School of Civil Engineering and Mapping and Engineering, Jiangxi University of Technology, Ganzhou, Jiangxi, China.
State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing, China.
Disabil Rehabil Assist Technol. 2024 May;19(4):1657-1675. doi: 10.1080/17483107.2023.2227224. Epub 2023 Jul 4.
In this article, we comprehensively review the current situation and research on technology related to outdoor travel for blind and visually impaired people (BVIP), given the diverse types and incomplete functionality of navigation aids for the blind. This aims to provide a reference for related research in the fields of outdoor travel for BVIP and blind navigation.
We compiled articles related to blind navigation, of which a total of 227 of them are included in the search criteria. One hundred and seventy-nine articles are selected from the initial set, from a technical point of view, to elaborate on five aspects of blind navigation: system equipment, data sources, guidance algorithms, optimization of related methods, and navigation maps.
The wearable form of assistive devices for the blind has the most research, followed by the handheld type of aids. The RGB data class based on vision sensor is the most common source of navigation environment information data. Object detection based on picture data is also particularly rich among navigation algorithms and associated methods, indicating that computer vision technology has become an important study content in the field of blind navigation. However, research on navigation maps is relatively less.
In the study and development of assistive equipment for BVIP, there will be an emphasis on prioritizing attributes, such as lightness, portability, and efficiency. In light of the upcoming driverless era, the research focus will be on the development of visual sensors and computer vision technologies that can aid in navigation for the blind.
鉴于盲人导航辅助设备种类繁多且功能不完善，本文全面回顾了与盲人及视障人士（BVIP）户外出行相关技术的现状和研究，旨在为 BVIP 户外出行和盲人导航相关研究提供参考。
我们编译了与盲人导航相关的文章，其中共有 227 篇符合搜索标准。从技术角度出发，从最初的一组文章中选择了 179 篇文章，详细阐述了盲人导航的五个方面：系统设备、数据源、引导算法、相关方法的优化以及导航地图。
盲人辅助设备的可穿戴形式研究最多，其次是手持型辅助设备。基于视觉传感器的 RGB 数据类是导航环境信息数据最常见的来源。基于图片数据的目标检测在导航算法和相关方法中也特别丰富，这表明计算机视觉技术已成为盲人导航领域的重要研究内容。然而，导航地图的研究相对较少。
在盲人辅助设备的研究和开发中，将优先考虑轻便、便携和高效等属性。鉴于即将到来的无人驾驶时代，研究重点将放在开发视觉传感器和计算机视觉技术上，以帮助盲人进行导航。
