• 정보처리학회논문지B
• /
• 제15B권4호
• /
• pp.269-274
• /
• 2008

본 논문에서는 스테레오 영상(stereo image)을 이용하여 스네이크 기반 객체 추출 방법들이 강력한 외부 에너지(external energy)를 생성할 수 있도록 새로운 스테레오 일치화 방법을 제안한다. 제안하는 방법의 첫 번째 단계로 한 쌍의 스테레오 영상에서 다중 레벨 에지 지도를 만들고 상관관계를 파악하여 에지 기반의 변위 지도(disparity map)를 만든다. 이때 비슷한 세기를 가진 에지를 정합(matching)에 이용한다. 이 후 영상 내에서 추출하고자 하는 객체의 에지 지도를 얻기 위하여 다음의 과정을 거친다. 왼쪽 영상에서의 관심 영역의 에지 패턴을 얻고 다시 오른쪽에서도 똑같이 패턴을 얻어낸 후 두 패턴을 정합하여 객체의 변위(disparity)를 얻어낸다. 이렇게 얻어진 에지 지도를 이용하여 스네이크에서 사용될 외부 에너지를 만든다. 제안하는 방법을 이용하여 두 종류의 스네이크 모델에서 테스트를 한 결과 기존의 방법에 비해 더 나은 결과를 얻게 되었다.

• 한국정보처리학회논문지
• /
• 제6권4호
• /
• pp.1120-1128
• /
• 1999

모델을 이용한 물체인식을 모델영상들과 입력영상 간의 그래프 매칭과정으로 정의하였다. 본 논문에서는 그래프 매칭 문제를 최적화문제로 모델링하였고 최적화 문제해결을 위하여 유전자 알고리즘을 제안하였다. 이를 위하여 적합성함수, 자료구조, 유전연산자들이 개발되었다. 제안된 유전자 알고리즘이 이차원 영상에서 부분적으로 겹쳐진 물제들을 인식하기 위한 모델영상과 입력영상 간의 특징 점들을 일치시킴을 시뮬레이션을 통하여 보였다. 제안된 방법의 성능을 신경회로망을 이용한 방법과 비교하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.213-215
• /
• 2009

Using the object recognition processing on the captured images, we can inspect whether a packaging process is performed correctly in real time. So we realized the functions that acquire an image of each state of the packaging process using a camera, extract each object in the image, and inspect the packaging process using the extracted object data. In case an object shape is solid, for object search, a shape-based matching algorithm was used which searches the object utilizing the informations on the shape. In case an object shape is not solid, and Is flexible, gray-level difference of the pixels in the limited image region including the object was used to recognize the object.

• 한국통신학회논문지
• /
• 제28권2C호
• /
• pp.121-128
• /
• 2003

본 논문에서는 스테레오 영상 압축 시 흔히 사용되는 블록 정합 기법의 문제점인 블록화 에러를 줄일 수 있는 객체기반 블록 정합 기법(object based block matching algorithm : OBMA)을 제안한다. 제안된 OBMA 기법에서는 영상의 경계 정보(edge map)를 추출한 후 블록내의 경계선 정보의 유무를 가지고 영상을 각각의 객체로 나누어 객체별로 변이를 예측함으로써 기존 블록정합 기법에서 발생하던 경계부분에서의 블록화 에러를 줄일 수 있었다. 모의 실험 결과 기존의 블록 정합(block matching) 기법보다 주관적 영상 품질은 현저히 개선하면서도 유사한 성능의 PSNR을 유지할 수 있었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.568-571
• /
• 2005

This paper introduces a correlation-based surface matching algorithm that can be used to reconstruct the surface topography of an object that is scanned from multiple overlapping regions by an AFM. The image matching technique is applied to two neighboring images intentionally overlapped with each other. To account for the inaccuracy of the coarse stage implemented in AFM, all the six axes including the rotational degrees of freedom are successively matched to maximize the correlation coefficient. The results show that the proposed 6-axes image matching method is useful for expanding the measurement range of AFM.

• 전자공학회논문지S
• /
• 제34S권2호
• /
• pp.63-70
• /
• 1997

This paper proposes a new algorithm for recognizing polyhedral objects using a single 2-D image. It is base don a new representation scheme having two level hierarchey. In the lower level, geometrical features of each primitive surface are represented using their signatures and the variation of signature due to rotation is represented suing the rotation map. In the higher level, topological features are represented in the inter-surface description table(SDT). Based on the proposed representaton scheme, loer level database searched to find a matching primitive surface. The srotation map determines the degree of rotation as well as the matchness. If all surfaces in a test object find their matching primitive surfaces, its structural information is compared with the SDTs of object models. If primitive surfaces of a test object equal to tha tof certain model and satisfy inter-surfaces relationship in SDT, a test object is recognized as the model.

• 제어로봇시스템학회논문지
• /
• 제18권6호
• /
• pp.571-578
• /
• 2012

In the paper, we proposed a ring type structured light image based embedded ranging sensor for a mobile robot. Since the proposed ranging sensor obtains omnidirectional object distance, it is useful for autonomous navigation of a mobile robot. By matching the local omnidirectional distance map with a given global object map, it is possible to get position and heading angle of mobile robot in the global coordinates. Experiments for matching and navigation were carried out to verify the performance of the proposed ranging sensor.

• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.935-956
• /
• 2016

With the help of advanced image acquisition and processing technology, the vision-based measurement methods have been broadly applied to implement the structural monitoring and condition identification of civil engineering structures. Many noncontact approaches enabled by different digital image processing algorithms are developed to overcome the problems in conventional structural dynamic displacement measurement. This paper presents three kinds of image processing algorithms for structural dynamic displacement measurement, i.e., the grayscale pattern matching (GPM) algorithm, the color pattern matching (CPM) algorithm, and the mean shift tracking (MST) algorithm. A vision-based system programmed with the three image processing algorithms is developed for multi-point structural dynamic displacement measurement. The dynamic displacement time histories of multiple vision points are simultaneously measured by the vision-based system and the magnetostrictive displacement sensor (MDS) during the laboratory shaking table tests of a three-story steel frame model. The comparative analysis results indicate that the developed vision-based system exhibits excellent performance in structural dynamic displacement measurement by use of the three different image processing algorithms. The field application experiments are also carried out on an arch bridge for the measurement of displacement influence lines during the loading tests to validate the effectiveness of the vision-based system.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2005년도 추계학술대회
• /
• pp.59-80
• /
• 2005

This Paper Presents a Rational Function Model (RFM)-based image matching technique for IKONOS satellite imagery. This algorithm adopts the object-space approach and reduces the search space within the confined line-shaped area called the Piecewise Matching Line (PLM). Also, the detailed procedure of generating 3-D surface information using the Rational Function model Coefficients (RFCs) is introduced as an end-user point of view. As a result, the final generated Digital Elevation Model (DEM) using the proposed scheme shows a mean error of 2$\cdot$2 m and RMSE of 3$\cdot$8 m compared with that from 1:5000 digital map.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.311-311
• /
• 2000

We propose a DP-based formulation for matching line patterns by defining a robust and stable geometric representation that is based on the conceptual organizations. Usually, the endpoint proximity and collinearity of image lines, as two main conceptual organization groups, are useful cues to match the model shape in the scene. As the endpoint proximity, we detect junctions from image lines. We then search for junction groups by using geometric constraint between the junctions. A junction chain similar to the model chain is searched in the scene, based on a local comparison. A Dynamic Programming-based search algorithm reduces the time complexity for the search of the model chain in the scene. Our system can find a reasonable matching, although there exist severely distorted objects in the scene. We demonstrate the feasibility of the DP-based matching method using both synthetic and real images.