ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
Search
Advanced search
OR
Browse
Search
40.43 Media Engineering(ME)
Displaying 1-11 of 11 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • Media Engineering(ME)
    Pages Cover1-
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_Cover1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (113K)
  • Contents
    Pages Cover2-
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_Cover2
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (104K)
  • Action detection for concentration degree estimation of TV viewer
    Yu INOUE, Masaki HAYASHI, Yosimitsu AOKI
    Session ID: ME2016-125
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In recent years, the demand to an internal state of the person estimate technology increases. The non-contact type technique to estimate internal state of in particular is expected in application to purchasing action analysis and human-robot interactive. In this suggestion, I think it to become available as useful information in CM or improvement of the program contents production by understanding a view state of the TV viewer. Unlike daily action recognition, I classify pose of TV viewer by learning joint coordinate of the spine with a Support Vector Machine and detect action of TV viewer by identifying sub-interval with the maximum score of classifier learned with joint coordinates, joint angles and object information around the hand of the upper body because it is thought that they are necessary to estimate a concentration degree of TV viewer.
    View full abstract
    Download PDF (1029K)
  • Effect of Selective Use of Image Pairs for Motion Stereo Based on Fixational Eye Movements
    Ryuki TOSHIMA, Yihsin HO, Kan OKUBO, Norio TAGAWA
    Session ID: ME2016-126
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_5
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    For 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. Additionally, we examined the selective use of the image pairs for depth recovery to improve the accuracy. The evaluation value for the selection seems to be intuitive and qualitative. In this study, we study a new evaluation value based on the approximation error of optical flow cased by first order approximation in the gradient equation. Its effectiveness is verified through experiments using the actual camera system.
    View full abstract
    Download PDF (732K)
  • A Study on Detection of Similar Scenes based on Pass Regions in Soccer Videos
    Sho TAKAHASHI, Miki HASEYAMA
    Session ID: ME2016-127
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_9
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper proposes a pass region-based method for detecting similar scenes 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. Generally, since the tactics are defined by the formation of players, in the case of same tactic in two soccer scenes, the pass course is considered to be similar. Therefore, in this paper, we propose a detection method of similar scenes by utilizing the pass regions in soccer videos.
    View full abstract
    Download PDF (411K)
  • Camera Pose Measurement using Straight Lines on Court for Recording Basketball Game
    Yuto IDAKA, Kouya YASUDA, Yihsin HO, Kan OKUBO, Norio TAGAWA
    Session ID: ME2016-128
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_13
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In basketball analysis, a ball and players are often hidden by other players, which is called an occlusion, and such a condition is important to be solved. Therefore, we use image sequences taken from multi-views at the same time to avoid the occlusion and to obtain 3D information of a ball and players. When we suppose to record scenes of a game under a good condition by moving hand-held video cameras with adjusting zoom, we have to know the position and the pose of each camera so as to use a multi-view analysis system. In this study, we focus on the pose, i.e. the direction of the camera, and propose a measuring system. Its effectiveness is confirmed through experiments.
    View full abstract
    Download PDF (796K)
  • Support image training for sports
    Takeo ISHII, Asato OKAMURA, Masaki Hayashi, Ryunosuke Kurose, Yosh ...
    Session ID: ME2016-129
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_17
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    We developed a low-effort and -time body motion analysis system utilizing home-use digital video camera. Inputting the movie of sports motion and performance data into the system, image processing and statistical processing were automatically carried out and the postures that improve performance were instantly displayed. We believe that this system is useful for players to improve motion with image training because posture information that affects the performance is displayed instantly and visually. We present a newly developed system of motion analysis using tennis serve of a University tennis player as an example. As a result, the subject continued his serve practice with image training using this system and improved his performance of serve control.
    View full abstract
    Download PDF (555K)
  • Pose trend analysis in tennis video based on pose estimation
    Ryunosuke KUROSE, Masaki HAYASHI, Takeo ISHII, Asato OKAMURA, Yosh ...
    Session ID: ME2016-130
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_21
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Recently, demand for sports video analysis is increasing, for example, analysis of players and teams. In this paper, we focus on Tennis videos. First, we estimate joint positions using Convolutional Pose Machine. Second, we classify similar actions into the same class. Third, we compare behaviors in the same class. Our method can visualize clustering result to grasp detailed difference between similar behavior.
    View full abstract
    Download PDF (2359K)
  • A Proposal of the Gripping Object Enhancement in Sports Video
    Saki MIYASHITA, Mitsuo YOSHIDA, Kyoji UMEMURA
    Session ID: ME2016-131
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_25
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In this study, we have developed a system where users can select the angle of the video and where the gripping object is enhanced. At First, we record points in video with 3-dimensional position and we generate the gripping object enhancement. Next, we generate videos from multiple angles using the points. Finally, a specialized browser of the videos shows the video from the desired angle to user. We have conducted an experiment to verify the effectiveness the generated videos.
    View full abstract
    Download PDF (553K)
  • Development and application of an immediate feedback system for speed skating trajectory
    Toshiharu YOKOZAWA, Hironobu TAKAHASHI
    Session ID: ME2016-132
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_29
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    We developed an immediate feedback system to measure skaters’ trajectory and velocity during speed skating, which can automatically identify the skater with template matching method using 28 cameras mounted on the ceiling of oval. We have measured in many events and during training and utilized for enhancement of the skaters’ performance. The system has many advantages such as no stress for skaters, possible to measure in official events because it need not attach anything to the skaters, and high accuracy.
    View full abstract
    Download PDF (965K)
  • Media Engineering(ME)
    Pages 34-
    Published: 2016
    Released on J-STAGE: January 16, 2020
    DOIhttps://doi.org/10.11485/itetr.40.43.0_34
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (131K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top