loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Affiliation

Tokyo Metropolitan University, Japan
Context (please use complete words only)
Field
Sort by

19 Papers

Efficient 3D Human Pose and Shape Estimation Using Group-Mix Attention in Transformer Models

Topics: Image-Based Modeling and 3D Reconstruction; Deep Learning for Visual Understanding ; 3D Deep Learning

Authors: Yushan Wang 1 , Shuhei Tarashima 2 ; 1 and Norio Tagawa 1

Affiliations: 1 Faculty of Systems Design, Tokyo Metropolitan University, Tokyo, Japan , 2 Innovation Center, NTT Communications Corporation, Tokyo, Japan

Digital Object Identifier: 10.5220/0013306400003912

Proceedings of VISAPP 2025, ISBN: 978-989-758-728-3

Collapse Button Quick Abstract
: Fully-transformer frameworks have gradually replaced traditional convolutional neural networks (CNNs) in recent 3D human pose and shape estimation tasks, especially due to its attention mechanism that can capture long-range and complex relationships between input tokens, surpassing CNN’s representation capabilities. Recent attention designs have reduced the computational complexity of transformers in core computer vision tasks like classification and segmentation, achieving extraordinary strong results. However, their potential for more complex, higher-level tasks remains unexplored. For the first time, we propose to integrate the group-mix attention mechanism to 3D human pose and shape estimation task. We combine token-to-token, token-to-group, and group-to-group correlations, enabling a broader capture of human body part relationships and making it promising for challenging scenarios like occlusion+blur. We believe this mix of tokens and groups is well suited to our task, where we need to learn the relevance of various parts of the human body, which are often not individual tokens, but larger in scope. We quantitatively and qualitatively validated our method successfully reduces the parameter count by 97.3% (from 620M to 17M) and the FLOPs count by 96.1% (from 242.1G to 9.5G), with a performance gap of less than 3%.

RacketDB: A Comprehensive Dataset for Badminton Racket Detection

Topics: Machine Learning Technologies for Vision; Features Extraction; Object Detection and Localization; Deep Learning for Visual Understanding

Authors: Muhammad Haq 1 ; 2 , Shuhei Tarashima 3 and Norio Tagawa 1

Affiliations: 1 Faculty of Systems Design, Tokyo Metropolitan University, Tokyo, Japan , 2 Department of Information Technology, Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia , 3 Innovation Center, NTT Communications Corporation, Tokyo, Japan

Digital Object Identifier: 10.5220/0013159700003912

Proceedings of VISAPP 2025, ISBN: 978-989-758-728-3

Collapse Button Quick Abstract
In this paper, we present RacketDB, a specialized dataset designed to address the challenges of detecting badminton rackets in images. This task often hindered by the lack of dedicated datasets. Existing general-purpose datasets fail to capture the unique characteristics of badminton rackets. RacketDB includes 16,608 training images, 3,175 testing images, and 2,899 validation images, all meticulously annotated to enhance object detection performance for sports analytics. To evaluate the effectiveness of RacketDB, we utilized several established object detection models, including YOLOv5, YOLOv8, DETR, and Faster R-CNN. These models were assessed based on metrics like mean average precision (mAP), precision, recall, and F1. Our results demonstrate that RacketDB significantly improves detection accuracy compared to general datasets, highlighting its potential as a valuable resource for developing advanced sports analytics tools. This paper provides a detailed description of RacketDB, the evaluation process, and insights into its application in enhancing automated detection in badminton. The dataset is available at https://github.com/muhabdulhaq/racketdb.

On Computing Three-Dimensional Camera Motion from Optical Flow Detected in Two Consecutive Frames

Topics: Stereo Vision and Structure from Motion; Optical Flow and Motion Analyses

Authors: Norio Tagawa and Ming Yang

Affiliation: Graduate School of Systems Design, Tokyo Metropolitan University, 6-6 Asahigaoka, Hino, Tokyo, Japan

Digital Object Identifier: 10.5220/0011785300003417

Proceedings of VISAPP 2023/VISIGRAPP, ISBN: 978-989-758-634-7

Collapse Button Quick Abstract
This study deals with the problem of estimating camera motion from optical flow, which is the motion vector between consecutive frames. The problem is formulated as a geometric fitting problem using the values of the depth map as the nuisance parameters. It is a problem whose maximum likelihood estimation does not satisfy the Cramer–Rao lower bound, and it has long been known as the Neyman–Scott problem. One of the authors previously proposed an objective function for this problem that, when minimized, yields an estimator with less variance in the estimation error than that obtained by maximum likelihood estimation. The author also proposed linear and nonlinear optimization methods for minimizing the objective function. In this paper, we provide new knowledge on these methods and evaluate their effectiveness by examining methods with low estimation error and low computational cost in practice.

Characteristics of Minimum Variance Beamformer for Frequency and Plane-wave Compounding

Topics: Image Formation, Acquisition Devices and Sensors; Medical Image Applications

Authors: Ryoya Kozai 1 , Norio Tagawa 1 , Masasumi Yoshizawa 2 and Takasuke Irie 1 ; 3

Affiliations: 1 Electrical Engineering and Computer Science, Tokyo Metropolitan University, Hino-shi, Tokyo, Japan , 2 Tokyo Metropolitan College of Industrial Technology, Arakawa-ku, Tokyo, Japan , 3 Microsonic Co. Ltd., Kokubunji-shi, Tokyo, Japan

Digital Object Identifier: 10.5220/0010300404230430

Proceedings of VISAPP 2021/VISIGRAPP, ISBN: 978-989-758-488-6

Collapse Button Quick Abstract
Recently, coherent plane-wave compounding (CPWC) that achieves high spatiotemporal resolution has been studied actively as a spatial compounding beamformer. Further, various frequency compounding methods have been proposed for reducing speckle noise. We already proposed the method called frequency and plane-wave compounding minimum variance distortionless response (FPWC-MVDR), which achieves high spatial resolution imaging by simultaneously optimizing frequency and spatial compounding based on minimum variance scheme. In the algorithm of this method, the data-compounded-on-receive MVDR (DCR-MVDR) principle developed for CPWC is extended and applied. In this study, we analyze the features and characteristics of FPWC-MVDR and the weaknesses to be solved in the future through experiments.

Player Tracking using Multi-viewpoint Images in Basketball Analysis

Topics: Entertainment Imaging Applications; Object Detection and Localization; Tracking and Visual Navigation

Authors: Shuji Tanikawa and Norio Tagawa

Affiliation: Graduate School of Systems Design, Tokyo Metropolitan University, Hino, Tokyo 191-0065, Japan

Digital Object Identifier: 10.5220/0009097408130820

Proceedings of VISAPP 2020/VISIGRAPP, ISBN: 978-989-758-402-2

Collapse Button Quick Abstract
In this study, we aim to realize the automatic tracking of basketball players by avoiding occlusion of players, which is an important issue in basketball video analysis, using multi-viewpoint images. Images taken with a hand-held camera are used, to expand the scope of application to uses such as school club activities. By integrating the player tracking results from each camera image with a 2-D map viewed from above the court, using projective transformation, the occlusion caused by one camera is stably solved using the information from other cameras. In addition, using OpenPose for player detection reduces the occlusion that occurs in each camera image before all camera images are integrated. We confirm the effectiveness of our method by experiments with real image sequences.

Improvement of Range Resolution of FDMAS Beamforming in Ultrasound Imaging

Topics: Image Formation, Acquisition Devices and Sensors; Image Enhancement and Restoration; Medical Image Applications

Authors: Ryoya Kozai , Jing Zhu , Kan Okubo and Norio Tagawa

Affiliation: Graduate School of System Design, Tokyo Metropolitan University, Hino, Tokyo 191-0065 and Japan

Digital Object Identifier: 10.5220/0007583601980205

Proceedings of VISAPP 2019/VISIGRAPP, ISBN: 978-989-758-354-4

Collapse Button Quick Abstract
Ultrasound imaging is applied to various fields because it is noninvasive and real-time imaging is possible. However, in diagnosis applications, ultrasound imaging is inferior in resolution to other modalities, so researches for improving resolution have been actively conducted. Recently, researches on beamforming methods have been advanced for the purpose of improving lateral resolution. In order to form a narrower beam, adaptive beamformers such as the MV (minimum variance) beamformer that adaptively changes the beamforming weights have been proposed, but these methods increase the computational complexity. Therefore, in recent years, the FDMAS (Filtered-Delay Multiply And Sum) beamformer which can realize high resolution and high contrast without using complicated calculation attracts attention. On the other hand, we proposed a method called the SCM (Super resolution FM-Chirp correlation Method) that improves range resolution based on frequency sweep. In addition, we proposed a new DAS (Delay And Sum) beam former which improves range resolution by multiplying the echo signal by the result of the SCM before DAS processing. This method is constructed in the usual RF (Radio Frequency) band. In this study, we first reconstruct the FDMAS as a baseband processing in order to improve the SNR, and apply the SCM result to the FDMAS in order to improve both range and lateral resolution.
Collapse Button Related Ontology Subjects/Areas/Topics (6)
Applications and Services

Image Enhancement and Restoration

Image Formation, Acquisition Devices and Sensors

Computer Vision, Visualization and Computer Graphics

Image Formation and Preprocessing

Medical Image Applications

Selective Use of Appropriate Image Pairs for Shape from Multiple Motions based on Gradient Method

Topics: Image-Based Modeling and 3D Reconstruction; Stereo Vision and Structure from Motion; Optical Flow and Motion Analyses

Authors: Norio Tagawa and Syouta Tsukada

Affiliation: Tokyo Metropolitan University, Japan

Digital Object Identifier: 10.5220/0005778805520561

Proceedings of VISAPP 2016/VISIGRAPP, ISBN: 978-989-758-175-5

Collapse Button Quick Abstract
For the gradient-based shape from motion, relative motions with various directions at each 3-D point on a target object are generally effective for accurate shape recovery. On the other hand, a proper motion size exists for each 3-D point having an intensity pattern and a depth that varied in each, i.e., a too large motion causes a large error in depth recovery as an alias problem, and a too small motion is inappropriate from the viewpoint of an SNR. 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 the gradient method based on the 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.
Collapse Button Related Ontology Subjects/Areas/Topics (9)
Applications

Image-Based Modeling

Pattern Recognition

Computer Vision, Visualization and Computer Graphics

Motion, Tracking and Stereo Vision

Software Engineering

Geometry and Modeling

Optical Flow and Motion Analyses

Stereo Vision and Structure from Motion

Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme

Authors: Norio Tagawa and Shoei Koizumi

Affiliation: Tokyo Metropolitan University, Japan

Digital Object Identifier: 10.5220/0005462500920099

Proceedings of IMTA-5 2015/VISIGRAPP, ISBN: 978-989-758-094-9

Collapse Button Quick Abstract
The gradient-based depth from motion method is effective for obtaining a dense depth map. However, the accuracy of the depth map recovered only from two successive images is not so high, and hence, to increase the depth information by tracking corresponding image points through an image sequence is often performed by using, for example, the Kalman filter-like technique. Alternatively, multiple image pairs generated by random small camera rotations around a reference direction can be used for gaining much information of depth without such the tracking procedure. In the framework of this strategy, in this study, to further improve the accuracy, we propose a selective use of the optimal image resolution. The appropriate resolution image is required to have a linear intensity pattern which is the most important supposition for the gradient method often used for dense depth recovery based on the theory of “shape from motion.” The performance of our proposal is examined through numerical evaluations using artificial images.

Energy Expenditure during Walking, Jogging and Running in Bare and Shod Conditions

Topics: Applied Physiology and Exercise; Health and Fitness

Authors: Junichiro Yamauchi 1 , Hideaki Koike 2 and Keiji Koyama 3

Affiliations: 1 Tokyo Metropolitan University, Future Institute for Sport Sciences and Khon Kaen University, Japan , 2 Tokyo Metropolitan University, Japan , 3 Toin University of Yokohama, Japan

Collapse Button Quick Abstract
This study was to compare between barefoot and wearing running shod conditions on energy expenditure during walking, jogging and running. Healthy young individuals performed walking (4km/hr), jogging (8km/hr) and running (12km/hr) on the treadmill in barefoot (BARE) and shod (SHOD) conditions. Respiratory gas analysis was performed using a computerized metabolic measurement cart on a breath-by-breath mode. Exercises with a shod condition were significantly higher energy expenditure than those with a barefoot condition in walking, jogging and running.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Applied Physiology and Exercise

Health, Sports Performance and Support Technology

Sport Science Research and Technology
Health and Fitness

Exploring the Use of Smartphone Accelerometer and Gyroscope to Study on the Estimation of Road Surface Roughness Condition

Topics: Environmental Monitoring and Control; Time and Frequency Response; Sensors Fusion; Engineering Applications

Authors: Viengnam Douangphachanh and Hiroyuki Oneyama

Affiliation: Tokyo Metropolitan University, Japan

Digital Object Identifier: 10.5220/0005117407830787

Proceedings of ICINCO 2014, ISBN: 978-989-758-039-0

Collapse Button Quick Abstract
Smartphones are potentially useful to be adopted as a cost-effective and easy to implement tool for the measurement of road surface roughness condition, which is very essential for road monitoring and maintenance planning. In this study, an experiment has been carried out to collect data from accelerometers and gyroscopes on smartphones, which are placed at different locations inside vehicles running on road sections with different roughness conditions. The collected data is processed in the frequency domain to calculate magnitudes of the vibration. It has been revealed that at the considered frequency range of 40-50Hz, there is a very strong relationship between road roughness condition and the magnitudes of vibration, calculated from each axis of the accelerometers and gyroscopes; as well as the average speed. Road roughness condition that is modelled as a linear function of the vibration magnitudes, taking into account of both data from accelerometer and gyroscope as well as the average speed, achieves better estimation than the model that takes into account the magnitude from the accelerometer and the average speed alone. The finding is potentially significant for the development of a more accurate model and a better smartphone app to estimate road roughness condition from smartphone sensors.
Collapse Button Related Ontology Subjects/Areas/Topics (11)
Biomedical Engineering

Informatics in Control, Automation and Robotics

Signal Processing, Sensors, Systems Modeling and Control

Biomedical Signal Processing

Intelligent Control Systems and Optimization

Time and Frequency Response

Engineering Applications

Robotics and Automation

Time-Frequency Analysis
Environmental Monitoring and Control

Sensors Fusion

Topic(s):

Filter listed results, by

Publication date

From:
To:
Author
Locate Author in list below
Data pager
Data pager
1234
 Page 1 of 4, items 1 to 10 of 37.
Add Author(s) to filter:
Conference
Locate Conference in list below
Add Conference(s) to filter:

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic