Suppr超能文献

虚拟现实训练助力盲人导航摄影

VR Training to Facilitate Blind Photography for Navigation.

作者信息

Hong Jonggi, Coughlan James M

机构信息

Smith-Kettlewell Eye Research Institute, California, USA.

出版信息

J Technol Pers Disabil. 2023;11:245-259.

Abstract

Smartphone-based navigation apps allow blind and visually impaired (BVI) people to take images or videos to complete various tasks such as determining a user 's location, recognizing objects, and detecting obstacles. The quality of the images and videos significantly affects the performance of these systems, but manipulating a camera to capture clear images with proper framing is a challenging task for BVI users. This research explores the interactions between a camera and BVI users in assistive navigation systems through interviews with BVI participants. We identified the form factors, applications, and challenges in using camera-based navigation systems and designed an interactive training app to improve BVI users' skills in using a camera for navigation. In this paper, we describe a novel virtual environment of the training app and report the preliminary results of a user study with BVI participants.

摘要

基于智能手机的导航应用程序使盲人和视力受损者能够拍摄图像或视频,以完成各种任务,如确定用户位置、识别物体和检测障碍物。图像和视频的质量会显著影响这些系统的性能,但对于视力受损用户来说,操作相机以捕捉构图合适的清晰图像是一项具有挑战性的任务。本研究通过对视力受损参与者进行访谈,探讨了辅助导航系统中相机与视力受损用户之间的交互。我们确定了基于相机的导航系统的外形因素、应用场景和挑战,并设计了一款交互式训练应用程序,以提高视力受损用户使用相机进行导航的技能。在本文中,我们描述了该训练应用程序的一个新颖虚拟环境,并报告了一项针对视力受损参与者的用户研究的初步结果。

相似文献

本文引用的文献

2
The Last Meter: Blind Visual Guidance to a Target.最后一米:对目标的盲目视觉引导。
Proc SIGCHI Conf Hum Factor Comput Syst. 2014 Apr-May;2014:3113-3122. doi: 10.1145/2556288.2557328.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验