Hisayuki Tatsumi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hisayuki Tatsumi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Masahiro Miyakawa
Tsukuba University of Technology, Tsukuba, Ibaraki, Japan
2 shared publications- Yasuyuki Murai
Nihon Pharmaceutical University, Bunkyo-ku, Tokyo, Japan
2 shared publications Lucien Haddad
Royal Military College of Canada, Kingston, Ontario, Canada
1 shared publication- Makoto Kobayashi
National Institute for Fusion Science, Toki, Japan
1 shared publication - Makoto Suzuki
Tohoku University
1 shared publication - Maurice Pouzet
Department University of Calgary
1 shared publication
Latest Publications
- Open Access
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 125-129
AI-Powered Walking Assistance System for the Visually Impaired: Estimating Navigable Areas Using Pedestrian Information and AI Cameras
This paper presents the development of an AI-based system to assist visually impaired individuals in navigating safely. The system utilizes a wearable camera and advanced AI algorithms to identify and map "walkable areas" based on the presence of sighted pedestrians. This approach leverages human spatial awareness, providing a robust, real-time solution for navigating complex environments. Unlike conventional methods relying on obstacle detection or pre-defined maps, this system dynamically adapts to changing surroundings. It employs a pre-trained YOLO model for pedestrian recognition and an OAK-D Pro AI camera for real-time pedestrian detection and tracking. The system then generates a walkable area map based on the identified pedestrian movements displayed on a smartphone or tablet. This research addresses the limitations of traditional assistive navigation systems by leveraging pedestrian spatial awareness. The developed system empowers visually impaired individuals with greater independence and confidence in their daily lives by harnessing the power of AI and human spatial perception.
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 125-129
Open AccessAI-Powered Walking Assistance System for the Visually Impaired: Estimating Navigable Areas Using Pedestrian Information and AI Cameras
This paper presents the development of an AI-based system to assist visually impaired individuals in navigating safely. The system utilizes a wearable camera and advanced AI algorithms to identify and map "walkable areas" based on the presence of sighted pedestrians. This approach leverages human spatial awareness, providing a robust, real-time solution for navigating complex environments. Unlike conventional methods relying on obstacle detection or pre-defined maps, this system dynamically adapts to changing surroundings. It employs a pre-trained YOLO model for pedestrian recognition and an OAK-D Pro AI camera for real-time pedestrian detection and tracking. The system then generates a walkable area map based on the identified pedestrian movements displayed on a smartphone or tablet. This research addresses the limitations of traditional assistive navigation systems by leveraging pedestrian spatial awareness. The developed system empowers visually impaired individuals with greater independence and confidence in their daily lives by harnessing the power of AI and human spatial perception.
- Open Access
- 26 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 423-428
Prototyping of a walking assistance system for visually impaired people using AI and LiDAR
This research focuses on the development of an AI-based system designed to provide walking support for individuals with visual impairments. Depending on the specific characteristics of their disability, visually impaired individuals may encounter challenges when walking in a straight line. To address this issue, we are working on a system that incorporates a small body-worn camera to capture movement direction, identify safe walking areas from the recorded images, and guide users toward those regions. The current system in development utilizes AI to detect pedestrian position information from the camera images, establishing a "walkable area" based on this data to ensure user safety. Voice notifications are employed to communicate movement directions and other relevant information to the user. In this report, we propose integrating LiDAR technology to gather comprehensive environmental information, enhancing the safety of the walking support system. We employ Simultaneous Localization and Mapping (SLAM) techniques to create an environment map using the collected LiDAR data. The report outlines the progress made in developing a prototype system capable of providing walking support through the utilization of the environment map and the defined walkable area.
- 26 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 423-428
Open AccessPrototyping of a walking assistance system for visually impaired people using AI and LiDAR
This research focuses on the development of an AI-based system designed to provide walking support for individuals with visual impairments. Depending on the specific characteristics of their disability, visually impaired individuals may encounter challenges when walking in a straight line. To address this issue, we are working on a system that incorporates a small body-worn camera to capture movement direction, identify safe walking areas from the recorded images, and guide users toward those regions. The current system in development utilizes AI to detect pedestrian position information from the camera images, establishing a "walkable area" based on this data to ensure user safety. Voice notifications are employed to communicate movement directions and other relevant information to the user. In this report, we propose integrating LiDAR technology to gather comprehensive environmental information, enhancing the safety of the walking support system. We employ Simultaneous Localization and Mapping (SLAM) techniques to create an environment map using the collected LiDAR data. The report outlines the progress made in developing a prototype system capable of providing walking support through the utilization of the environment map and the defined walkable area.
- Open Access
- 1 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 62-67
Hereditary rigidity, separation and density: In memory of Professor I.G. Rosenberg
We continue the investigation of systems of hereditarily rigid relations started in Couceiro, Haddad, Pouzet and Schölzel [1]. We observe that on a set $V$ with $m$ elements, there is a hereditarily rigid set $\mathcal{R}$ made of $n$ tournaments if and only if $m(m-1)\leq 2^{n}$ . We ask if the same inequality holds when the tournaments are replaced by linear orders. This problem has an equivalent formulation in terms of separation of linear orders. Let $h_{\text{Lin}}(m)$ be the least cardinal $n$ such that there is a family $\mathcal{R}$ of $n$ linear orders on an $m$ -element set $V$ such that any two distinct ordered pairs of distinct elements of $V$ are separated by some member of $\mathcal{R}$ , then $[\log_{2}(m(m-1))]\leq h_{\text{Lin}}(m)$ with equality if $m\leq 7$ . We ask whether the equality holds for every $m$ . We prove that $h_{\text{Lin}}(m+1)\leq h_{\text{Lin}}(m)+1$ . If $V$ is infinite, we show that $h_{\text{Lin}}(m)=\aleph_{0}$ for $m\leq 2^{\aleph_{0}}$ . More generally, we prove that the two equalities $h_{\text{Lin}}(m)=log_{2}(m)=d$ (Lin $(V)$ ) hold, where $\log_{2}(m)$ is the least cardinal $\mu$ such that $m\leq 2^{\mu}$ , and $d$ (Lin $(V)$ ) is the topological density of the set Lin (V) of linear orders on $V$ (viewed as a subset of the power set $\mathcal{P}(V\times V)$ equipped with the product topology). These equalities follow from the Generalized Continuum Hypothesis, but we do not know whether they hold without any set theoretical hypothesis.- 1 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 62-67
Open AccessHereditary rigidity, separation and density: In memory of Professor I.G. Rosenberg
We continue the investigation of systems of hereditarily rigid relations started in Couceiro, Haddad, Pouzet and Schölzel [1]. We observe that on a set $V$ with $m$ elements, there is a hereditarily rigid set $\mathcal{R}$ made of $n$ tournaments if and only if $m(m-1)\leq 2^{n}$ . We ask if the same inequality holds when the tournaments are replaced by linear orders. This problem has an equivalent formulation in terms of separation of linear orders. Let $h_{\text{Lin}}(m)$ be the least cardinal $n$ such that there is a family $\mathcal{R}$ of $n$ linear orders on an $m$ -element set $V$ such that any two distinct ordered pairs of distinct elements of $V$ are separated by some member of $\mathcal{R}$ , then $[\log_{2}(m(m-1))]\leq h_{\text{Lin}}(m)$ with equality if $m\leq 7$ . We ask whether the equality holds for every $m$ . We prove that $h_{\text{Lin}}(m+1)\leq h_{\text{Lin}}(m)+1$ . If $V$ is infinite, we show that $h_{\text{Lin}}(m)=\aleph_{0}$ for $m\leq 2^{\aleph_{0}}$ . More generally, we prove that the two equalities $h_{\text{Lin}}(m)=log_{2}(m)=d$ (Lin $(V)$ ) hold, where $\log_{2}(m)$ is the least cardinal $\mu$ such that $m\leq 2^{\mu}$ , and $d$ (Lin $(V)$ ) is the topological density of the set Lin (V) of linear orders on $V$ (viewed as a subset of the power set $\mathcal{P}(V\times V)$ equipped with the product topology). These equalities follow from the Generalized Continuum Hypothesis, but we do not know whether they hold without any set theoretical hypothesis. - Open Access
- 23 October 2020
- Published by Association for Computing Machinery (ACM)
- p. 46-50
Floor-Volleyball Motion Feedback System for Visually Impaired Players
Floor-volleyball is one of the common sports for visually impaired people, including the blind in Japan. Its history started from the 1960s and most of young students in the special schools for the blind have experience of this sport in a class of physical education or a club activity. However, there is not an appropriate way to recognize motions of players by their own, because of their visual impairments. Therefore, sensing the motion of the Floor-volleyball player and developing a tactile device which shows the motion was carried out in this research. Using a three-dimensional motion capture system, four visually impaired players’ data were collected and analyzed. The results showed that each player has each character of the motion. The significant difference was observed in the back-swing speed. To display the difference to the blind players, a small wireless tactile display device was successfully developed. It equips 384 refreshable tactile pins which are arranged in 36 by 12. These pins are driven by piezo actuators same as the common braille display. The main feature of the device is that the controller equips ESP-WROOM-02 Wi-Fi module and AAA batteries. The device is perfectly wireless and suitable for the physical education field.
- 23 October 2020
- Published by Association for Computing Machinery (ACM)
- p. 46-50
Open AccessFloor-Volleyball Motion Feedback System for Visually Impaired Players
Floor-volleyball is one of the common sports for visually impaired people, including the blind in Japan. Its history started from the 1960s and most of young students in the special schools for the blind have experience of this sport in a class of physical education or a club activity. However, there is not an appropriate way to recognize motions of players by their own, because of their visual impairments. Therefore, sensing the motion of the Floor-volleyball player and developing a tactile device which shows the motion was carried out in this research. Using a three-dimensional motion capture system, four visually impaired players’ data were collected and analyzed. The results showed that each player has each character of the motion. The significant difference was observed in the back-swing speed. To display the difference to the blind players, a small wireless tactile display device was successfully developed. It equips 384 refreshable tactile pins which are arranged in 36 by 12. These pins are driven by piezo actuators same as the common braille display. The main feature of the device is that the controller equips ESP-WROOM-02 Wi-Fi module and AAA batteries. The device is perfectly wireless and suitable for the physical education field.
- 9 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 000361-000366
Low vision aid through laser retina imaging: Toward building eyesight-aid
Laser retina imaging technology enables creation of a clear picture in any retina area. It is focus-free, i.e. irrelevant of refractive disorder. So in many cases of low vision, one can see the picture by one's own eyesight. In this article we describe possible applications of this emerging technology, including
- 9 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 000361-000366
Low vision aid through laser retina imaging: Toward building eyesight-aid
Laser retina imaging technology enables creation of a clear picture in any retina area. It is focus-free, i.e. irrelevant of refractive disorder. So in many cases of low vision, one can see the picture by one's own eyesight. In this article we describe possible applications of this emerging technology, including