• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.310-310
• /
• 2000

The main problem in stereo vision is to find corresponding points in left and right image known as correspondence problem. Once correspondences determined, the depth information of those points are easily computed form the pairs of points in both image. In this paper, dynamic programming considering half-occluded region is used fer solving correspondence problem.

• 한국항해학회지
• /
• 제16권3호
• /
• pp.77-85
• /
• 1992

Camera arrangement for depth and image correspondence is very important to the computer vision. Two conventional comera arrangements for stereo computer vision are lateral model and axial motion model. In this paper, using the axial motion stereo camera model, the algorithm for camera focal length measurement and the surface smoothness with the radiance-irradiance is proposed fro 3-dimensional image correspondence on stereo computer vision. By adapting the above algorithm, camera focal length can be measured precisely and the resolution of 3-dimensional image correspondence has been improved comparing to that of the axial motion model without the radiance-irradiance relation.

• 한국정밀공학회지
• /
• 제10권4호
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.189-190
• /
• 2000

The purpose of this study is to estimate of design and ambience of goods by using 5 Kansei design items (shape, color, sense of material, fit, functionality/convenience). This paper describe that effectiveness of 5 Kansei design items. selecting image words and correspondence of 5 Kansei design items with image words. Kansei design items, selecting image words and correspondence of 5 Kansei design items with image words. (image words: the word describing about item image)

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

• 전자공학회논문지S
• /
• 제34S권7호
• /
• pp.78-88
• /
• 1997

A three dimensional-two spatical dimensions plus time-image segmentation is widely used in a very low bit rate image sequence coding because it can solve the region correspondence problem. Mathematical morphology is a very efficient tool for the segmentation because it deals well with geometric features such as size, shape, contrast and connectivity. But if the motion in the image sequence is large in time axis, the conventional 3D morphological segmentation algorithm have difficulty in solving region correspondence problem. To alleviate this problem, we propose the hierarchical image sequence segmentation algorithm that uses the region motion information. Since the motion of a region in previous level affects that in current level uses the previous motion information to increase region correspondence. Simulation result shows improved performance for sequence frames with large motion.

• 한국통신학회논문지
• /
• 제21권11호
• /
• pp.2776-2788
• /
• 1996

A new feature-based motion parameter estimation for arbitrary-shaped regions is proposed. Existing motion parameter estimation algorithms such as gradient-based algorithm require iterations that are very sensitive to initial values and which often converge to a local minimum. In this paper, the motion parameters of an object are obtained by solving a set of linear equations derived by the motion of salient feature points of the object. In order to estimate the displacement of the feature points, a new process called the "bi-directional correspondence scheme" is proposed to ensure the robjstness of correspondence. The proposed correspondence scheme iteratively selects the feature points and their corresponding points until unique one-to-one correspondence is established. Furthermore, initially obtained motion paramerters are refined using an iterative method to give a better performance. The proposed algorithm can be used for motion estimationin object-based image coder, and the experimental resuls show that the proposed method outperforms existing schemes schemes in estimating motion parameters of objects in image sequences.sequences.

• 융합신호처리학회논문지
• /
• 제12권4호
• /
• pp.242-249
• /
• 2011

화면 내의 평면영역에서 투영변환행렬 대응 매칭법을 제안한다. 본 연구는 RANSAC에 있지만, RANSAC에서 랜덤 샘플링에 균일분포를 이용하는 것아 아니고, 화상의 특징점 위치나 템플리트 매칭의 차이로부터 구한 다중의 비균일 분포를 이용한다. 기존의 매칭법은 정대응이 거의 만족해야 할 조건을 이용하여 올바르다고 추정되는 대응을 샘플링하고, 그 대응을 1대 1로 매칭시켜 RANSAC을 행하였지만, 제안 방법에서는 화상으로부터 구한 다중의 확률 분포에서 단계적으로 샘플링함으로써 확률이 높은 정대응을 다중의 대응 후보 중에서 효율적으로 샘플링할 수 있다. 그 결과 최종적으로 수많은 정대응을 구할 수 있으며, 시뮬레이션과 실제 화상의 실험에 의하여 제안 방법의 유효성을 검증한다.

• 융합신호처리학회논문지
• /
• 제12권1호
• /
• pp.26-32
• /
• 2011

This paper proposes a new method to process panoramic image stitching using SURF(Speeded Up Robust Features). Panoramic image stitching is considered a problem of the correspondence matching. In computer vision, it is difficult to find corresponding points in variable environment where a scale, rotation, view point and illumination are changed. However, SURF algorithm have been widely used to solve the problem of the correspondence matching because it is faster than SIFT(Scale Invariant Feature Transform). In this work, we also describe an efficient approach to decreasing computation time through the homography estimation using RANSAC(random sample consensus). RANSAC is a robust estimation procedure that uses a minimal set of randomly sampled correspondences to estimate image transformation parameters. Experimental results show that our method is robust to rotation, zoom, Gaussian noise and illumination change of the input images and computation time is greatly reduced.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.529-536
• /
• 2007

Registration between image and object space is a fundamental step in photogrammetry and computer vision. Along with rapid development of sensors - multi/hyper spectral sensor, laser scanning sensor, radar sensor etc., the needs for registration between different sensors are ever increasing. There are two important considerations on different sensor registration. They are sensor invariant feature extraction and correspondence between them. Since point to point correspondence does not exist in image and laser scanning data, it is necessary to have higher entities for extraction and correspondence. This leads to modify first, existing mathematical and geometrical model which was suitable for point measurement to line measurements, second, matching scheme. In this research, linear feature is selected for sensor invariant features and matching entity. Linear features are incorporated into mathematical equation in the form of extended collinearity equation for registration problem known as photo resection which calculates exterior orientation parameters. The other emphasis is on the scheme of finding matched entities in the aide of RANSAC (RANdom SAmple Consensus) in the absence of correspondences. To relieve computational load which is a common problem in sampling theorem, deterministic sampling technique and selecting 4 line features from 4 sectors are applied.