Faculty Profiles - TANJO YUI

Papers - TANJO YUI

Division display1 - 20 of about 600／ All the affair displays >>

Development of an Outdoor Autonomous Travel Robot Using Graph-based Segmentation and Deep Learning Reviewed International journal

Kako Koyama, Yui Tanjo

Proceedings of the 14th International Conference on Electronics, Communications and Networks (CECNet 2024) ( Frontiers in Artificial Intelligence and Applications ) 193 - 198 2024.11

Authorship：Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

Japan Matsue 2024.11.05 - 2024.11.08

This paper presents a novel approach to autonomous robot navigation using an RGB-D camera technology for complex urban environments. The paper proposes a comprehensive system integrating checkpoint-based path planning, image-based self-localization, and a hybrid method for drivable area estimation. The drivable area estimation technique combines Graph-based Segmentation (GBS), deep learning-based road detection and texture feature analysis. Using 315 diverse urban images, the system’s performance was evaluated by comparing the results of three methods: (i) GBS with texture features, (ii) deep learning alone, and (iii) the proposed hybrid approach. While deep learning achieved the highest overall performance (IoU: 0.832, Accuracy: 0.875), the hybrid approach showed competitive results (IoU: 0.823, Accuracy: 0.870). Importantly, qualitative analysis revealed that the proposed hybrid approach outperformed deep learning in challenging scenarios such as roads adjacent to vehicular traffic and narrow pathways. These findings demonstrate the potential of the proposed approach for robust autonomous navigation in complex urban environments, advancing applications in service robotics.
Keywords: Robot vision, Region segmentation, GBS, Autonomous travel, Deep learnin

Kyutacar

Development of a Navigation System Using MY VISION for Visually Impaired People －A Method to Guide the Direction of Travel Reviewed International journal

Yuki Koike, Yui Tanjo

( IEEE ) 3275 - 3280 2024.10

High-Accuracy human motion recognition independent of motion direction using a single camera Reviewed International journal

Jing Cao, Yui Tanjo

International Journal of Innovative Computing, Information and Control ( ICIC International ) 20 ( 4 ) 1093 - 1103 2024.08

Authorship：Corresponding author Language：English Publishing type：Research paper (scientific journal)

With the rapid development of computer vision research, the technology has
received extensive attention and has been widely used. In today’s society, the technology of
automatic recognition of human movements is particularly important in research related
to the development of elderly care systems and crime prevention systems. However, most
conventional researches on motion recognition assume that the motion is on the plane
perpendicular to the optical axis of the camera. There are only a few studies dealing
with the motion in the direction of a camera’s optical axis and the reported accuracy
is only 83.7%. Therefore, to improve the accuracy while reducing processing time, this
paper proposes a TMRIs (Triplet Motion Representation Images) that expresses human
motion by extending the traditional method named MHI (Motion History Image), Ex-
HOOF (Extended Histogram of Oriented Optical Flow) that includes features of motion
direction and velocity information, and the change of features of the area and the center
of gravity of the foreground object, to identify the movement toward the optical axis of
a camera and hence improve the accuracy of action recognition. The performance and
effectiveness of the proposed method are verified by experiments.
Keywords: Motion recognition, Elderly care, Crime prevention, MHI, Optical flows

DOI： 10.24507/ijicic.20.04.1093

Kyutacar

Scopus

Other Link： http://www.ijicic.net/

A METHOD OF RECOGNIZING HUMAN WALK MOTION FROM MULTIPLE DIRECTIONS Reviewed International journal

Miki Ooba, Yui Tanjo

International Journal of Innovative Computing, Information and Control ( ICIC International ) 20 ( 4 ) 1245 - 1256 2024.08

Analysis of Human Walking Posture Using a Wearable Camera Reviewed International journal

Ziyue Liu, Joo Kooi Tan

International Journal of Innovative Computing, Information and Control ( ICIC International ) 19 ( 3 ) 805 - 819 2023.05

Detecting Approaching Human Hands in a Human-Robot Coexistent Food Preparation Work Area for Preventing Collision Reviewed International journal

Joo Kooi Tan, Takaaki Yotsumoto

Journal of Robotics, Networking and Artificial Life 9 ( 3 ) 289 - 294 2022.12

A Method of Navigating a Visually Impaired Person Using MY VISION Reviewed International journal

Joo Kooi Tan, Kohei Kitagawa

Journal of Robotics, Networking and Artificial Life 9 ( 1 ) 25 - 30 2022.06

A Method of Identifying a Public Bus Route Number Employing MY VISION Reviewed International journal

Joo Kooi Tan, Yosiki Hamasaki, Ye Zhou, Ishitobi Kazuma

Journal of Robotics, Networking and Artificial Life 8 ( 3 ) 224 - 228 2021.12

Detection of a Fallen Person and its head and lower body from aerial images Reviewed International journal

Joo Kooi Tan, Haruka Egawa

Journal of Robotics, Networking and Artificial Life 8 ( 2 ) 134 - 138 2021.09

Estimation of Self-Posture of a Pedestrian Using MY VISION Based on Depth and Motion Network Reviewed International journal

Joo Kooi Tan,Tomoyuki Kurosaki

Journal of Robotics, Networking and Artificial Life 7 ( 3 ) 152 - 155 2020.12

Human-robot Cooperation Based on Visual Communication Reviewed International journal

Joo Kooi Tan, Akitoshi Sato

International Journal of Innovative Computing, Information and Control ( ICIC International ) 16 ( 2 ) 543 - 554 2020.04

Authorship：Lead author Language：English Publishing type：Research paper (scientific journal)

This paper proposes a human-robot cooperative system supported by visual communication. Human-robot cooperation is expected in various fields nowadays in order to raise efficiency, accuracy and safety of work, to name a few, production of goods, logistics, car driving, care of aged people, etc. In the human-robot cooperation, it is desirable that a human takes less part of work; whereas a robot takes a larger role with it. The idea of the present paper is that visual decision making is done by a human rather than a robot. The proposed system goes to a specified remote spot autonomously and performs objects acquisition there by communicating visually with a user. It aims at realizing ‘a shopping robot’ in near future and expected to be used by disadvantaged shoppers. The proposed system is presented and some experimental results are shown.

DOI： 10.24507/ijicic.16.02.543

Other Link： https://www.scopus.com/record/display.uri?eid=2-s2.0-85082019101&origin=resultslist&sort=plf-f

A Method of Describing a Self-occlusive Motion - A Reverse Motion History Image Reviewed

Joo Kooi Tan, Sayaka Okae, Youtaro Yamashita, Yuta Ono

International Journal of Biomedical Soft Computing and Human Sciences 24 ( 1 ) 1 - 7 2019.07

Walk Environment Analysis Using MY VISION: Toward a Navigation System Providing Visual Assistance Reviewed International journal

Joo Kooi Tan, Tomoki Ishimine and Shohei Arimasu

International Journal of Innovative Computing, Information and Control 15 ( 3 ) 861 - 871 2019.06

Human motion recognition using TMRIs with extended HOOF Reviewed International journal

Jing Cao, Youtaro Yamashita, Joo Kooi Tan

Journal of Robotics, Networking and Artificial Life 7 ( 4 ) 231 - 235 2021.03

Detecting Pedestrians and Their Walk Directions Using a MY VISION System Reviewed International journal

Joo Kooi Tan, Hori Kenta, Seiji Ishikawa

Journal of Robotics, Networking and Artificial Life 7 ( 2 ) 137 - 141 2020.09

Development of an Autonomous Mobile Robot Doing Self-Position Estimation and Road Region Search Reviewed International journal

Naokazu Iwata, JooKooi Tan

Journal of Advances in Artificial Life Robotics 1 ( 2 ) 99 - 103 2020.08

A Support System for a Visually Impaired Person Finding Bus Route Numbers Employing MY VISION Reviewed International journal

Daichi Nanaura, Seiji Ishikawa, Yui Tanjo

The 2025 International Conference on Artificial Life and Robotics ( Robot Artificial Life Society ) 927 - 930 2025.02

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

Japan Oita 2025.02.13 - 2025.02.16

A bus is not a very convenient means for a visually impaired person because of the difficulty in identifying its route number, although it is an economical tool for travel. This paper proposes a method of detecting and identifying a bus route number using the MYVISION system which employs an ego camera worn by a visually impaired person. The method finds a frontal area of a bus approaching a bus stop using the video which the camera provides by using optical flow and random forest employing Haar-like features. It then extracts the upper destination panel area followed by the detection of a route number at the right-hand side of the panel. Finally, the detected route number is identified by template matching. In the experiment, various kinds of videos containing the buses of a bus company were captured at different places and different weather conditions, and the effectiveness of the proposed method was shown. The method is now planned to be applied to the busses of various bus companies.

Kyutacar

Human Pose Estimatin From Egocentric Videos Reviewed International journal

Shunya Egashira, Yui Tanjo

The 2025 International Conference on Artificial Life and Robotics ( Robot Artificial Life Society ) 931 - 934 2025.02

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

Japan Oita 2025.02.13 - 2025.02.16

According to a survey conducted by the Ministry of Health, Labour and Welfare in 2019, about 30% of patients suffer from back pain and stiff shoulders. Although researches on pose estimation have been conducted for a long time, they cannot be used for daily pose estimation, because they need fixed cameras to capture target/subject motions. To solve this problem, the present paper proposes a novel pose estimation method from egocentric videos using Epipolar Geometry. It computes three rotational angles, i.e., pitch, yaw and roll, from the egocentric motion videos to evaluate differences from his/her normal motion. In the experiment, three egocentric videos were used to verify the performance and effectiveness of the proposed method and reasonable/satisfactory results were obtained.

Kyutacar

Human Motion Recognition from Multiple Directions and Its Gait Cycles Analysis Reviewed International journal

Miki Ooba, Yui Tanjo

The 2024 International Conference on Artificial Life and Robotics ( Robot Artificial Life Society ) 959 - 963 2024.02

Human Behavior Segmentation and Recognition Using a Single-camera Reviewed International journal

Jing Cao, Yui Tanjo

The 2024 International Conference on Artificial Life and Robotics ( Robot Artificial Life Society ) 969 - 973 2024.02

　PREV- NEXT 　

<TANJO YUI>

Papers - TANJO YUI