• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.61-63
• /
• 2005

Retreiving indoor scene reference image from database using visual information is important issue in Robot Navigation. Scene matching problem in navigation robot is not easy because input image that is taken in navigation process is affinly distorted. We represent probabilistic framework for the feature matching between features in input image and features in database reference images to guarantee robust scene matching efficiency. By reconstructing probabilistic scene matching framework we get a higher precision than the existing feaure-feature matching scheme. To construct probabilistic framework we represent each image as Gaussian Mixture Model using Expectation Maximization algorithm using SIFT(Scale Invariant Feature Transform).

• 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.

• 한국통신학회논문지
• /
• 제21권6호
• /
• pp.1361-1369
• /
• 1996

Motion estimation is one of the key components for high quality video coding. In this paper, a new motion estimation scheme for MPEG-like video coder is suggested. The proposed temporally adaptive motion estimation scheme consists of five functional blocks: Temporal subband analysis (TSBA), extraction of temporal information, scene change detection (SCD), picture type replacement (PTR), and temporally adapted block matching algorithm (TABMA). Here all the functional components are based on the temporal subband analysis. In this papre, we applied the analysis part of subband decompostion to the temporal axis of moving picture sequence, newly defined the temporal activity distribution (TAD) and average TAD, and proposed the temporally adapted block matching algorithm, the scene change detection algorithm and picture type replacement algorithm which employed the results of the temporal subband analysis. A new block matching algorithm TABMA is capable of controlling the block matching area. According to the temporal activity distribution of objects, it allocates the search areas nonuniformly. The proposed SCD and PTR can prevent unavailable motion prediction for abrupt scene changes. Computer simulation results show that the proposed motion estimation scheme improve the quality of reconstructed sequence and reduces the number of block matching trials to 40% of the numbers of trials in conventional methods. The TSBA based scene change detection algorithm can detect the abruptly changed scenes in the intentionally combined sequence of this experiment without additional computations.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.689-692
• /
• 1998

Matching two images is an essential step for many computer vision applications. A new approach to the scale and rotation invariant scene matching is presented. A set of andidate parameters are hypthesized by mapping the angular difference and a new distance measure to the hough space and by detecting maximally consistent points. The proposed method is shown to be much faster than the conventinal one where the relaxation process is repeated until convergence, while providing robust matching performance, without a priori information on the geometrical transformation parameters.

• 한국통신학회논문지
• /
• 제22권7호
• /
• pp.1523-1533
• /
• 1997

Image registration is concerned with the establishment of correspondence between images of the same scene with translational, rotational, and scaling differences. The estimated transformation parameters between images are very important information in the field of many applications. In this paper, we propose a shape matching scheme for finding correspondence points for images with various differences, Tranditional solutions to this area are unreliable for the rotational and schaling changes between images, and the feature extraction of partially occluded scene. To solve those problems, dominant points on digital curves are detected by scale-space filtering, and initial matching is performed by similarity measure of cumulative curvatures for dominant points. For initial matching segments pairs, optimal matching points are calculated using dynamic programming.Finally, transformation parameters are estimated.

• 융합신호처리학회논문지
• /
• 제6권2호
• /
• pp.74-81
• /
• 2005

디지털 미디어 데이터의 증가에 따라 디지털 미디어를 효과적으로 관리하고 사용하기 위하여 다양한 비디오 색인 및 비디오 시퀀스 정합을 위한 장면전환 검출 알고리즘이 제안되었다. 본 논문에서는 급격한 밝기 변화를 가지는 비디오 시퀀스에 대해서 효율적인 비디오 장면전환 검출 알고리즘을 제안한다. 급격한 밝기 변화를 고려한 비디오 색인의 정확도를 향상시키고 계산량을 줄이기 위해 제안한 알고리즘은 칼라 특성뿐만 아니라 에지 특성도 함께 사용하였으며 기존의 알고리즘에 비해 현저한 성능 향상을 보였다. 제안한 알고리즘은 먼저 칼라 히스토그램을 사용하여 후보 샷경계 지점을 추출하고 에지 정합과 밝기 보상을 이용하여 후보점들이 샷경계인지 밝기 변화인지를 결정한다. 장면내의 밝기 변화가 작은 경우 에지 정합과 밝기 보상은 샷경계에서만 일어난다. 실험 결과 제안한 방법은 기존의 방법에 비해 비슷한 계산량으로 현저히 향상된 성능과 효율을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2576-2589
• /
• 2017

Co-saliency detection is a task of detecting same or similar objects in multi-scene, and has been an important preprocessing step for multi-scene image processing. However existing methods lack efficiency to match similar areas from different images. In addition, they are confined to single image detection without a unified framework to calculate co-saliency. In this paper, we propose a novel model called Superpixel Matching-Cellular Automata (SMCA). We use Hausdorff distance adjacent superpixel sets instead of single superpixel since the feature matching accuracy of single superpixel is poor. We further introduce Cellular Automata to exploit the intrinsic relevance of similar regions through interactions with neighbors in multi-scene. Extensive evaluations show that the SMCA model achieves leading performance compared to state-of-the-art methods on both efficiency and accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.96-99
• /
• 1987

In the way of perception and depth finding of 3-D scene stereo vision is one of the best ways. Matching is important problem of stereo vision. In this paper we develop an algorithm that is adaptable to errors and computation time. And we demonstrate the way of matching.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.182-187
• /
• 1999

Stereo matching is one of the most crucial parts in DEM generation. Naive stereo matching algorithms often create many holes and blunders in a DEM and therefore a carefully designed strategy must be employed to guide stereo matching algorithms to produce “good” 3D information. In this paper, we describe one such a strategy designed by the use of scene geometry, in particular, the epipolarity for generation of a DEM from linear pushbroom images. The epipolarity for perspective images is a well-known property, i.e., in a stereo image pair, a point in the reference image will map to a line in the search image uniquely defined by sensor models of the image pair. This concept has been utilized in stereo matching by applying epipolar resampling prior to matching. However, the epipolar matching for linear pushbroom images is rather complicated. It was found that the epipolarity can only be described by a Hyperbola- shaped curve and that epipolar resampling cannot be applied to linear pushbroom images. Instead, we have developed an algorithm of incorporating such epipolarity directly in least squares correlation matching. Experiments showed that this approach could improve the quality of a DEM.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권11호
• /
• pp.767-774
• /
• 2002

기존의 원영상 복원 기술은 주로 신호 처리 분야에서 영상의 형성(formation), 저장 및 통신상에서 발생되는 왜곡 현상을 복원하는 연구가 많이 이루어 졌다. 원 영상 복원과 관련된 기존의 연구는 블록 정합(block matching algorithm)을 이용한 원영상 복원 방법이 있다. 이 방법은 오 정합(incorrect matching)이 발생하기 쉽고, 오 정합 시 에러가 전파되는 문제점이 있다. 그리고 장면 전환이 2회 이상 발생될 경우 장면 전환 지점과 지점 사이의 복원이 불가능하다는 문제점이 있다. 본 논문에서는 기존의 문제점들을 해결하기 위하여 확장적 블록 정합 방법(EBMA: Extended Block Matching Algorithm)과 영역 보상법(Region compensation method)을 이용한 원영상 복원 방법을 제안하고자 한다. 원영상 복원에 사용하기 위하여 비디오 사전 정보(장면 전환 정보, 카메라 모션 정보, 캡션 영역 정보)를 추출한다. 추출된 캡션 영역 정보를 이용하여 캡션 문자의 구성 요소 정보를 추출한다. 추출된 비디오 사전 정보를 이용하여 복원의 방향성을 결정하고, 복원의 방향성에 따라 문자의 구성 요소 단위로 확장적 블록 정합 방법과 영역 보상법을 이용하여 원영상 복원을 수행한다. 실험결과 확장적 블록 정합 방법은 빠른 물체의 움직임이나 복잡한 배경에 영향을 받지 않고 복원이 잘 되는 것을 알 수 있었다. 참조할 원영상이 없이 원영상 복원을 수행하는 영역 보상법의 복원 결과 또한 좋음을 볼 수 있었다.