron and backscattered electron image, mechanism of imaging process and image quality are quite different each other. For the sake of characterize imaging process, Monte Carlo simulation code have been developed. It simulates electron penetration and depth profile in certain material. In addition, secondary electron and backscattered electron generation process as well as their spatial distribution and energy characteristics can be simulated. Geometries that has fundamental feature have been imaged using the developed Monte Carlo code. Two, SE and BSE images generation process will be discussed. BSE imaging process can be readily used to discriminate in both material and geometry by simply changing position and direction of BSE detector. The developed MC code could be useful to design BSE detector and their position. Furthermore, surface reconstruction technique is possibly developed at the further research efforts. Basics of Monte Carlo simulation method will be discussed as well as characteristics of SE and BSE images.