• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1199-1206
• /
• 2015

This paper introduces an algorithm for computing similarity between two poses in the motion capture data with different scale of skeleton, different number of joints and different joint names. The proposed algorithm first performs the topological analysis on the skeleton hierarchy for classifying the joints into more meaningful groups. The global joints positions of each joint group then are aggregated into a point cloud. The number of joints and their positions are automatically adjusted in this process. Once we have two point clouds, the algorithm finds an optimal 2D transform matrix that transforms one point cloud to the other as closely as possible. Then, the similarity can be obtained by summing up all distance values between two points clouds after applying the 2D transform matrix. After some experiment, we found that the proposed algorithm is able to compute the similarity between two poses regardless of their scale, joint name and the number of joints.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.440-450
• /
• 2001

This paper discusses an effective algorithm which is proposed for abrupt scene change detection in MPEG bitstream. The proposed algorithm restores DC images by decoding only DC coefficients and estimates the new motion vectors between adjacent DC images and detects scene change by similarity measure between frames. The proposed algorithm calculates similarity measure between adjacent frames, i.e motion compensated inter-frame correlation, and detects scene change by comparing this similarity measure with threshold value independent of sequences. Experimental results show that the proposed algorithm has more than 90% \`recall\` and \`precision\` in almost sequences and these results can be considered better than other algorithms using threshold value dependent of sequences.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• 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.

• Journal of Ocean Engineering and Technology
• /
• v.15 no.3
• /
• 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.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2001.05a
• /
• 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.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.305-310
• /
• 2010

In this paper, we propose a heuristic algorithm for motion correspondence based on a point series similarity. A point series is a sequence of points which are sorted in the ascending order of their x-coordinate values. The proposed algorithm clusters the points of a previous frame based on their local adjacency. For each group, we construct several potential point series by permuting the points in it, each of which is compared to the point series of the following frame in order to match the set of points through their similarity based on a proximity constraint. The longest common subsequence between two point series is used as global information to resolve the local ambiguity. Experimental results show an accuracy of more than 90% on two image sequences from the PETS 2009 and the CAVIAR data sets.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.3_1spc
• /
• 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.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• 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
• /
• v.4 no.2
• /
• 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)
• /
• v.7 no.11
• /
• 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.