AUTHORS: Worawat Choensawat, Sachie Takahashi, Minako Nakamura and Kozaburo Hachimura

ABSTRACT: Labanotation [Hutchinson, 2005] is a graphical notation scheme for describing human body movement that has been widely accepted for the purpose of recording human movements in the fields of choreography and dance education, mainly in Western dance communities. Labanotation is rich in symbols, and by using the full set of symbols almost all of our body movements can be described.

AUTHORS: Worawat Choensawat and Kozaburo Hachimura

ABSTRACT: When producing the animation of a body motion from the dance notation, the dance knowledge is a key for accomplishing high-quality movement. This knowledge enables the dancer to know how to perform the correct movement from a movement notation score. This paper presents an approach for automatically simulating a CG animation from Labanotation scores. We achieve this goal by the integration of a CG animation with a dance-style interpretation module which is called an autonomous dance avatar. In our experiment, we implemented an autonomous dance avatar to perform Japanese stylized traditional dance Noh plays.

AUTHORS: Worawat Choensawat and Kozaburo Hachimura

ABSTRACT: When producing the animation of a body motion from the dance notation, the dance knowledge is a key for accomplishing high-quality movement. This knowledge enables the dancer to know how to perform the correct movement from a movement notation score. This paper presents an approach for automatically simulating a CG animation from Labanotation scores. We achieve this goal by the integration of a CG animation with a dance-style interpretation module and it is called an autonomous dance avatar. In our experiment, we implemented an autonomous dance avatar to perform a Japanese stylized traditional dance such as Noh-Plays. The result shows that the autonomous dance avatar can reproduce

AUTHORS: Worawat Choensawat, Woong Choi and Kozaburo Hachimura

ABSTRACT: In this paper, we propose (1) a method of similarity retrieval of motion capture data in which a new feature extraction technique is introduced for the improvement of similarity search precision, as well as (2) a method to reduce the search time on a large database by using lower bound Dynamic Time Wrapping (DTW). For similarity search, joint speed has been mainly used as features of a particular motion. Our method differs from others in that we use not only the magnitude of speed but also the pattern of speed change. We measure the pattern of changing joint speed in a short period of time with the derivative of joint speed. In our experiments, we found that our

AUTHORS: Worawat Choensawat, Woong Choi, Hiroyuki Sekiguchi and Kozaburo Hachimura

ABSTRACT: Segmentation is a key process of the motion-capture-data retrieval systems, which have been widely used in media technologies. This paper introduces a new method to improve the segmentation accuracy of complex motion data such as dancing. The proposed method is a neural network which is achieved as non-linear classifier in many applications. Use of SMOTE technique can overcome a defective case of neural networks in case the data set is seriously imbalanced. An imbalanced dataset is where the instances of one class far outnumber the other class. In our case, the ratio of segmentation and non-segmentation classes equal to 1:10. Our experimental results show the increasing percentage of both precision

AUTHORS: Kingkarn Sookhanaphibarn, Ruck Thawonmas, Frank Rinaldo and Kuan-Ta Chen

ABSTRACT: Spatiotemporal data displayed in a spatial layout are not the best visualization for simultaneously exploring visitor paths and comparing their residing time. A challenging problem is the visual analytics of circulation patterns in varying layouts commonly found in both real and virtual environments. A circulation pattern is defined as how visitors move within space regarding a sequence of visited items. Understanding and discovering the circulation patterns has received much attention from space designers for increasing visitor satisfaction. This paper proposes a layout-independent visualization approach that transforms the four dimensional data of visitor trajectories (3D-position+ time) into time series data. One time series datum represents

AUTHORS: Worawat Choensawat, Sachie Takahashi, Minako Nakamura and Kozaburo Hachimura

ABSTRACT: We have long been conducting research on the description and reproduction of body motion based on Labanotation, and developed a system called LabanEditor. Labanotation uses a symbolic description and it is said that the notation can even describe motions of the fine each finger of a dancer. However, since, in this case, the resulting score staff will become extremely complicated, only the basic description has usually been used. On the other hand, there are styles of motion particular to traditional dances, and if we restrict ourselves to handling these dances, the basic notation scheme is insufficient to describe these motions. Based on the above, we

AUTHORS: Kingkarn Sookhanaphibarn and Ruck Thawonmas

ABSTRACT: Over two decades, a great expectation on digital museums has been addressed, but most implementation platform has been web technologies. Emerging Second Life which supports rich communication, virtual collaboration, and 3-D content creation has carried out a new platform of digital museums. This paper investigates the requirement of idealized digital museums to improve the percentage of returning visitors and to impress the first-time visitors. The framework for design and evaluation of digital museums in Second Life as learning institutions is elaborated and discussed in the paper.

AUTHORS: Kingkarn Sookhanaphibarn and Ruck Thawonmas

ABSTRACT: Over two decades, a great expectation on digital museums has been addressed but most of them have been implemented based on web technologies. Emerging Second Life, which supports rich communication, virtual collaboration, and 3-D content creation, has brought a new platform to digital museums. As a result, a way to systematically manage and arrange a tremendous amount of information in SL museums is required. In addition, dynamic content and context to encourage audiences to return to the museum more frequently must be designed based on audience drives and preferences. In this paper, a Content Management System (CMS) of digital museums in Second Life is presented to cope with these issues. Six proposed modules are the integral parts of CMS to handle data

AUTHORS: Worawat Choensawat, Woong Choi and Kozaburo Hachimura

ABSTRACT: A similarity retrieval of motion capture data has received substantial attention in recent years. In this paper, we focus on feature extraction and quick filtering methods in the similarity retrieval system. A representation of motion capture data is joint angles, which can distinguish different human body poses. We propose a new technique for dimensionality reduction based the average and variance of joint angles. Our dimensionality reduction is simple to

AUTHORS: Jakarin Smitaveja, Kingkarn Sookhanaphibarn and Chidchanok Lursinsap

ABSTRACT: Face recognition technology has been an increasingly important module in security systems. A challenging problem is how to extract features tolerant to the appearance variables such as changes in shape, illumination, and occlusion. Extracted metrical features of facial caricatures that are combined with their facial photographs in the training set are examined. The facial caricature is a personal representative amplifying perceptually significant information of individuals. Unlike Eigenfaces, Fisherfaces, and Laplacianfaces, the twenty-nine metrical features that used in this study do not depend upon illumination and occlusion variables. Our results show that facial caricature-trained neural networks outperform significantly of those