• 한국정보통신학회논문지
• /
• 제19권5호
• /
• pp.1199-1206
• /
• 2015

본 논문은 위상분석 기법을 이용하여, 스켈레톤의 크기, 조인트의 개수, 조인트 이름이 다른 모션들에 대한 유사도를 자동으로 계산하는 알고리즘을 제안한다. 제안하는 알고리즘은 스켈레톤의 계층구조와 기본포즈를 분석하여 k 개의 조인트 그룹으로 자동 분류하며, 분류된 조인트 그룹은 조인트의 전역 위치를 이용한 포인트 클라우드로 변환된다. 이 때, 비교 대상이 되는 각 그룹의 포인트 클라우드 내 포인트의 위치는 스켈레톤의 크기를 고려하여 자동으로 조정되며, 포인트 개수 또한 자동으로 일치하게 된다. 비교 대상이 되는 두 포인트 클라우드들은 유사도 계산을 위해 거리 값을 최소로 하는 최적의 2D변환 행렬을 구하게 되며, 이 행렬을 적용 후 나타나는 포인트 간의 거리의 합을 최종 유사도 값으로 결정한다. 실험을 통해, 제안하는 알고리즘은 스켈레톤의 크기, 조인트의 개수, 조인트 이름에 상관없이 유사도 값을 계산해 줌을 알 수 있었다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제7권5호
• /
• pp.440-450
• /
• 2001

본 논문에서는 MPEG 비디오의 급진적 장면전환검출을 위한 효과적인 알고리즘을 제안한다. 제안된 알고리즘은 각 프레임들의 DC 계수만을 디코딩하여 DV 영상을 추출한다. 그리고 두 DC 영상 사이에서 움직임 예측을 시행함으로써 크기가 줄어든 DC 영상에 적합한 움직임 벡터를 찾아내며, 얻어진 DC 영상과 움직임 벡터를 이용하여 프레임 사이의 유사도 측정치를 구함으로써 장면전환을 검출한다. 본 논문에서 제안하는 알고리즘은 인접한 프레임 사이의 유사도 측정치, 즉 움직임 보상된 프레임간 상관계수를 계산하고 이를 시퀀스에 관계없이 동일한 값을 가지는 임계값과 비교함으로써 장면전환을 검출한다. 실험 겨로가, 제안된 알고리즘은 대부분의 시퀀스에서 90% 이상의 ‘recall’과 ‘precision’을 나타내었으며 시퀀스에 따라 서로 다른 임계값을 사용하는 기존의 알고리즘들보다 더 좋은 결과를 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2851-2865
• /
• 2014

To improve the rate-distortion performance of distributed video compressive sensing (DVCS), the adaptive sparse basis and nonlocal similarity of video are proposed to jointly reconstruct the video signal in this paper. Due to the lack of motion information between frames and the appearance of some noises in the reference frames, the sparse dictionary, which is constructed using the examples directly extracted from the reference frames, has already not better obtained the sparse representation of the interpolated block. This paper proposes a method to construct the sparse dictionary. Firstly, the example-based data matrix is constructed by using the motion information between frames, and then the principle components analysis (PCA) is used to compute some significant principle components of data matrix. Finally, the sparse dictionary is constructed by these significant principle components. The merit of the proposed sparse dictionary is that it can not only adaptively change in terms of the spatial-temporal characteristics, but also has ability to suppress noises. Besides, considering that the sparse priors cannot preserve the edges and textures of video frames well, the nonlocal similarity regularization term has also been introduced into reconstruction model. Experimental results show that the proposed algorithm can improve the objective and subjective quality of video frame, and achieve the better rate-distortion performance of DVCS system at the cost of a certain computational complexity.

• 한국해양공학회지
• /
• 제15권3호
• /
• pp.134-141
• /
• 2001

An experimental method to investigate the dynamic characteristics of buoys in extreme environmental condition is established. Because the buoy model requires a resonable size for accurate experiment, the test condition in model basin that satisfies the similarity law is hardly compatible with capability of test facilities. It is suggested that the linear wave component that is unable to satisfy similarity is separated with others. The model experiment is carried out with mitigated condition for the linear wave components while others including wave drift, current and wind are keeping the similarities. Then, the result can be extrapolated to give the dynamic behavior of buoys n extreme condition because linear wave component is solely responsibly to oscillatory buoy motion and other environmental components are applied as a initial tension. The similarity for current and wind conditions is viewed as equivalence of restoring forces. The validity of proposed method is examined with different types of standard ocean buoys and it indicates that the linearity of measured characteristics is assured with a limitation of resonable distance between test and estimated wave conditions.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2001년도 춘계학술대회 논문집
• /
• pp.208-215
• /
• 2001

An experimental method to investigate the dynamic charasteristics of buoys in extreme environmental condition is established. Because the buoy model requires a resonable size for accurate experiment, the test condition in model basin that satisfies the similarity law is hardly met with capability of test facilities. It is suggested that the linear wave component that is unable to satisy similarity is separated with others. The model experiment can be carried out with mitigated condition for the linear wave components while others including wave drift, current and wind are keeping the similarities. Then the result is extrapolated to give the dynamic behavior of buoys in extreme condition because linear wave component is soley responsible to oscillatory buoy motion and other environmental components are applied as a initial tension. the similarity for current and wind conditions is viewed as equivalence of restoring forces. the validity of proposed method is examined with different types of standard ocean buoys and it indicates that the linearity of measured characteristics is assured with a limitation of resonable distance between test and estimated wave conditions.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권4호
• /
• pp.305-310
• /
• 2010

본 논문에서는 점 계열 유사도에 기반하여 모션 대응에 대한 휴리스틱 알고리즘을 제안한다. 점 계열은 x좌표를 기준으로 하여 오름 차순으로 정렬된 일련의 점 들의 리스트이다. 본 연구에서는 국부근접성에 기반하여 현재 프레임 전 프레임의 점들을 클러스터링 하고, 각 그룹에 있는 점 들의 순서를 변경해 가면서 여러 개의 가상 점 계열들을 구성하며, 가상 점 계열은 근접 제약조건에 근거한 유사도를 이용하여 현재 프레임의 점 계열과 정합한다. 국부적 애매함을 해결하기 위해 두 개 점 계열간의 가장 긴부분 문자열을 찾는 방법이 전체적인 정보로 사용된다. PETS2009과 CAVIAR데이터 집합들과 같은 다양한 영상 이미지 시퀀스에 대해 본 연구의 모션 대응 알고리즘은 90%이상의 정확도를 보여준다.

• 한국생산제조학회지
• /
• 제22권3_1spc호
• /
• pp.558-565
• /
• 2013

This paper describes a whole-body (human body's) motion generation scheme for an android robot that uses motion capture device and a nonlinear constrained optimization method. Because the captured motion data are based on global coordinates and the actors have different heights and different upper-lower body ratios, the captured motion data cannot be used directly for a humanoid robot. In this paper, we suggest a method for obtaining robot joint angles, which allow the resultant robot motion to be as close as possible to the captured human motion data, by applying a nonlinear constrained optimization method. In addition, the results are animated to demonstrate the similarity of the motions.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 추계 학술발표회 논문집
• /
• pp.1-8
• /
• 2003

The traffic patterns of today's IP networks exhibit two important properties: self-similarity and long-range dependence. The fractional Brownian motion is widely used for representing the traffic model with the properties. We consider a single server fluid queueing system with input process of a fractional Brownian motion type. Formulas for effective bandwidth are derived in a single source and multiple source cases.

• International Journal of Contents
• /
• 제4권2호
• /
• pp.24-28
• /
• 2008

In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio-temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.