In this paper, we propose a system which decides a camera work in 3D virtual space and generates 3DCG animation automatically. The system is called "Data Animating." The system generates 3DCG animation according to user's select of soccer's play event. The 3D virtual space is composed of player position and play event data estimated from soccer footage. We focus on Cinematography and an art of rhetoric of image, and take them to the system. Therefore the system can automate an composition of an animation story and decide an camera work based on the story. The animation story is based on the four - part organization of Chinese poetry. Although the four parts are introduction, development, turn, and, conclusion, the "turn" is not used in the system. And an appropriate camera work is decided in each scenes. Moreover, the camera work considering a picture composition of the screen is decided. In the experimental result, we confirm the system can generate 3DCG animation automatically from user's select scene.

We have developed a robust method for estimating camera parameters for live TV production based on infrared markers whose feature-point extraction is simple and two-dimensional color histogram matching that considers the effects of specular reflection due to lighting. We first explain the principle of the proposed technique. We then present the results of a basic experiment for evaluating the accuracy of marker identification and the results of an image-compositing experiment using estimated camera parameters. We show that the proposed technique is effective based on those results.

When making a TV program in a studio, care must be taken that the camera does not shoot beyond the boundary of the studio set. In addition, limitations in cost and space for the set must be taken into account. In a virtual studio, on the other hand, we can solve this cost and space problem, but in turn, actors are requested to perform in front of a blue background screen, which is not always an easy task for them. To solve these problems associated with real studios and virtual studios, we have developed a new type of virtual studio called Real Space-based Virtual Studio in which a real space image and virtual space image are combined naturally with no boundary seam. There are two major advantages in using this new virtual-real hybrid system. One is that the actors can concentrate on their role in the real studio sets, and the other is that camera work can be done without worrying about off-screen areas of the set. In the present study, we constructed an omnidirectional image with ultra high-definition features and combined it as a virtual studio image with a real studio image. We have developed an integration system and from the experimentation we have shown that the omnidirectional images and the real studio images can combine smoothly and naturally.

We are studying an image-based virtual studio. This type of virtual studio makes it possible to reconstruct realistic synthesized video by extracting shape, texture, and other necessary information (called video components) from each object in the subject video for use on the set. When using video components made up of shape and texture information to reconstruct natural-looking video under any lighting conditions, lighting effects like highlights and shading that are present at the time of measurement must be removed from texture information. For this purpose, the authors have proposed a technique that uses polarized light on the lighting side and a polarized filter on the camera side, and have confirmed its effectiveness by experiments.

Article Evaluating the location of hot spots in interactive scenes using the 3R toolbox Share on Authors: Andre Plante ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, Japan ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, JapanView Profile , Shoji Tanaka ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, Japan ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, JapanView Profile , Seiki Inoue ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, Japan ATR Media Integration & Communications Research Laboratories, 2-2 Hikaridai Seika-cho, Souraku-gun, Kyoto, JapanView Profile Authors Info & Claims CHI '98: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsJanuary 1998 Pages 117–123https://doi.org/10.1145/274644.274662Online:01 January 1998Publication History 4citation259DownloadsMetricsTotal Citations4Total Downloads259Last 12 Months4Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Article Avatar creation using automatic face processing Share on Authors: Michael Lyons ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, JapanView Profile , Andre Plante ATR Media Integration and Communication Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan ATR Media Integration and Communication Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, JapanView Profile , Sebastien Jehan ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, JapanView Profile , Seiki Inoue ATR Media Integration and Communication Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan ATR Media Integration and Communication Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, JapanView Profile , Shigeru Akamatsu ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan ATR Human Information Processing Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, JapanView Profile Authors Info & Claims MULTIMEDIA '98: Proceedings of the sixth ACM international conference on MultimediaSeptember 1998 Pages 427–434https://doi.org/10.1145/290747.290816Online:01 September 1998Publication History 17citation614DownloadsMetricsTotal Citations17Total Downloads614Last 12 Months20Last 6 weeks2 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

In the development of a method of estimating the global camera motion from encoded video, we propose a robust estimation based on an outlier rejection scheme. The extended Kalman filter and the Levenberg-Marquardt method are implemented for the estimation. Both implementations show promising results, but from a computational aspect, the LM method is more efficient than the extended Kalman filter in our implementation.

We propose a method to generate an arbitrary view based on 5 reference views. We attempt to synthesize a new view of best attainable quality given limited information. The method is based on estimation of depth map and successive image warping: transformation of depth map, guessing depth map for uncovered area, and back-mapping using the filled depth map with elaborate check. Uncovered area due to view change is shown to be handled on the basis of observable viewpoint. It is confirmed that a variety of view of acceptable quality can be synthesized efficiently.

This paper presents a method and a prototype system for video browsing to retrieve video data which contains not only images but also text, voices, sounds characters and so on. In this paper, we describe a trial using a video of Noh, which is, a traditional Japanese play, because we could easily obtain Noh videos and text books including scenarios, actions to words, and so on. In addition to these convenient features we could use camera operation of Noh videos for generating index data to retrieve because the main feature of camera operations is to follow a leading Noh player. We developed a prototype system which is able to retrieve a scene by an action name, words, a position on the stage of the Noh video.

Recent advances in computer technology and video technology have made it easy to transmit high-volume multimedia contents. However, high-quality multimedia production requires special knowledge and techniques. We are engaged in research on an environment that can help nonspecialists to create such contents. In this paper we propose a new integrated media handling system COMI&CS (Computer Organized Media Integration and Communication System) and image expression environment IER (Image Expression Room). Those can allows people that do not have expert knowledge on the manipulation of media or the technique of expression to express their images with a high degree of freedom.

Upon viewing a picture, its audience gets an impression of that work. In this case, the picture has certain factors that can affect viewers' impressions, which in Japan are called KANSEI factors. In general, highly attractive regions of a picture have the ability to affect the majority of viewers' impressions. By extracting and analyzing those attractive regions, it becomes possible to predict viewers' impressions within a reasonable error. This paper proposes a method for extracting attractive regions of pictures for analyzing KANSEI factors. It also describes a function for evaluating attractive regions segmented from a picture based on the size and color features of those regions.