All issues
Predecessor
39.49
Displaying 1-12 of 12 articles from this issue
- |<
- <
- 1
- >
- >|
-
Article type: Cover
Pages Cover1-
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (10K) -
Article type: Index
Pages Toc1-
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (30K) -
Sho TAKAHASHI, Miki HASEYAMAArticle type: Article
Session ID: ME2015-118
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSThis paper proposes a high performance parallel computing for Active net-based pass region estimation in soccer videos. In the soccer games, since the pass is very useful for analyses of various soccer tactics, the visualization of the pass regions is a very important task. Therefore, the pass region estimation method based on Active net is proposed. However, computation time of the pass region estimation must be reduced. Thus, in this paper, we propose a high performance parallel computing for Active net-based pass region estimation. By utilizing CUDA^<TM> as the computation environment, the high performance parallel computing is realized.View full abstractDownload PDF (694K) -
Sho TAKAHASHI, Miki HASEYAMAArticle type: Article
Session ID: ME2015-119
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSThis paper reports a effectiveness of the estimation method of group advantage in soccer videos. The group advantage represents the degree of team's superiority or inferiority in each group. For this analysis, the proposed method classifies players into some groups. As a result of this classification, the players in one group are closely related in terms of soccer tactics. In this method, the relationship between the players in the groups are analyzed by using player positions. Then, this method estimates group advantages by utilizing the relationship of the players. In the last of this paper, by utilizing the actual soccer videos, we evaluate the estimation method of the group advantage.View full abstractDownload PDF (8782K) -
Yuto IDAKA, Kouya YASUDA, Yihsin HO, Norio TAGAWAArticle type: Article
Session ID: ME2015-120
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSIn basketball analysis, resolution of the occlusion the ball and players is hidden to the other players is important. This study utilizes the image taken from the multi-view at the same time, aiming to avoid occlusions. For photography, it is also added appropriately zooming while changing the orientation of the hand-held video camera. If it is assumed conditions for obtaining appropriate images, for utilization of multiple images, it is necessary to know the position and orientation and zoom of the video camera for each frame.View full abstractDownload PDF (9421K) -
Yuta ONODERA, Satoshi ITO, Yoshifumi YAMADAArticle type: Article
Session ID: ME2015-121
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSCompressed sensing (CS) has inspired significant interest because of its potential to reduce data acquisition time. However, CS reconstruction is an iterative reconstruction technique, especially in 3D image reconstruction so it is more computationally intensive than traditional inverse Fourier reconstruction. In this study, we examine to accelerate the 3D CS reconstruction by using the Graphics Processing Unit (GPU) as a general-purpose use. Experimental results show that CS reconstruction with 256×256×32 images based on Multi-GPU was executed in 11s while CPU computing cost was 478s.View full abstractDownload PDF (10565K) -
Nagatoshi HAYABUSA, Hiroki TAKAHASHIArticle type: Article
Session ID: ME2015-122
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSThis paper aims for down motion evaluations in a hip-hop dance using down motions with rhythms in order to perform a dance well. 20 kinds of human joints are measured by Kintct^<TM> and a down motion rhythm error as a motion information is calculated by time differences of a music beat and a human motion beat. In addition to the down motion rhythm error, 3 dimensional coordinates of a neck, both shoulders, both elbows, a spine, both hips, and both knees at the human motion beat time are calculated for a motion evaluation with SVM (Support Vector Machine) trained down motion information that are preliminarily evaluated by experienced dancers.View full abstractDownload PDF (651K) -
Shouta TSUKADA, Norio TAGAWAArticle type: Article
Session ID: ME2015-123
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSFor the gradient-based shape from motion, relative motions with various directions at every 3-D point on a target object are generally effective for accurate recovery. On the other hand, a proper motion size exists for each 3-D point with the intensity pattern and the depth that varied in each, i.e., too large motion causes a large error in depth recovery as an alias problem, and too small motion is inappropriate at a point of view of SNR. An application of random camera rotations imitating involuntary eye movements of a human eyeball has been proposed, which can generate multiple image pairs. In this study, in order to realize accurate shape recovery, we improve a gradient method based on multiple image pairs by selecting appropriate image pairs to be used. Its effectiveness is verified through experiments using the actual camera system that we developed.View full abstractDownload PDF (11734K) -
Mitsugu KAKUTA, Tadao HAYASHIArticle type: Article
Session ID: ME2015-124
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (306K) -
Article type: Appendix
Pages App1-
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (82K) -
Article type: Appendix
Pages App2-
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (82K) -
Article type: Appendix
Pages App3-
Published: December 03, 2015
Released on J-STAGE: September 22, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (82K)
- |<
- <
- 1
- >
- >|