• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.179-182
• /
• 2003

This paper proposes a new stereo matching algorithm using both the divide-and-conquer method and the DSI(Disparity Space Image) technique. Firstly, we find salient feature points on the each scanline of the left image and find the corresponding feature point at the right image. Then the problem of a scanline is divided into several subproblems. By this way, matching of the subintervals is implemented by using the DSI technique. The DSI technique for stereo matching process is a very efficient solution to find matches and occlusions simultaneously and it is very speedy. In addition, we apply three occluding patterns to process occluded regions, as a result, we reduce mismatches at the disparity discontinuity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.224-241
• /
• 2015

Multiview plus depth (MVD) videos are widely used in free-viewpoint TV systems. The best-known technique to determine depth information is based on stereo vision. In this paper, we propose a novel local stereo matching algorithm which is radiometric invariant. The key idea is to use a combined matching cost of intensity and gradient based similarity measure. In addition, we realize an adaptive cost aggregation scheme by constructing an adaptive support window for each pixel, which can solve the boundary and low texture problems. In the disparity refinement process, we propose a four-step post-processing technique to handle outliers and occlusions. Moreover, we conduct stereo reconstruction tests to verify the performance of the algorithm more intuitively. Experimental results show that the proposed method is effective and robust against local radiometric distortion. It has an average error of 5.93% on the Middlebury benchmark and is compatible to the state-of-art local methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.6
• /
• pp.2217-2229
• /
• 2015

Since the variations of illumination, the irregular changes of human shapes, and the partial occlusions, multiple person tracking is a challenging work in computer vision. In this paper, we propose a graph clustering method based on spatio-temporal information of moving objects for multiple person tracking. First, the part-based model is utilized to localize individual foreground regions in each frame. Then, we heuristically leverage the spatio-temporal constraints to generate a set of reliable tracklets. Finally, the graph shift method is applied to handle tracklet association problem and consequently generate the completed trajectory for individual object. The extensive comparison experiments demonstrate the superiority of the proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.6
• /
• pp.596-601
• /
• 2011

Autonomous navigating algorithms for mobile robots have been proved to be a difficult task. Based on the excellent homing performance shown by many insects, bio-inspired navigation algorithms for robotic experiments have been widely researched and applied to the design of navigational strategies for mobile robots. In this paper, among them, we analyze two simple landmark navigation methods their strengths and limits. We investigate the effect of the occlusion problem mainly, which is an important yet tough problem in many landmark navigation algorithms. In the point of view of the error of homing vector and the performance of the homing paths in the environment with artificial occlusions, we investigate the effect of occlusion problem in both methods in order to further study on solutions.

• The Journal of Korea Robotics Society
• /
• v.3 no.2
• /
• pp.117-122
• /
• 2008

This paper presents a multi-robot localization based on multidimensional scaling (MDS) in spite of the existence of incomplete and noisy data. While the traditional algorithms for MDS work on the full-rank distance matrix, there might be many missing data in the real world due to occlusions. Moreover, it has no considerations to dealing with the uncertainty due to noisy observations. We propose a robust MDS to handle both the incomplete and noisy data, which is applied to solve the multi-robot localization problem. To deal with the incomplete data, we use the Nystr$\ddot{o}$m approximation which approximates the full distance matrix. To deal with the uncertainty, we formulate a Bayesian framework for MDS which finds the posterior of coordinates of objects by means of statistical inference. We not only verify the performance of MDS-based multi-robot localization by computer simulations, but also implement a real world localization of multi-robot team. Using extensive empirical results, we show that the accuracy of the proposed method is almost similar to that of Monte Carlo Localization(MCL).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.1964-1981
• /
• 2014

An improved Mean-Shift (MS) tracker called joint CB-LBWH, which uses a combined weighted-histogram scheme of CBWH (Corrected Background-Weighted Histogram) and LBWH (likelihood-based Background-Weighted Histogram), is presented. Joint CB-LBWH is based on the notion that target representation employs both feature saliency and confidence to form a compound weighted histogram criterion. As the more prominent and confident features mean more significant for tracking the target, the tuned histogram by joint CB-LBWH can reduce the interference of background in target localization effectively. Comparative experimental results show that the proposed joint CB-LBWH scheme can significantly improve the efficiency and robustness of MS tracker when heavy occlusions and complex scenes exist.

• International Journal of CAD/CAM
• /
• v.9 no.1
• /
• pp.103-109
• /
• 2010

Recently, various conformal geometric methods have been presented for non-rigid surface matching and registration. This work proposes to improve the robustness of conformal geometric methods to the boundaries by incorporating the symmetric information of the input surface. We presented two symmetric conformal mapping methods, which are based on solving Riemann-Cauchy equation and curvature flow respectively. Experimental results on geometric data acquired from real life demonstrate that the symmetric conformal mapping is insensitive to the boundary occlusions. The method outperforms all the others in terms of robustness. The method has the potential to be generalized to high genus surfaces using hyperbolic curvature flow.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.5
• /
• pp.88-95
• /
• 1999

스테레오 정합에서 가장 중요하고도 어려운 문제는 대응점 추출 문제와 폐색 영역에 대한 처리이다. 특히 폐색 영역의 점들은 대응점이 존재하지 않기 때문에 변이 정보 획득에 많은 어려움이 있다. 이러한 문제에 대한 효과적인 접근을 위해 본 논문에서는 쌍방향 정합 알고리즘을 기반으로 폐색 영역의 정합 정도를 향상 시키는 방법을 제안한다. 즉 좌,우 영상 각각의 기준에 대해 독립적인 변이 정보를 구하고, 이를 바탕으로 정합의 타당성 여부를 검토하여 그 결과를 다음 처리에서 반영하는 상호 보완적인 반복 처리 기법을 적용하였다. 이 과정에서 구해진 폐색 영역에 대한 변이 정보는 스테레오 영상 모델의 기하학적 구조를 적용하여 좌, 우측 기준 정합에 대해 그 좌, 우측 점들의 변이 정보들로 대체함으로써 불연속점들의 무뎌짐(blurring)현상을 개선하였다. 한편, 실험 결과를 보다 객관적으로 비교하기 위해 정합율과 에러율이라는 파라메터를 정의하여 개선된 결과를 보였다.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.317-318
• /
• 2006

There are lot of noises and errors in depth map image which is gotten by using a stereo camera. These errors are caused by mismatching of the corresponding points which occur in texture-less region of input images of stereo camera or occlusions. In this paper, we use a method which is able to get rid of the noises through post processing and reduce the errors of disparity values which are caused by the mismatching in the texture-less region of input images through the correlation between the depth map images and the input images. Then we propose a novel method which segments the object by using the improved disparity map images and projections.

• The korean journal of orthodontics
• /
• v.15 no.2
• /
• pp.279-289
• /
• 1985

This study was undertaken to find out the factor highly correlated to the depth of overbite among the skeletal factors of the craniofacial complex using lateral roentgenocephalograms. The subjects cconsited of fifty normal occlusions, sixty Class I malocclusions, sixty Class II division I malocclustions and sixty Class III malocclusions. The results were as follows: 1. Ans-Go-Me angle and lower genial angle showed high correlation to the depth of overbite in the total malocclusion sample. 2. The mean values of Ans-Go-Me angle and lower goinal angle for the normal sample were $49.8^{\circ}\;and\;75.6^{\circ}$, respectively. 3. Ans-Go-Me angle above $56^{\circ}$ or lower gonial angle above $84^{\circ}$ indicated a tendency toward an openbite. Conversely, Ans-Go-Me angle below $48^{\circ}$ or lower goinal angle below $73^{\circ}$ indicated a tendency toward a deepbite.