• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.213-218
• /
• 2003

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS). We can save much efforts and time in adjusting robots to newly defined workcells by using OLPS. A proposed visual calibration scheme is based on position-based visual feedback. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test and construction of simple silhouette figures. Then camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 봄 학술발표논문집 Vol.28 No.1 (B)
• /
• pp.70-72
• /
• 2001

최근 멀티미디어 응용의 증가에 따라 그래픽 데이터를 위한 내용 기반 검색 기술에 대한 연구가 활발히 진행되고 있다. 또한 인터넷 응용분야에서 3차원 그래픽 데이터베이스 사용의 필요성이 대두되고 활용되고 있다. 대부분의 3차원 그래픽 시스템은 사용자에게 그래픽은 검색이 대상이 아니라 단순히 보여주는 역할로 주로 사용되고 있다. 3차원 그래픽객체는 어떤 객체들로 구성되여 있으며 그들의 크기는 어떠한지 등의 정보를 포함하고 있다. 따라서 3차원 그래픽 객체에서는 2차원 그래픽 객체에서는 2차원 이미지보다 의미객체에 대한 정확한 정보를 더 많이 얻어 낼 수 있다. 이러한 사실 때문에 2차원 이미지의 특징추출의 방법과는 다른 형식의 접근이 필요하다. 본 논문에서는 3차원 그래픽으로 모델링 된 3차원 객체들을 대상으로 객체가 이루는 X, Y, Z축상의 비율과 윤곽형태에 대한 SPBT(Space Partitioning Binary Tree)의 결과값으로 특징을 추출하고 샘플 데이터를 통해서 이들간의 클러스터링과 실제 예제 질의를 토한 비교분석을 통해 객체간의 유사검색이 가능하도록 하는 특징추출 방법을 제안하였다. 본 논문에서는 제시한 모양기반 특징추출 방법은 웹상의 다양한 3차원 객체정보의 자동분류나 3차원 그래픽 데이터베이스를 위한 인덱스 구축 등에 활용될 수 있을 것이다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.55-59
• /
• 1990

This study presents new algorithm for generating octree by volume intersection with pseudo-octrees which are constructed for each orthogonal face views in order to represent 3D objects exactly. In this algorithm, optimal quadtree is constructed for depth images in which distance information is represented in gray level, and then pseudo-octrees are constructed by using optimal quadtree in each orthogonal face view. It is shown that 3D object with concave parts can be reconstructed exactly by our suggested algorithm, and that memory space and tree construction time are also reduced compared with other algorithms.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.259-262
• /
• 2004

In most of the character recognition systems, the method of template matching or statistical method using hidden Markov model is used to extract and recognize feature shapes. In this paper, we used modified chain-code which has 8-directions but 4-codes, and made the chain-code of hand-written character, after that, converted it into transition chain-code by applying to HMM(Hidden Markov Model). The transition chain code by HMM is analyzed as signal flow graph by Mason's theory which is generally used to calculate forward gain at automatic control system. If the specific forward gain and feedback gain is properly set, the forward gain of transition chain-code using Mason's theory can be distinguished depending on each object for recognition. This data of the gain is reorganized as tree structure, hence making it possible to distinguish different hand-written characters. With this method, $91\%$ recognition rate was acquired.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2000년도 가을 학술발표회논문집
• /
• pp.159-165
• /
• 2000

A new state evaluation approach for structural safety is presented in this study. To reduce the subjectivity of the view and judgement of each expert founded on a limited body of knowledge in cognitive and inferential process of safety assessment, we introduced inductive learning method in AI. Inductive learning derives generalization from experiences. Decision tree induction algorithm analyzes the domain knowledge, produce rules via decision trees and then allow us to determine the classification of an object from case examples. The training set of state evaluation is constructed according to the selected attributes from working reports of RC bridge girders.

• 전자공학회논문지B
• /
• 제29B권9호
• /
• pp.50-58
• /
• 1992

A new algorithm for filling the interior of contours and labelling each filled region concurrently is presented. Filling is simply accomplished by inversion method. The labelling information in every scan lines is extracted directly from current direction of chain code so that the proposed algorithm needs less comparision and is more efficient. The contours are followed by two different directions, clockwise for the outer contour and counterclockwise for the inner contour to get filling and labelling information. This algorithm can be applied in case that contours are nested or regions are continous. Simulataneously the proposed algorithm can find the structure tree of object without additional post processing.

• 전자공학회논문지B
• /
• 제29B권1호
• /
• pp.1-10
• /
• 1992

This study presents a complete octree construction algorithm for 2D depth images obtained from orthogonal face views, which can represent 3D objects exactly. In constructing quadtree, optimal quadtree construction algorithm is applied to depth images for efficient use of memory and reduction of tree construction time. In addition, pseudo-octrees are constructed by using our proposed method, which construct pseudo-octrees according to the resolution value given in each node of constructed quadtree and mapping relation between quadrants and octants. Finally, a complete octree, which represents a 3D object, is constructed by volume intersection with each constructed pseudo-octree. The representation accuracy of a complete octree constructed by our algorithm is investigated by using a 3D display method and a volume ratio method for a complete octree.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.114-117
• /
• 2003

본 논문에서는 video stream내의 움직이는 객체 정보를 추정하고 동적 GTM(genetic tree-map) 알고리즘을 사용하여 얼굴 영역 검출 기법을 제안한다. 기존의 일반적인 객체 추정 기법은 클러스터(cluster)과정을 통하여 영상 정보를 분할하고 그 중 움직이는 객체 부분을 복원함으로서 추정하였다. 제안하는 기법은 BMA(block matching algorithm)［1］ 알고리즘을 사용하여 video stream 에서 움직이는 객체 정보를 얻고 클러스터 알고리즘으로 PCA(principal component analysis)를 사용한다. PCA 기법은 입력 데이터에 관해 통계적 특성을 이용하여 주성분을 찾는다. 주축과 영역분할 알고리즘을 사용하여 데이터를 분할하고, 분할된 객체 정보를 사용하여 특정 객체만을 추정하는 것이 가능하다. 이렇게 추정된 객체를 얼굴영역의 feature에 대하여 신경망 학습인 동적 GTM 알고리즘을 사용하여 생성된 동적 GTM 맵의 정보에 따라 객체의 얼굴영역만을 추출해 낼 수 있다［2-6］.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.737-739
• /
• 1996

Abnormal conditions and disturbances in distribution system cause an immediate influence to the customers. Conventional detection schemes for the distribution abnormalities have been applied in limited extents mainly because of their low reliability. In this paper, we developed a disturbance identification system which monitors the load level after a transient, checks the harmonic behavior of the load, and finally makes decision on the cause of the disturbance. This system identifies and discriminates overcurrent faults, arcing ground faults, recloser activities, and foreign object or tree contacts. In the implementation of the identification system, we applied fuzzy logic to better represent some variables whose Quantities are expressed only in non-numerical terms.