AudioBrowser: a mobile browsable information access for the visually impaired

Although a large amount of research has been conducted on building interfaces for the visually impaired that allows users to read web pages and generate and access information on computers, little development addresses two problems faced by the blind users. First, sighted users can rapidly browse and select information they find useful, and second, sighted users can make much useful information portable through the recent proliferation of personal digital assistants (PDAs). These possibilities are not currently available for blind users. This paper describes an interface that has been built on a standard PDA and allows its user to browse the information stored on it through a combination of screen touches coupled with auditory feedback. The system also supports the storage and management of personal information so that addresses, music, directions, and other supportive information can be readily created and then accessed anytime and anywhere by the PDA user. The paper describes the system along with the related design choices and design rationale. A user study is also reported.     

视听触同步刺激的数字化盲文学习方法

盲文是视障人士获取信息,学习知识的重要媒介.然而,目前基于纸质书籍的盲文学习方法只能提供盲文点位的触觉刺激,存在不便携、不易用且内容陈旧等问题.为此,本文提出了一种视觉、听觉和触觉同步刺激的数字化盲文学习方法,能够提高视障人士的盲文学习效率.基于多感知盲文学习机,本文设计了一种多感知信息匹配算法,能够输出文字、声音和盲...     

Graphical message transmission using the monotonic vibration function of a smart phone

This study aimed at evaluating four vibrotactile capabilities for perceiving graphical information presented on a smart phone. Thirty-two blindfolded college students participated in four experiments to test their capabilities of two-point discrimination, relative and absolute judgments of line thickness, and recognition of basic shapes. All the information was received through the default vibration function of the phone, sensed by their scanning fingers. The results showed a good two-point discrimination accuracy rate, reaching 98.8% when the distance between two points was set at 3.2 mm; the relative judgment of line thickness reached the level of 78.3% accuracy when the two-line width difference ratio was set at 3%; the absolute judgment reached the level of 78.8% when the participants recognised line thickness from one of two. Overall, especially for the shapes judgment, the information transmitted by the various codes may be quite low. These findings should inspire advanced investigations and provide design guidelines.     

Walking strategies of visually impaired people on trapezoidal- and sinusoidal-section tactile groundsurface indicators

The visual system in walking serves to perceive feedback or feed-forward signals. Therefore, visually impaired persons (VIP) have biased motor control mechanisms. The use of leading indicators (LIs) and long canes helps toimprove their walking efficiency. The aims of this study were to compare the walking efficiency of VIP on trapezoidal- and sinusoidal-section LIs using an optoelectronic motion analysis system. VIP displayed a significantly longer stance phase, a shorter swing phase and shorter step and stride lengths when they walked on the sinusoidal LIthan when they walked on the trapezoidal LI. Compared with the trapezoidal LI, VIP walking on the sinusoidalLIdisplayed significantly lower joint ranges of motion. The centre of mass lateral displacement was wider for VIP walking on the sinusoidal LI than on the trapezoidal LI. Some significant differences were also found in sighted persons walking on both LIs. In conclusion, the trapezoidal shape enabled visually impaired subjects to walk more efficiently, whereas the sinusoidal shape caused dynamic balance problems.

Statement of Relevance: These findings suggest that VIP can walk more efficiently, with a lower risk of falls, on trapezoidal-section than on sinusoidal-section LIs. These results should be considered when choosing the most appropriate ground tactile surface indicators for widespread use.     

RGB-D和惯性传感器融合的地面障碍物检测技术

针对视障人士出行辅助中可通行区域地面障碍物实时检测问题,提出一种基于RGB-D和惯性传感器融合的地面障碍物检测技术.首先建立地面障碍物空间模型,并融合惯性传感器参数计算相机倾角以校正地面障碍物世界坐标;其次针对视障人士实际使用场景和需求,使用阈值分割算法将深度图像中距离较远的检测像素去除,并将深度图划分4个区域,通过融合惯性传感器数据实现ROI的动态划分;最后通过改进RANSAC算法设计了基于地面区域生长的障碍物检测算法,并采集真实数据进行实验验证.实验结果表明,所提技术的准确率和召回率分别达到90.87%和89.33%,并在执行时间效率上优于已有地面障碍物检测算法,满足了视障人士对算法的实时性要求.     

盲人触觉图形显示器的交互体验研究

在互联网时代,盲人由于视力缺失,通过触听觉对图形图像的认知需求越来越强烈.文中通过对触觉和现有触觉图形显示器的梳理分析,围绕其交互技术和用户体验进行研究.首先从人的触觉生理角度论证了触觉图形显示器的可用性;然后列举了主要的触觉图形显示器的研发原型或产品,梳理了各种交互技术及参数的对比,并以用户体验的角度,通过实验分析了影响体验的重要设计因素.最后针对大数据时代,以盲人对产品的体验为中心设计了一套盲人触觉显示器的交互原则,为触觉图形显示器的设计提供了参考.     

辅助视障出行融合障碍物检测的路径规划研究进展

视障人士是社会中的弱势群体,独立出行面临重重障碍.为视障人士提供安全可靠的辅助设备体现了社会文明的进步.介绍了辅助视障出行有关的障碍物检测识别关键技术和路径规划相关算法.重点对障碍物检测之后的路径规划算法进行分析,综合对比各种技术的应用特点及场景并讨论了相关方法在视障辅助设备中的研究进展.总结了多技术融合使用在智能辅助设备中的应用现状.在此基础上,结合人工智能及嵌入式设备等技术的进步展望了未来辅助视障出行设备的发展方向.     

Assisting Visually Impaired People to Acquire Targets on a Large Wall-Mounted Display

Large displays have become ubiquitous in our everyday lives, but these displays are designed for sighted people.This paper addresses the need for visually impaired people to access targets on large wall-mounted displays. We developed an assistive interface which exploits mid-air gesture input and haptic feedback, and examined its potential for pointing and steering tasks in human computer interaction（HCI）. In two experiments, blind and blindfolded users performed target acquisition tasks using mid-air gestures and two different kinds of feedback（i.e., haptic feedback and audio feedback）. Our results show that participants perform faster in Fitts＇ law pointing tasks using the haptic feedback interface rather than the audio feedback interface. Furthermore, a regression analysis between movement time（MT） and the index of difficulty（ID）demonstrates that the Fitts＇ law model and the steering law model are both effective for the evaluation of assistive interfaces for the blind. Our work and findings will serve as an initial step to assist visually impaired people to easily access required information on large public displays using haptic interfaces.     

Multiobjective Navigation of a Guide Mobile Robot for the Visually Impaired Based on Intention Inference of Obstacles

Different from ordinary mobile robots used in a well-structured industrial workspace, a guide mobile robot for the visually impaired should be designed in consideration of multiple moving obstacles of various types and with different speeds while it adaptively maintains a certain distance from the user. Here, the moving obstacles mostly refer to pedestrians in intentional motions. Thus, navigation of the guide robot can be facilitated if the intention of each obstacle detected can be known in advance.In the paper, we propose to use a fuzzy grid-type local map in order to infer the intention of a moving obstacle. And, then, we determine the motion control of the robot by adopting a multiobjective decision making method in order to take into consideration various requirements including goal-seeking, multiple obstacle avoidance and maintenance of a certain distance from the user. To show the effectiveness of the proposed method, some experimental results are provided.     

Robot-assisted shopping for the blind: issues in spatial cognition and product selection

Research on spatial cognition and blind navigation suggests that a device aimed at helping blind people to shop independently should provide the shopper with effective interfaces to the locomotor and haptic spaces of the supermarket. In this article, we argue that robots can act as effective interfaces to haptic and locomotor spaces in modern supermarkets. We also present the design and evaluation of three product selection modalities—browsing, typing and speech, which allow the blind shopper to select the desired product from a repository of thousands of products.