Free-Viewpoint Video


Reserch
figure summary


kasuya http://www.image.esys.tsukuba.ac.jp/wp-content/uploads/2014/02/kasuya.png 742w" sizes="(max-width: 300px) 100vw
300px" />

This paper proposes a method to estimate the trajectories of soccer players by using two cameras set in a large-scale outdoor space such as a soccer stadium, which is normally not advantageous for image processing. We estimate a player's position as the intersection of the primary axes of two body regions, corresponding to the two cameras, and a shadow region on the surface of the field. By projecting the foreground silhouette regions extracted from both cameras' images onto the soccer field, each player's body region and its shadow region are identified. Furthermore, our method utilizes color information of the players' uniforms to improve the accuracy of object tracking. We have applied our proposed method to a real soccer game held in a soccer stadium and demonstrated its effectiveness.

Nozomu Kasuya,Itaru Kitahara,Yoshinari Kameda,Yuichi Ohta,Robust Trajectory Estimation of Soccer Players by Using Two Cameras ; Proceedings of the 19th International Conference on Pattern Recognition (ICPR2008),pp.4pages (2008.12)

自由視点映像技術を用いたサッカーシーンの選手視点映像生成、糟谷望・北原 格・亀田能成・大田友一,信学会2009年総合大会講演論文集 D-12-106,(2009) [電子情報通信学会,平成21年度学術奨励賞]


watanabe http://www.image.esys.tsukuba.ac.jp/wp-content/uploads/2014/02/watanabe.jpg 881w" sizes="(max-width: 300px) 100vw
300px" />

This paper proposes an interface for capturing the 3D free-viewpoint video of a soccer game by using bimanual operation. Users virtually capture 3D free-viewpoint video by observing a virtualized miniature soccer stadium on a tabletop. To exploit the human hand's dexterous manipulation ability, we use a 3D tracker to input the 3D position and the orientation of a virtual camera that captures the 3D free-viewpoint video. The proposed system displays the overhead-view on a tabletop where a user manipulates the virtual camera. By browsing this overhead-view, the context can be easily understood (e.g., positions of players and the ball) in a virtualized soccer scene. We develop a proposed system and conduct on evaluations to confirm the effectiveness of our proposed method.

Tetsuya Watanabe,Itaru Kitahara,Yoshinari Kameda,Yuichi Ohta,3D Free-Viewpoint Video Capturing Interface By Using Bimanual Operation; Proceedings of 3DTV Conference 2010,pp.4 pages (2010.6)


kashiwakuma http://www.image.esys.tsukuba.ac.jp/wp-content/uploads/2014/02/kashiwakuma.png 438w" sizes="(max-width: 300px) 100vw
300px" />

This paper introduces a 3D free-viewpoint video-browsing interface that applies multi-touch manipulation to virtual camera control. It is difficult for general users to browse 3D free-viewpoint video because they are not accustomed to controlling a virtual camera from a free-viewpoint perspective. We focus on the multi-touch interface installed in tablet PCs as an input device, which has become a popular interface thanks to its easy and intuitive manipulation. We conduct subjective evaluations to define suitable gestures for virtual camera control. The results reveal which multi-touch gestures users tend to prefer for controlling a virtual camera.

Junya Kashiwakuma,Itaru Kitahara,Yoshinari Kameda,Yuichi Ohta,A Virtual Camera Controlling Method Using Multi-Touch Gestures for Capturing Free-viewpoint Video; 11th European Interactive TV Conference ,pp.67-74 (2013.6) [Best Paper Honorable Mention Award]


yamagiri http://www.image.esys.tsukuba.ac.jp/wp-content/uploads/2014/02/yamagiri.png 587w" sizes="(max-width: 300px) 100vw
300px" />

Abstract.This paper discusses body motion design to maneuver a virtual camera in 3D soccer game where people want to move and rotate the camera three dimensionally.We propose to select four body motions each of which is assigned to a typical camera-work.These four body motions easily remind people their associated camera controls intuitively and naturally.Since the four popular camera-works we take up in this paper are going straight,making turn,tilting up/down,and climbing up/down,we selected stamping,twisting,leaning back/bending ,and crawling as natural body motions. We have implemented body motion estimation method by Microsoft Xbox Kinect and succeeded in maneuvering the virtual camera over a soccer game. We bave conducted a survey on preferred body motions can be verified.We also conducted an experiment of browsing soccer games by the proposed method and obtained subjective scores from participants.

Yasushi Yamagiri,Itaru Kitahara,Yoshinari Kameda,Yuichi Ohta,“Body Motion Design for Maneuvering a Virtual Camera in 3D Soccer Game”,The 23rd International Conference on Artificial Reality and Telexistence (ICAT2013),2013. 12. 11-13. (ICAT2013,Tokyo,Japan)


shuttle3Dresult http://www.image.esys.tsukuba.ac.jp/wp-content/uploads/2014/02/shuttle3Dresult.png 836w" sizes="(max-width: 300px) 100vw
300px" />

Abstract. To build a robust visual tracking method it is important to consider issues such as low observation resolution and variation in the target object's shape. When we capture an object moving fast in a video camera motion blur is observed. This paper introduces a visual trajectory estimation method using blur characteristics in the 3D space. We acquire a movement speed vector based on the shape of a motion blur region. This method can extract both the position and speed of the moving object from an image frame, and apply them to a visual tracking process using Kalman filter. We estimated the 3D position of the object based on the information obtained from two different viewpoints. We evaluated our proposed method by the trajectory estimation of a badminton shuttlecock from video sequences of a badminton game.

Hidehiko Shishido,Itaru Kitahara,Yoshinari Kameda,Yuichi Ohta,“A Trajectory Estimation Method for Badminton Shuttlecock Utilizing Motion Blur” 6th Pacific Rim Symposium on Image and Video Technology (PSIVT2013),Oct,2013 2013.10.28-11.1 Guanajuato,Mexico PSIVT2013,LNCS 8333,pp.325-336. Springer,Heidelberg (2014)