FacultyInformation Science
Teacher OrganizationInformation Science
Education and
 Research Organization
Faculty of Engineering /Graduate School of Engineering
Last Updated: 19/07/23 19:09

Researcher Profile & Settings


    TOKAI Shogo

Profile & Settings


  •  Information Science Professor


  • 1996Nagoya University 情報工学
  • 1991Nagoya University

Academic & Professional Experience

  • Apr. 1996Mar. 2000Kyoto University Research Associate

Association Memberships

    The Society for Art and Science member,

Overseas travel history

  • マレーシア Hotel Equatorial Penang Jan.  2017- Jan. 2017
  • タイ シーナカリンウィロート大学 Sep.  2015- Sep. 2015
  • アメリカ Hilton San Francisco Union Square Hotel Feb.  2015- Feb. 2015
  • 台湾 成功大学 Jan.  2015- Jan. 2015

Research Activities

Published Papers

  • Search Region Correction via Spectrum Domain for Online Visual Tracking
    Hotta, K., Tokai, S., Zhang, C.
    Proceedings of the 6th International Conference on Intelligent Systems and Image Processing (ICISIP) 256-262 Sep.  2018 Refereed
  • Panoramic image generation from a handheld video by combination of attitude sensors and image features
    Shinnosuke Yabuuchi; Shogo Tokai
    Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019 110493T-(5) Mar.  2019 Refereed
  • Remarkable point extraction from overlapping analysis of view fields in multiple smartphones shooting environment
    Shogo Tokai, Fumiaki Motoyama
    Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019 110493F-(5) Mar.  2019 Refereed
  • Realtime Colored Point Cloud Acquisition and Visualization for Wide Area Sports Scene
    Shogo Tokai, Shumpei Uchino
    Proceeding of International Workshop on Advance Image Technology 2017 (IWAIT 2017) OR_165 Jan.  2017 Not refereed
  • ズームカメラを装着した携帯端末の手持ち撮影における映像対の統合処理とその安定化
    ITE Technical Report 40(28) 5-8 Aug.  2016 Not refereed
  • A method of camera-work generation from multiple views for effective scene visualization based on keyframe settings
    Shiori Yamamoto, Shogo Tokai
    IEICE Technical Report 115(505) 55-58 Mar.  2016 Not refereed
  • Frame-wise camera parameter estimation of hand-held video sequence and its multi-view application
    Hiromi Tanabe, Shogo Tokai
    IEICE Technical Report 115(505) 59-62 Mar.  2016 Not refereed
  • Shooting, Processing, Visualization, and Application of Multi-view Videos from Spectators' Smartphones
    Shogo Tokai
    IEICE Technical Report 115(505) 69-74 Mar.  2016 Not refereed
  • D-12-55 A Method for Panoramic Video Browsing from a Handy Camera Video
    Sakamoto Kazumasa;Tokai Shogo
    Proceedings of the IEICE General Conference 2016(2) Mar.  2016 Not refereed
  • D-12-85 A method for depth super resolution combining with a high-res color image
    Uchino Shumpei;Tokai Shogo
    Proceedings of the IEICE General Conference 2016(2) Mar.  2016 Not refereed
  • Improvement of Scene Situation Recognition based on Multiple View Overlapping and its Evaluation
    Fumiaki Motoyama, Shogo Tokai
    IEICE Technical Report 115(348) 47-52 Nov.  2015 Not refereed
  • 多視点ビルボードテクスチャ獲得における被写体領域抽出の改良と考察(若葉研究者の集い5,サマーセミナー2015?実用分野を切り拓き、価値を生み出すビジョン技術?)
    ITE Technical Report 39(30) 61-62 Aug.  2015 Not refereed
  • Rotated Character Recognition over 3,000 Categories with A Few Popular Fonts
    Yuta Baba, Hiroyuki Hase, Shogo Tokai
    IPSJ SIG Technical Report 2015-CVIM-196(10) 1-8 Mar.  2015 Not refereed
  • The Camera Position Alignment on a Gimbal Head for Fixed Viewpoint Swiveling using a Misalignment Model
    Ryosuke Takeba, SHogo Tokai, Kazumasa Sakamoto
    IPSJ SIG Technical Report 2015-CVIM-196(10) 1-7 Mar.  2015 Not refereed
  • A Method of Acquisition of Multi-view Billboard Textures for Free Viewpoint Browsing
    Hiroaki Murakami, Shogo Tokai
    ITE Technical Report 39(8) 79-82 Feb.  2015 Not refereed
  • Camera Model Compensation for Image Integration of Time-of-flight Depth Video and Color Video
    Hiromu Yamashita, Shogo Tokai, Shunpei Uchino
    Proceedings of SPIE-IS&T Electronic Imaging 2015 9393 93930F-(11) Feb.  2015 Refereed
  • The Camera Position Alignment on a Gimbal Head for Fixed Viewpoint Swiveling using a Misalignment Model
    IPSJ SIG Notes. CVIM 2015(10) 1-7 Feb.  2015 Not refereed
    When the camera sets on a gimbal head as a fixed-view-point, it is effective to generate a panoramic image. However if the projection center isn't aligned to the rotation center, the panoramic image contains difference with depth dependencies. By using Zhang's method, camera positions and directions for each swiveling situation are obtained with changing a mounted position of the camera by sliders with swiveling of the gimbal head. A position of the rotation center is estimated from movement of the camera positions. In this paper, we propose a method for it using a misalignment model with only one dimensional changing of the camera position to obtain the two dimentional ideal position for one rotation.
  • Rotated Character Recognition over 3,000 Categories with A Few Popular Fonts
    IPSJ SIG Notes. CVIM 2015(14) 1-8 Feb.  2015 Not refereed
    We proposed a rotated character recognition method using eigen-subspace characterized multiple projection and simple projection so far. In our previous work, a high recognition accuracy over 99.8% was achieved especially by multiple projections of the input rotated images. In this paper, a challenge of rotated character recognition for ideal character images of Japanese Kanji, Hiragana and Katakana with two popular fonts of Mincho and Gothic is presented. First, we obtained very high accuracy and high angle precision for 3,133 Japanese categories of two fonts. Second, this method were tested for not only 2D rotation but also 3D rotation of a character image. As the result, when the angles of X and Y axes were within 6 degrees, we found out that we can get more than 90% of recognition rate. Next, we experimented for camera images, then when the character size is over 45×45 pixels, it is found that we can get a high accuracy like the ideal character image. Next, we applied this method to a rotated document image with a complicated layout. As the result, we obtained a good estimation statistically by voting the recognized angle of a connected component. At last, although the computation time using all dimensions per a character was 0.6[s], the computation time was reduced by decreasing the number of categories using a distance threshold. An advantage of this method is to be obtained the category, the font and the angle at the same time.
  • A Method of Acquisition of Multiview Billboard Textures for Free Viewpoint Browsing
    Murakami Hiroaki;Tokai Shogo
    ITE Technical Report 39(8) 79-82 Feb.  2015 Not refereed
    We acquire figures as textures from multiview videos, and do free view point browsing with them by a billboard method. The figures acquired are selected and switched according to the location of one's eyes. We explain the above method with application example on a sports scene.
  • A Consideration of a Time Management in the Multiple Smartphones Video Shooting System
    Yasuhide Tsuji, Shogo Tokai,
    Proceedings of 2015 International Workshop on Advanced Image Technology (IWAIT2015) 508 Jan.  2015 Not refereed
  • [Paper] Rotated Character Recognition and its Properties
    Baba Yuta;Hase Hiroyuki;Tokai Shogo
    ITE Transactions on Media Technology and Applications 3(1) 22-29 Jan.  2015 Refereed
    We present about a characteristic and the performance of the rotated character recognition using eigen-subspace for Japanese characters of 3,133 categories. At first, a few advantages of recognition experiments by noise-free character images are described. Next, it is shown that the multiple-projection method is more effective than the simple projection in low dimension, also the angle is precisely estimated within ±2 degrees. And the tendency of misclassification is considered for both projection methods. Next, although we use 36 character images as learning data, their sufficiency is shown experimentally. Furthermore, it is shown that very high recognition performance is obtained even when 3,133 Japanese categories of popular Mincho and Gothic fonts are used. Finally, when camera images are used, the deterioration of the recognition performance is improved. Also, it is shown that the inclination angle of a document can be estimated by this method without using layout analysis.
  • Scene Analysis from Viewing Orientations in a Shooting Environment of Multiple Mobile Phones
    TOKAI Shogo;MORIOKA Takayoshi;HASE Hiroyuki
    IEICE Trans. Fundamentals 97(11) 2178-2180 Nov.  2014 Refereed
    We propose a method to extract scene situation by orientation sensors of multiple mobile phones environment. By using orientations recorded with videos, we analyzed their view concentrations as a remarkable position of the scene for each frame of videos. In an experiment for a soccer scene, the extracted points can be related to a trajectory of a soccer ball.
  • A Consideration of Multiple camera calibration with Handheld Operation
    Hiromi Tanabe, Shogo Tokai
    ITE Technical Report 38(39) 13-16 Oct.  2014 Not refereed
  • Virtual Camera-work Synthesis from Multi-view Videos based on Key-frame Configuration
    Shiori Yamamoto, Shogo Ttokai
    ITE Technical Report 38(39) 9-12 Oct.  2014 Not refereed
  • デプスカメラとカラーカメラを併用した3次元情報獲得に関する一考察
    ITE Technical Report 38(39) 41-42 Aug.  2014 Not refereed
  • 手持ち撮影映像からのパノラマ映像合成の一手法
    ITE Technical Report 38(32) 29-30 Aug.  2014 Not refereed
  • Camera-worked Video Generation from Multiple View Videos with Handheld Smart-phones
    Shiori Yamamoto, Shogo Tokai and Hiroyuki Hase
    Proceeding of Nicograph International 2014 101-104 May  2014 Refereed
  • Extraction of Scene Situation from Orientation of Multiple Mobile Terminals in Shooting with Overlaps of Their Views
    Takayoshi Morioka, Shogo Tokai, Hiroyuki Hase
    IEICE Technical Report 113(467) 31-36 Mar.  2014 Not refereed
  • Construction of an Academic Paper Database using a High-resolution Camera and Page Turning Machine
    Y. Tanaka, H.Hase, S.Tokai
     16-19 Jan.  2014 Not refereed
  • Rotated Character Recognition for A Huge Kinds of Categories
    Y. Baba, H.Hase, S.Tokai
     381-386 Jan.  2014 Not refereed
  • Synchronization of Variable Framerate Videos based on Optical Flow Histories
    Y. Nagase, T. Rita, S.Tokai, H.Hase
     89-93 Jan.  2014 Not refereed
  • A Method to Combine Color and Depth Information and Its Application
    H. Yamashita, S.Tokai, H.Hase
     136-141 Jan.  2014 Not refereed
  • A Method to Synthesize Wide Panoramic Video from Multiple View Videos using Billboards
    K. Shimizu, S.Tokai, H.Hase
     599-604 Jan.  2014 Not refereed
  • Construction of Multi-View Synchronized Video Acquisition System Using Android Smartphones and its Evaluation of Synchronization
    K.Shimada, S.Tokai, H. Hase
    The Journal of the Institute of Image Electronics Engineers of Japan 42(3) 384-391 May  2013 Refereed
  • Rotated Kanji Character Recognition
    Yuta Baba, Hiroyuki Hase, Shogo Tokai
    MVA2013 IAPR International Conference on Machine Vision Applications 302-305 May  2013 Refereed
  • Agent-assisted multi-viewpoint video viewer and its gaze-based evaluation
    Takatsugu Hirayama, Takafumi Marutani, Daishi Tanoue, Shogo Tokai, Sidney Fels, and Kenji Mase
    Proceedings of the 6th workshop on Eye gaze in intelligent human machine interaction: gaze in multimodal interaction (GazeIn '13), 29-34 Jan.  2013 Refereed
  • A Method of Camera Position Alignment on a Gimbal Head for Fixed Viewpoint Swiveling
    Ryosuke Takeba, Taku Shibata, S.Tokai, H.Hase
     72-77 Jan.  2013 Not refereed
  • Rotated Japanese Character Recognition
    Y. Baba, H. Hase, S. Tokai
    Proceedings of The 2013 International Workshop on Advanced Image Technology (IWAIT 2013) Jan.  2013 Not refereed
  • A Method of Panoramic Video Generation from a Video Sequence by Mobile Phone Using It's Posture Sensor Information
    Akira Minomo, Shogo Tokai, H. Hase
     86-90 Jan.  2012 Not refereed
  • Multi-view Video Shooting System Using Android Mobile Phones and Its Simultaneous Shooting Control
    K. Shimada, S.Tokai, H.Hase
     100-105 Jan.  2012 Not refereed
  • A Method for Arbitrary View Generation from a Pair of Depth and Video Cameras
    Y. Asayama, S.Tokai, H.Hase
     266-271 Jan.  2012 Not refereed
  • A Method of Pseudo-synchronization for Asynchronous Videos Based on Optical Flow Information
    T. Rita, S.Tokai, H.Hase
     272-276 Jan.  2012 Refereed
  • A Study of Simultaneous Shooting Control for Multi-view Camera System using Mobile Phones
     111(210) 81-86 Sep.  2011 Not refereed
  • Deeper Understanding on Solution Ambiguity by Homography Decomposition
    IASTED Conference on Computer Vision CV2011 Jun.  2011 Refereed
  • Multiple Handy Camera System with 3D Motion Sensors for Supporting 3D TV
    Shogo Tokai
    Asiagraph 2010 Jun.  2010 Not refereed
  • Facial Expression Recognition from 2.5D Partial Face Data by Using Face Plane
    Theekapun Charoenpong, Hiroyuki Hase, Shogo Tokai
    ECTI Trans. On Electrical Eng., Electronics and Communications 8(1) 32-42 Feb.  2010 Refereed
  • Estimation of Viewer's Interests from Multi-point View Browsing Log in Skill Transfer
    Kousuke Niwa, Kenji Mase, Shogo Tokai, Tetsuya Kawamoto
    Intelligent User Interfaces 2010 Feb.  2010 Refereed
  • Peg-scope navigation using high speed multi-view videos for industrial skill-transfer
    Shogo Tokai, Kenji Mase, Tetsuya Kawamoto, Toshiaki Fujii
    International workshop on advanced image technology 2010 (IWAIT2010) S8-3 (p.100 in abstracts) Jan.  2010 Not refereed
  • A Method of Pseudo-synchronization for Asynchronous Multiple Videos
     34(44) 69-72 Jan.  2010 Not refereed
  • On the Solution Ambiguity of Homography Decomposition method for 3D Motion Parameter Estimation
     Nov.  2009 Not refereed
  • 最小自乗距離に基づく平面物体の3次元動き推定方法
    19th Intelligent System Symposium(FAN2009) Sep.  2009 Not refereed
  • On-Body Multi-Sensor Analysis and Evaluation for Manufacturing Skill Training
    Keita Kojima, Kenji Mase, Shogo Tokai, Tetsuya Kawamoto, Toshiaki Fujii
    13th IEEE International Symposium on Wearable Computers (ISWC'09) pp.21-28 Sep.  2009 Refereed
  • 3D Pose Estimation of a Planar Object
    He Liu, Hiroyuki Hase, Shogo Tokai
     Jul.  2009 Not refereed
  • Skill Contents Production based on Peg-Scope Navigation using High Spe ed Multi-view Videos
    Shogo Tokai, Kenji Mase, Tetsuya Kawamoto, Toshiaki Fujii
    Meeting on Image Recognition and Understanding 2009 (MIRU2009) IS3-26 Jul.  2009 Not refereed
  • A Method for 3D Reconstruction from Multidirectional Images using a Microscope with Rotating Mirror Head
    Hiroki Ojima, Shogo Tokai, Yousuke Oota, Hiroyuki Hase
    ITE Tech. Rep. ITE-33(ITE-ME-20,ITE-AIT-20) 42008 May  2009 Not refereed
  • Study of Contents Production based on Peg Scope Navigation Method using High Speed Multi-view Videos
    Shogo Tokai, Kenji Mase, Tetsuya Kawamoto, Toshiaki Fujii
    ITE Tech. Rep. ITE-33(ITE-HI-17) 13-16 Mar.  2009 Not refereed
  • An image alignment tool for flexible multi-camera positioning
    ITE Tech. Rep. ITE-33(ITE-IDY-42,ITE-3DIT-42) 45-48 Jan.  2009 Not refereed
  • Pegged to Point Browsing: An approach to browse multi-view video with view switching, and its applications
    S.Tokai, Kenji Mase, Toshiaki Fujii, Tetsuya Kawamoto
     Dec.  2008 Refereed
  • Multi-font Rotated Character Recognition using Periodicity
    Hiroyuki Hase, Kohei Tanabe, Tran Thi Hong Ha, Shogo Tokai
    8-th IAPR Workshop on Document Analysis Systems(DAS2008) Sep.  2008 Refereed
  • Facial Expression Recognition From Partial Data By Using SVM
    Theekapun Charoenpong, S. Wongwit, Shogo Tokai, Hiroyuki Hase
    3rd Int. Symp. On Biomedical Engineering(ISBME08) Aug.  2008 Refereed
  • 3D Face Reconstruction from 2.5D Partial Face Data
    Theekapun Charoenpong, Shogo Tokai, Hiroyuki Hase
     37(4) 476-485 Jul.  2008 Refereed
  • Facial Expression Recognition from a Partial Face Image by Using Displacement Vector
    T. Charoenpong, 東海彰吾, 長谷 博行
    ECTI-CON2008 May  2008 Refereed
  • A Novel Method of Facial Expression Recognition from a 2.5D Partial Face Data
    Theekapan Charoenpong, 東海彰吾, 長谷 博行
     PRMU2007-318 477-482 Mar.  2008 Not refereed
  • Facial expression recognition from a side view face by using face plane
    charoenpong Theekapun, Shogo Tokai, Hiroyuki Hase
    ICWAPR2007 Nov.  2007 Refereed
  • A Novel Approach of 3D Face Reconstruction using Ellipse Fitting
    MVA2007 528-531 May  2007 Refereed
  • Synthesis arbitrary vvews from two images based on improved view morphing technique
    HungGang Liang, S.Tokai, H.Hase
     203-206 May  2007 Refereed
  • Robust Nose Localization by Using Fitting of Ellipse from 2.5D Image
    Theekapun Charoenpong, 長谷 博行, Shogo Tokai
    IEEE TENCON 2006 PO5.8 Nov.  2006 Refereed
  • Attention Navigation by keeping Screen Layout for Switching Multiple Views
    Shogo Tokai, Hiroyuki Hase
    18th Int.Conf. on Pattern Recognition P-IV-2-40 Aug.  2006 Refereed
  • A Robust Method of Recognizing Multi-font Rotated Characters
    H.Hase, T.Shinokawa, S.Toukai, C.Y.Suen
     CD-ROM 363-366 Aug.  2004 Refereed
  • Color Segmentation for Text Extraction
    H.Hase, M.Yoneda, S.Toukai, J.Kato, C.Y.Suen
     6(4) 271-283 Apr.  2004 Refereed
  • Homography Based Parallel Volume Intersection: Toward Real-Time Volume Reconstruction Using Active Cameras
    T.Wada, X.Wu, S.Tokai, T.Matsuyama
     Sep.  2000 Refereed
  • Active Image Capturing and Dynamic Scene Visualization
    T.Matsuyama, T.Wada, S.Tokai
     Sep.  1998 Not refereed

Conference Activities & Talks

  • Feature Distraction Based Upon Implicit Geometry Information Of Facial Point Cloud
    薛梅, 東海 彰吾, 長谷 博行
    第75回情 報処理学会全国大会 Mar.  2013
  • Research on Local Face Motion in 3D Facial Expression Generation without Mesh
    Mei Xue, S.Tokai, H.Hase
     Jul.  2011
  • 距離測定カメラとビデオカメラを併用したステレオ動画生成の一手法
    浅山能久, 東海 彰吾, 長谷 博行
     Jul.  2011
  • 人物動作を対象とした非同期撮影された多視点映像の擬似同期の一手法
    利田貴人, 東海 彰吾, 長谷 博行
     Jul.  2011
  • Android携帯端末による多視点映像とセンサ情報の取得・収集システム
    嶋田恭兵, 東海 彰吾, 長谷 博行
     Jul.  2011
  • Method of 3D Facial Expression Generation from Point Clouds Based on Segmentation and Interpolation
    Xue Mei, S.Tokai, H.Hase
     Dec.  2010
  • Stability improvement using camera calibration for attention navigation by switching multiple views
    Shogo Tokai, Shouta HIguchi, 長谷 博行
    MIRU2007 Aug.  2007

Management activities information

Free description - Notices registration

  •  2016【委員会担当の漏れ】 ・入試委員会委員(2年任期の1年目) ・FD委員会委員(2年任期の2年目)
  •  2015【委員会担当の漏れ】 ・FD委員会委員(2年任期の1年目)
  •  2006委員などとして大学運営の中心的な管理活動に加わってはいないが、足を引っ張らないようにきを付けていきたい。