Papers - Saito, Hideo

Speed up in Computation of HMAX Features for Object Localization

Takuya Minagawa, Hideo Saito

ITE Transactions on Media Technology and Applications 2 ( 1 ) 60 - 73 2014.01

Research paper (scientific journal), Accepted

　View Summary

While HMAX features have been proved to have excellent performance in image categorization tasks, the computational cost of recognition is expensive. If we aim to apply the HMAX features to object localization tasks, in which the categorization tasks are repeatedly performed by sliding windows, their processing time increases enormously. In this paper, we propose a method for speed up in computation of object localization based on HMAX features. We found that the HMAX features cause specific redundancies in the sliding window approach. The speed up is achieved by eliminating the redundancies in our method. The results from experiments using the University of Illinois-Urbana-Champaign (UIUC) car dataset and the face detection dataset benchmark (FDDB) indicate that this modification improved processing speeds significantly with insignificant reductions in precision.

• Access to Document (DOI)

Plane approximation-based approach for 3d reconstruction of ball trajectory for performance analysis in table tennis

Tamaki Sho, Saito Hideo

Advances in Computer Vision and Pattern Recognition 71   47 - 66 2014

Research paper (scientific journal), Joint Work,  ISSN  2191-6586

　View Summary

<p>A plane approximation-based approach for 3D reconstruction of ball trajectory is introduced, which was developed as a solution to the problem with conventional analysis in table tennis. There are methods of reconstructing 2D ball trajectories or 3D trajectories of balls heavier than those in table tennis. However, these methods cannot be adopted to reconstruct the 3D trajectories of table tennis balls, because there are problems that are attributed to the dimensions of the trajectories and weight of the balls. The method proposed in this chapter could reconstruct the 3D trajectories of a table tennis ball. The key feature of the method is that it approximates that a ball is traveling on tilted planes. This approximation makes reconstruction robust against failure to measure 3D ball positions. Two systems were developed based on the new method. A system using two RGB cameras experimentally demonstrated that it could provide accurate information for match analysis. A system using an RGB-D camera was experimentally demonstrated that the system could provide accurate information for service analysis.</p>

• Access to Document (DOI)

A Tracking Method for 2D Canvas in MR-Based Interactive Painting System

Sandy Martedi, Mai Otsuki, Hideo Saito, Maki Sugimoto, Asako Kimura, Fumihisa Shibata

International Conference on Signal-Image Technology & Internet-Based Systems (SITIS2013) (IEEE)     790 - 794 2013.12

Research paper (international conference proceedings), Accepted

　View Summary

We have proposed a mixed reality based painting system. In this paper, we tackle a problem in our previous painting system that fully relies on magnetic sensor that is attached on the canvas, the users needed to detach and attach a sensor on the canvas during painting when they want to switch the canvas. Instead of that, in this paper, we aim to automatically detect the shape of the canvas for registration purpose. Using the shape or region detection method such as MSER (maximally stable extremal regions), we detect and track the shape on the canvas on the captured camera image. We then compute the camera pose for virtually overlay the painting result. Using the brush device, we can draw and paint freely on the tracked canvases. We show that using visual based tracking method, we can generate the equivalent result compared to the result of using the sensor.

• Access to Document (DOI)

Arbitrarily Shaped Objects Relighting Using an RGB-D Camera

Takuya Ikeda, Francois de Sorbier, Hideo Saito

2nd IAPR Asian Conference on Pattern Recognition (ACPR), 2013    631 - 636 2013.11

Research paper (international conference proceedings), Accepted

• Access to Document (DOI)

Detecting Fall Incidents of the Elderly Based on Human-Ground Contact Areas

Dao Huu Hung, Hideo Saito, Gee-Sern Hsu

2nd IAPR Asian Conference on Pattern Recognition (ACPR), 2013    516 - 521 2013.11

Research paper (international conference proceedings), Accepted

• Access to Document (DOI)

パフォーマンス分析への応用を目的とした卓球ボールの3次元軌跡復元システム

SAITO HIDEO

精密工学会誌 79 ( 11 ) 1102 - 1109 2013.11

Research paper (scientific journal), Joint Work, Accepted

Virtual Slicer: Development of Interactive Visualizer for Tomographic Medical Images Based on Position and Orientation of Handheld Device

Sho Shimamura, Motoko Kanegae, Yuji Uema, Masahiko Inami, Tetsu Hayashida, Hideo Saito, Maki Sugimoto

International Conference on Cyberworlds (CW), 2013 (IEEE)     383 - 383 2013.10

Research paper (international conference proceedings), Accepted

• Access to Document (DOI)

Region-based tracking using sequences of relevance measures

SAITO HIDEO

IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2013 (IEEE)     1 - 6 2013.10

Research paper (international conference proceedings), Accepted

　View Summary

We present the preliminary results of our proposal: a region-based detection and tracking method of arbitrary shapes. The method is designed to be robust against orientation and scale changes and also occlusions. In this work, we study the effectiveness of sequence of shape descriptors for matching purpose. We detect and track surfaces by matching the sequences of descriptor so called relevance measures with their correspondences in the database. First, we extract stable shapes as the detection target using Maximally Stable Extreme Region (MSER) method. The keypoints on the stable shapes are then extracted by simplifying the outline of the stable regions. The relevance measures that are composed by three keypoints are then computed and the sequences of them are composed as descriptors. During runtime, the sequences of relevance measures are extracted from the captured image and are matched with those in the database. When a particular region is matched with one in the database, the orientation of the region is then estimated and virtual annotations can be superimposed. We apply this approach in an interactive task support system that helps users for creating paper craft objects.

• Access to Document (DOI)

An Automatic Broadcast System for a Weather Report Radio Program

Hiroyuki Segi, Reiko Takou, Nobumasa Seiyama, Tohru Takagi, Yuko Uematsu, Hideo Saito, Shinji Ozawa

IEEE Transactions on Broadcasting (IEEE)  59 ( 3 ) 548 - 555 2013.09

Research paper (scientific journal), Accepted,  ISSN  0018-9316

• Access to Document (DOI)

From smartphone to virtual window

Zhang, E.; Saito, H. ; De Sorbier, F.

IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2013 (IEEE)     1 - 6 2013.07

Research paper (international conference proceedings), Accepted

　View Summary

We propose a vehicle make and model recognition method for the smart phone, and implemented it onto them. Our method identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the frontal or rear view images. This method enables the users to take the pictures from a certain range of angles. Our method uses SIFT, that has scale and rotation invariance to solve the alignment issue. It creates the pseudo frontal view images by homography matrix and extracts the keypoints. Homography matrix is calculated with the position of the license plate. Our experimental result shows our method enables to recognize up to 60-degree angle.

• Access to Document (DOI)

Vehicle make and model recognition by keypoint matching of pseudo frontal view

Yukiko Shinozuka, Ruiko Miyano, Takuya Minagawa, Hideo Saito

IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2013 (IEEE)     1 - 6 2013.07

Research paper (international conference proceedings), Accepted

　View Summary

We propose a vehicle make and model recognition method for the smart phone, and implemented it onto them. Our method identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the frontal or rear view images. This method enables the users to take the pictures from a certain range of angles. Our method uses SIFT, that has scale and rotation invariance to solve the alignment issue. It creates the pseudo frontal view images by homography matrix and extracts the keypoints. Homography matrix is calculated with the position of the license plate. Our experimental result shows our method enables to recognize up to 60-degree angle.

• Access to Document (DOI)

Reconstruction of 3D Trajectories for Performance Analysis in Table Tennis

Sho Tamaki, Hideo Saito

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 (IEEE)     1019 - 1026 2013.06

Research paper (international conference proceedings), Accepted

　View Summary

A method of reconstructing the 3D trajectories of a table tennis ball is introduced, which was developed to solve the problem with conventional analysis in table tennis. There are several methods of reconstructing 2D ball trajectories or 3D trajectories of balls heavier than those in table tennis. However, these methods cannot be adopted to reconstruct the 3D trajectories of table tennis balls, because there are problems that are attributed to the dimensions of the trajectories and weight of the balls. The method proposed in this paper could reconstruct the 3D trajectories of a table tennis ball. The key feature of the method is that it approximates that a ball is traveling on tilted planes. This approximation makes reconstruction robust against failure to measure 3D ball positions. A system using two RGB cameras was developed based on the new method. The system experimentally demonstrated that it could provide accurate information for match analysis. A system using an RGB-D camera was then developed to optimize usability for practitioners. We experimentally demonstrated that the system could provide accurate information for service analysis.

• Access to Document (DOI)

Displayed Object Recognition for Smartphone Interaction

Karim Kadar, Francois de Sorbier, Hideo Saito

13th IAPR International Conference on Machine Vision Applications (MVA 2013)    105 - 108 2013.05

Research paper (international conference proceedings), Joint Work, Accepted

A Training Support System for Table Tennis Service using Kinect

Tamaki Sho, Nakamura Jun, Saito Hideo

The 13th ITTF Sports Science Congress  2013.05

Research paper (international conference proceedings), Joint Work, Accepted

Illumination Estimation from Object Shadow and Incomplete Object Shape Information Captured by an RGB-D Camera

Ikeda Takuya, Oyamada Yuji, Sugimoto Maki, Saito Hideo

The journal of the Institute of Image Information and Television Engineers (社団法人 映像情報メディア学会)  67 ( 4 ) J124-J133 2013.03

Research paper (scientific journal), Joint Work, Accepted,  ISSN  13426907

Feature-based Alignment Method for Projecting Virtual Content on a Movable Paper Map

Sandy Martedi, Maki Sugimoto, Hideo Saito, Bruce Thomas

IEEJ Trans. on Electronics, Information, and Systems (電気学会)  133 ( 3 ) 672-679 2013.03

Research paper (scientific journal), Joint Work, Accepted

Stable Keypoint Recognition using Viewpoint Generative Learning

Takumi Yoshida, Hideo Saito, Masayoshi Shimizu and Akinori Taguchi

the International Conference on Computer Vision Theory and Applications(VISAPP2013) (The Institute for Systems and Technologies of Information, Control and Communication (INSTICC))  2   310 - 315 2013.02

Research paper (international conference proceedings), Joint Work, Accepted

　View Summary

We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local
features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when
the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning.
By generating various patterns as seen from different viewpoints and collecting local invariant features, our
system can learn feature descriptors under various camera poses for each keypoint before actual matching. Ex-
perimental results comparing usual local feature matching or patch classification method show both robustness
and fastness of learning.

A Mobile AR System for Sports Spectators using Multiple Viewpoint Cameras

Ruiko Miyano, Takuya Inoue, Takuya Minagawa, Yuko Uematsu, Hideo Saito

the International Conference on Computer Vision Theory and Applications(VISAPP2013) (The Institute for Systems and Technologies of Information, Control and Communication (INSTICC))  1   23 - 32 2013.02

Joint Work, Accepted

　View Summary

In this paper, we aimto develop an AR system which supports spectators who are watching a sports game using
smartphones in a spectators’ stand. The final goal of this system is that a spectator can watch information of
players through a smartphone and share experiences with other spectators. For this goal, we propose a system
which consists of smartphones and fixed cameras. Fixed cameras are set to cover the whole sports field and
used to analyze players. Smartphones held by spectators are used to estimate positions where they are looking
on the sports field. We built an AR system which makes annotation of players’ information onto a smartphone
image. And we evaluated the accuracy and the processing time of our system and revealed its practicality.

Non-rigid Surface Tracking for Virtual Fitting System

Naoki Shimizu, Takumi Yoshida, Tomoki Hayashi, Francois de Sorbier, Hideo Saito

the International Conference on Computer Vision Theory and Applications(VISAPP2013) (The Institute for Systems and Technologies of Information, Control and Communication (INSTICC))  2   12 - 18 2013.02

Research paper (international conference proceedings), Joint Work, Accepted

　View Summary

In this paper, we describe a method for overlaying a texture onto a T-shirt, for improving current virtual fitting
system. In such systems, users can try on clothes virtually. In order to realize such a system, a depth camera
has been used. These depth cameras can capture 3D data in real time and have been used by some industrial
virtual cloth fitting systems. However, these systems roughly, or just do not, consider the shape of the clothes
that user is wearing. So the appearance of these virtual fitting systems looks unnaturally. For a better fitting,
we need to estimate 3D shape of cloth surface, and overlay a texture of the cloth that the user wants to see
onto the surface. There are some methods that register a 3D deformable mesh onto captured depth data of a
target surface. Although those registration methods are very accurate, most of them require large amount of
processing time or either manually-set markers or special rectangles. The main contribution of our method is
to overlay a texture onto a texture of T-shirt in real-time without modifying the surface.

The Estimation of Heights and Occupied Areas of Humans from Two Orthogonal Views for Fall Detection

Dao Huu Hung and Hideo Saito

IEEJ Trans. on Electronics, Information, and Systems (電気学会)  133 ( 1 ) 117-127 2013.01

Research paper (scientific journal), Joint Work, Accepted