| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-01-22 |
| タイトル |
|
|
タイトル |
Quantitative Crowdedness Measure for Evaluation of Hazard Avoidance Smartphone Apps for Visually Impaired at Station Platform |
|
言語 |
en |
| その他のタイトル |
|
|
その他のタイトル |
QUANTITATIVE CROWDEDNESS MEASURE FOR EVALUATION OF HAZARD AVOIDANCE SMARTPHONE APPS FOR VISUALLY IMPAIRED AT STATION PLATFORM |
|
言語 |
en |
| 著者 |
Shimakawa, Manabu
Nakahara, Taiyo
Okuma, Chiharu
Kiyota, Kimiyasu
新見, 道治
|
| 著作権関連情報 |
|
|
権利情報 |
ICIC International Copyright (c) 2024 |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Accidents in which visually impaired persons falling off station platforms have occurred repeatedly. These accidents are often caused by misunderstandings, loss of direction, and other factors that prevent correct recognition of the actual surroundings. Although the installation of platform doors is crucial, it is more important that visually impaired individuals can navigate around their surroundings and avoid potential hazards. In our study, we are conducting research on the use of smartphones to support the safe walking of the visually impaired. The application uses a camera to scan the surroundings, identify various objects based on the acquired RGB images, and then alert the user when a dangerous situation is detected. In our previous study, we confirmed that the system can detect steps, stairs, bicycles, and other objects which is an effective method to detect dangerous situations. Currently, we are extending the application to specialize in preventing the accident of falling from station platforms. Due to the fact that the application decides dangerous scene based on images captured by digital cameras, the accuracy of the detection would be getting worser when target objects are hidden by human; in other words, the crowdedness of the area affects the detection ability. One of requirements to use this app safely is to make clear the detection ability of the app with varying the crowdedness. To do this, we need to quantitatively define the crowdedness. In this paper, two measures, a range-based measure and a weighted distance measure, classified as local density are employed as quantitative crowdedness measures. This paper reports the experimental results comparing the two crowdedness measures, and examines which is more effective for the purpose. We conducted this experiments using a human location measurement system that can track the location of people walking and obtain their coordinates. This crowdedness measure can be applicable to evaluation criteria for apps with the same purpose of our app. |
|
言語 |
en |
| 書誌情報 |
en : ICIC Express Letters, Part B: Applications
巻 15,
号 2,
p. 161-169,
発行日 2024-02
|
| 出版社 |
|
|
出版者 |
ICIC International |
|
言語 |
en |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Quantitative crowdedness measure |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Range-based measure |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Weighted distance measure |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Smartphone app |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Visually impaired persons |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.24507/icicelb.15.02.161 |
| ISSN |
|
|
収録物識別子タイプ |
PISSN |
|
収録物識別子 |
2185-2766 |
| 査読の有無 |
|
|
値 |
yes |
| 研究者情報 |
|
|
URL |
https://hyokadb02.jimu.kyutech.ac.jp/html/236_ja.html |
| 論文ID（連携） |
|
|
値 |
10430043 |
| 連携ID |
|
|
値 |
12155 |
10430043.pdf (1.7 MB)
