• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권1호
• /
• pp.52-58
• /
• 2007

본 논문에서는 실내 환경에서 동적 스테레오 카메라(active stereo camera)를 이용한 새로운 인체 실루엣 추출 방법을 제안한다. 제안한 알고리즘의 주된 응용분야는 이동 로봇 플랫폼에서의 인체 실루엣을 이용한 제스처 인식이다. 먼 거리에서 움직이는 객체를 분할(segmentation)하는 데에는 저해상도, 그림자, 스테레오 정합의 불확실성, 배경과 객체의 색 분포의 불안정성 등과 같은 다양한 문제를 내포한다. 우리는 먼저 이미지 분할 기법과 스테레오 정보를 이용하여 신뢰도 높은 객체와 배경 영역을 추정하였다. 이렇게 추정된 영역을 적절히 그래프 컷(graph cut)에 활용하는 방식을 고안함으로써 주변 환경의 변화에 강인한 인체 실루엣 추출을 가능하게 하였다. 제안한 방식은 실내에서 펜-틸트(pan-tilt) 스테레오 카메라로 획득된 비디오 데이타를 대상으로 실험하였으며, 색, 색과 스테레오, 색과 대비 정보를 기반으로 한 방법들과 비교 실험한 결과 정확도가 많이 향상된 것을 확인할 수 있었다.

• 대한전자공학회논문지SP
• /
• 제48권1호
• /
• pp.33-45
• /
• 2011

본 논문에서는 객체의 윤곽선 정보에 기반한 수정된 그래프컷(Graph-cut) 알고리즘을 이용하여 동영상에서 효율적으로 객체를 추출하는 방법을 제안한다. 이를 위해 먼저, 첫 프레임에서 자동 추출 알고리즘 이용하거나 사용자와의 상호작용을 통해 영상에서 객체를 분리한다. 객체의 형태 정보를 상속시키기 위해 이전 프fp임에서 추출된 객체 윤곽선의 움직임을 예측한다. 예측된 윤곽선을 기준으로 블록 단위 히스토그램 역투영(Block-based Histogram Back-projection) 알고리즘을 수행하여 다음 프레임의 각 픽셀에 대한 객체와 배경의 컬러 모델을 형성한다. 또한 윤곽선을 중심으로 전체 영상에 대한 로그함수 기반의 거리 변환 지도(Distance Transform Map)를 생성하고 인접 픽셀간의 연결(link)의 확률을 결정한다. 생성된 컬러 모델과 거리 변환 지도를 이용하여 그래프를 형성하고 에너지를 정의하며 이를 최소화하는 과정을 통해 객체를 추출한다. 다양한 영상들에 대한 실험 결과를 통해서 기존의 객체 추출 방법보다 제안하는 방법이 객체를 보다 정확하게 추출함을 확인할 수 있다.

• 대한수학회논문집
• /
• 제30권2호
• /
• 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
• /
• 제16권3호
• /
• 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
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• 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.

• 전기학회논문지
• /
• 제66권1호
• /
• 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.

• 반도체디스플레이기술학회지
• /
• 제16권2호
• /
• 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
• /
• 제11권1호
• /
• 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.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• 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.

• 대한의용생체공학회:의공학회지
• /
• 제38권2호
• /
• 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.