Yumiko Ota
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yumiko Ota has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Hisayuki Tatsumi
Tsukuba University of Technology, Tsukuba, Ibaraki, Japan
1 shared publication - Yasuyuki Murai
Nihon Pharmaceutical University, Bunkyo-ku, Tokyo, Japan
1 shared publication
Latest Publications
- 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.