• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.52-58
• /
• 2007

In this paper we propose a new robust method to extract accurate human silhouettes indoors with active stereo camera. A prime application is for gesture recognition of mobile robots. The segmentation of distant moving objects includes many problems such as low resolution, shadows, poor stereo matching information and instabilities of the object and background color distributions. There are many object segmentation methods based on color or stereo information but they alone are prone to failure. Here efficient color, stereo and image segmentation methods are fused to infer object and background areas of high confidence. Then the inferred areas are incorporated in graph cut to make human silhouette extraction robust and accurate. Some experimental results are presented with image sequences taken using pan-tilt stereo camera. Our proposed algorithms are evaluated with respect to ground truth data and proved to outperform some methods based on either color/stereo or color/contrast alone.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.33-45
• /
• 2011

In this paper, we present a method for extracting video objects efficiently by using the modified graph cut algorithm based on contour information. First, we extract objects at the first frame by an automatic object extraction algorithm or the user interaction. To estimate the objects' contours at the current frame, motion information of objects' contour in the previous frame is analyzed. Block-based histogram back-projection is conducted along the estimated contour point. Each color model of objects and background can be generated from back-projection images. The probabilities of links between neighboring pixels are decided by the logarithmic based distance transform map obtained from the estimated contour image. Energy of the graph is defined by predefined color models and logarithmic distance transform map. Finally, the object is extracted by minimizing the energy. Experimental results of various test images show that our algorithm works more accurately than other methods.

• Communications of the Korean Mathematical Society
• /
• v.30 no.2
• /
• pp.65-72
• /
• 2015

The minimum rank mr(G) of a simple graph G is defined to be the smallest possible rank over all symmetric real matrices whose (i, j)-th entry (for $i{\neq}j$) is nonzero whenever {i, j} is an edge in G and is zero otherwise. The corona $C_n{\circ}K_t$ is obtained by joining all the vertices of the complete graph $K_t$ to each n vertex of the cycle $C_n$. For any t, we obtain an upper bound of zero forcing number of $L(C_n{\circ}K_t)$, the line graph of $C_n{\circ}K_t$, and get some bounds of $mr(L(C_n{\circ}K_t))$. Specially for t = 1, 2, we have calculated $mr(L(C_n{\circ}K_t))$ by the cut-vertex reduction method.

• Annals of Fuzzy Mathematics and Informatics
• /
• v.16 no.3
• /
• pp.301-316
• /
• 2018

In this paper, the concept of connected geodesic number, $gn_c(G)$, of a fuzzy graph G is introduced and its limiting bounds are identified. It is proved that all extreme nodes of G and all cut-nodes of the underlying crisp graph $G^*$ belong to every connected geodesic cover of G. The connected geodesic number of complete fuzzy graphs, fuzzy cycles, fuzzy trees and of complete bipartite fuzzy graphs are obtained. It is proved that for any pair k, n of integers with $3{\leq}k{\leq}n$, there exists a connected fuzzy graph G : (V, ${\sigma}$, ${\mu}$) on n nodes such that $gn_c(G)=k$. Also, for any positive integers $2{\leq}a<b{\leq}c$, it is proved that there exists a connected fuzzy graph G : (V, ${\sigma}$, ${\mu}$) such that the geodesic number gn(G) = a and the connected geodesic number $gn_c(G)=b$.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1695-1700
• /
• 2005

In this paper, we propose an optimal thresholding method for the voxel coloring in the reconstruction of a 3D shape. Our purposed method is a new approach to resolve the trade-off error of the threshold value on determining the photo-consistency in the conventional method. Optimal thresholding value is decided to compare the surface voxel of photo-consistency with inside voxel on the optic ray of the center camera. As iterating the process of the voxels, the threshold value is approached to the optimal value for the individual surface voxel. And also, graph cut method is reduced to the surface noise on eliminating neighboring voxel. To verify the proposed algorithm, we simulated in the virtual and real environment. It is advantaged to speed up and accuracy of a 3D face reconstruction by applying the methods of optimal threshold and graph cut as compare with conventional algorithms.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.1
• /
• pp.107-113
• /
• 2017

Unlike regular images, there is no ground truth for bio surface images. Result of biosurface imaging is not only significantly affected by the environment and the condition of the bio surface, it requires more detailed expression than regular images. Therefore, unlike algorithms tested on regular images, studies on bio surface images requires a highly precise optimization process. We aim to optimize the graph cut algorithm, known to be the most outstanding among the stereo visions, by considering baseline, lambda, and disparity range. Optimal results were in the range of 1~10 for lambda. The disparity ranged from -30 to -50, indicating an optimal value in a slightly higher range. Furthermore, we verified the tested optimization data using SIFT.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.2
• /
• pp.70-74
• /
• 2017

Given two stereo images of a scene, it is possible to recover a 3D understanding of the scene. This is the primary way that the human visual system estimates depth. This process is useful in applications like robotics, where depth sensors may be expensive but a pair of cameras is relatively cheap. In this work, we combined our interests to implement a graph cut algorithm for stereo correspondence, and performed evaluation against a baseline algorithm using normalized cross correlation across a variety of metrics. Experimental trials revealed that the proposed descriptor exhibited a significant improvement, compared to the other existing methods.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Single-view reconstruction (SVR) is a fundamental method in computer vision. Often used for reconstructing human-made environments, the Manhattan world assumption presumes that planes in the real world exist in mutually orthogonal directions. Accordingly, this paper addresses an automatic SVR algorithm for Manhattan worlds. A method for estimating the directions of planes using graph-cut optimization is proposed. After segmenting an image from extracted line segments, the data cost function and smoothness cost function for graph-cut optimization are defined by considering the directions of the line segments and neighborhood segments. Furthermore, segments with the same depths are grouped during a depth-estimation step using a minimum spanning tree algorithm with the proposed weights. Experimental results demonstrate that, unlike previous methods, the proposed method can identify complex Manhattan structures of indoor and outdoor scenes and provide the exact boundaries and intersections of planes.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.282-285
• /
• 2020

포인트 클라우드는 2D 이미지를 3D 로 복원하고 표현하는 방법으로써 많은 연구가 진행되고 있다. 하지만 포인트 클라우드로만 표현할 경우 포인트와 포인트 사이에 빈 공간이 존재하여 실제 3D 물체와 차이가 존재한다. Mesh Reconstruction 은 보다 실제 3D 물체처럼 보이기 위해 포인트와 포인트를 이어 mesh 를 생성하는 방법인데 생성된 mesh 의 quality 는 texturing 을 거친 최종 결과에 큰 영향을 끼친다. 기존에 존재하는 이미지를 기반으로 생성된 포인트 클라우드의 Mesh Reconstruction 방법은 노이즈에 어느 정도 강한 면을 보이지만 최종 결과에서 잘 이어진 mesh 를 생성하지 못하고 hole 이 존재하는 문제가 있다. 본 논문에선 노이즈에 강하면서 최종 결과에서 잘 이어진 mesh 를 만들 수 있도록 하는 Mesh Reconstruction 알고리즘을 제안한다.

• Journal of Biomedical Engineering Research
• /
• v.38 no.2
• /
• pp.82-88
• /
• 2017

Enlargement of the lateral ventricles have been identified as a surrogate marker of neurological disorders. Quantitative measure of the lateral ventricle from MRI would enable earlier and more accurate clinical diagnosis in monitoring disease progression. Even though it requires an automated or semi-automated segmentation method for objective quantification, it is difficult to define lateral ventricles due to insufficient contrast and brightness of structural imaging. In this study, we proposed a fully automated lateral ventricle segmentation method based on a graph cuts algorithm combined with atlas-based segmentation and connected component labeling. Initially, initial seeds for graph cuts were defined by atlas-based segmentation (ATS). They were adjusted by partial volume images in order to provide accurate a priori information on graph cuts. A graph cuts algorithm is to finds a global minimum of energy with minimum cut/maximum flow algorithm function on graph. In addition, connected component labeling used to remove false ventricle regions. The proposed method was validated with the well-known tools using the dice similarity index, recall and precision values. The proposed method was significantly higher dice similarity index ($0.860{\pm}0.036$, p < 0.001) and recall ($0.833{\pm}0.037$, p < 0.001) compared with other tools. Therefore, the proposed method yielded a robust and reliable segmentation result.