Building new systems used for indoor objects detection and indoor assistance navigation presents a very crucial task especially in artificial intelligence and computer science fields. The number of ...blind and visually impaired persons (VIP) is increasing day by day. In order to help this category of persons, we propose to develop a new indoor object-detection system based on deep convolutional neural networks (DCNNs). The proposed system is developed based on the one-stage neural network RetinaNet. In order to train and evaluate the developed system, we propose to build a new indoor objects dataset which also presents 11,000 images containing 24 indoor landmark objects highly valuable for indoor assistance navigation. The proposed dataset provides a high intra and inter-class variation and various challenging conditions which aim to build a robust detection system for blind and visually impaired people (VIP) mobility. Experimental results prove the high detection performances of the developed indoor objects detection and recognition system. We obtained a detection accuracy reaching up to 98.75% mAP and 62 FPS as a detection speed.
In this article, a new design of a wearable navigation support system for blind and visually impaired people (BVIP) is proposed. The proposed navigation system relies primarily on sensors, real-time ...processing boards, a fuzzy logic-based decision support system, and a user interface. It uses sensor data as inputs and provides the desired safety orientation to the BVIP. The user is informed about the decision based on a mixed voice–haptic interface. The navigation aid system contains two wearable obstacle detection systems managed by an embedded controller. The control system adopts the Robot Operating System (ROS) architecture supported by the Beagle Bone Black master board that meets the real-time constraints. The data acquisition and obstacle avoidance are carried out by several nodes managed by the ROS to finally deliver a mixed haptic–voice message for guidance of the BVIP. A fuzzy logic-based decision support system was implemented to help BVIP to choose a safe direction. The system has been applied to blindfolded persons and visually impaired persons. Both types of users found the system promising and pointed out its potential to become a good navigation aid in the future.
We propose an automatic math expression reading system, called i-Math. i-Math is an educational tool, for blind and visually impaired (VI) students, to facilitate access to math materials. Although ...blind and VI students can access math documents/materials via many channels, e.g., human reader, math Braille codes, and audio (talking) books, these channels have limited availability. i-Math was designed to be an automatic reading aided tool and also a math learning and teaching tool for both students and teachers. i-Math operated with screen reader produce voice output on a computer. i-Math can read math documents aloud. Students can enjoy their newfound ability to read and practice math anytime and anywhere with i-Math while teachers can prepare their classroom handouts, assignments and exercises in audio version conveniently.
The evaluation of i-Math was conducted with 78 blind and VI students and six teachers. The evaluation results indicate that math materials can be easily accessible to blind and VI students through i-Math and then, they can independently and comfortably study and practice their mathematics.
Several technology-assisted aids are available to help blind and visually impaired people perform their daily activities. The current research uses the state-of-the-art technology to enhance the ...utility of traditional navigational aids to produce solutions that are more reliable. In this regard, a white cane is no exception, which is supplemented with the existing technologies to design Electronic Travel Aids (ETAs), Electronic Orientation Aids (EOAs), and Position Locator Devices (PLDs). Although several review articles uncover the strengths and limitations of research contributions that extend traditional navigational aids, we find no review article that covers research contributions on a technology-assisted white cane. The authors attempt to fill this literature gap by reviewing the most relevant research articles published during 2010-2017 with the common objective of enhancing the utility of white cane with the existing technology.
The authors have collected the relevant literature published during 2010-17 by searching and browsing all the major digital libraries and publishers' websites. The inclusion/exclusion criteria were applied to select the research articles that are relevant to the topic of this review article, and all other irrelevant papers were excluded. Among the 577 (534 through database searching and 43 through other sources) initially screened papers, the authors collected 228 full-text articles, which after applying exclusion/inclusion criteria resulted in 36 papers that were included in the evaluation, comparison, and discussion. This also includes research articles of commercially available aids published before the specified range.
The findings show that the research trend is shifting towards developing a technology-assisted white cane solution that is applicable in both indoor and outdoor environments to aid blind users in navigation. In this regard, exploiting smartphones to develop low-cost and user-friendly navigation solution is among the best research opportunities to explore. In addition, the authors contribute a theoretical evaluation framework to compare and evaluate the state-of-the-art solutions, identify research trends and future directions.
Researchers have been in the quest to find out ways of enhancing the utility of white cane using existing technology. However, for a more reliable enhancement, the design should have user-centric characteristics. It should be portable, reliable, trust-worthy, lightweight, less costly, less power hungry, and require minimal training with special emphasis on its ergonomics and social acceptance. Smartphones, which are the ubiquitous and general-purpose portable devices, should be considered to exploit its capabilities in making technology-assisted white cane smarter and reliable.
There is an increasing need to develop new adaptive technologies and new wayfinding assistance systems for blind and visually impaired persons in order to improve their daily lives. To address this ...need, we propose in this paper to develop a new deep learning-based indoor wayfinding assistance system consisting of detecting landmark indoor signs. Assistive technologies used for blind and sighted persons used to support daily activities to improve social inclusion are developing very fast. Training and testing experiments were performed on the proposed indoor signage dataset. Through the experiments conducted, we demonstrated the efficiency of the proposed indoor wayfinding aid system. We obtained 93.45% as a mean average precision (mAP) of the proposed indoor wayfinding and signage detection system.
The representation of pictorial data by people who are blind and sight impaired has gathered momentum with research and development; however, little research has focused on the use of a screen layout ...to provide people who are blind and sight impaired users with the spatial orientation to create and reuse graphics. This article contributes an approach to navigating on the screen, manipulating computer graphics, and user-defined images. The technique described in this article enables features such as zooming, grouping, and drawing by calling primitive and user-defined shapes. It enables blind people to engage in and experience drawing and art production on their own. The navigation technique gives an initiative sense of autonomy with compass directions, makes it easy to learn, efficient to manipulate shape with a the simple drawing language, and takes less time to complete with system support features. An empirical evaluation was conducted to validate the suitability of the SETUP09 technique and to evaluate the accuracy, and efficiency of the navigation and drawing techniques proposed. The drawing experiment results confirmed high accuracy (88%) and efficiency among blind and visually impaired (BVI) users.
While it is common for blind and visually impaired (BVI) users to use mobile devices to search for information, little research has explored the accessibility issues they encounter in their ...interactions with information retrieval systems, in particular digital libraries (DLs). This study represents one of the most comprehensive research projects, investigating accessibility issues, especially help-seeking situations BVI users face in their DL search processes. One hundred and twenty BVI users were recruited to search for information in six DLs on four types of mobile devices (iPhone, iPad, Android phone, and Android tablet), and multiple data collection methods were employed: questionnaires, think-aloud protocols, transaction logs, and interviews. This paper reports part of a large-scale study, including the categories of help-seeking situations BVI users face in their interactions with DLs, focusing on seven types of help-seeking situations related to visual interactions on mobile platforms: difficulty finding a toggle-based search feature, difficulty understanding a video feature, difficulty navigating items on paginated sections, difficulty distinguishing collection labels from thumbnails, difficulty recognizing the content of images, difficulty recognizing the content of graphs, and difficulty interacting with multilayered windows. Moreover, corresponding design recommendations are also proposed: placing meaningful labels for icon-based features in an easy-to-access location, offering intuitive and informative video descriptions for video players, providing structure information about a paginated section, separating collection/item titles from thumbnail descriptions, incorporating artificial intelligence image/graph recognition mechanisms, and limiting screen reader interactions to active windows. Additionally, the limitations of the study and future research are discussed.
This article compares two methods of employing novice Web workers to author descriptions of science, technology, engineering, and mathematics images to make them accessible to individuals with visual ...and print-reading disabilities. The goal is to identify methods of creating image descriptions that are inexpensive, effective, and follow established accessibility guidelines. The first method explicitly presented the guidelines to the worker, then the worker constructed the image description in an empty text box and table. The second method queried the worker for image information and then used responses to construct a template-based description according to established guidelines. The descriptions generated through queried image description (QID) were more likely to include information on the image category, title, caption, and units. They were also more similar to one another, based on Jaccard distances of q-grams, indicating that their word usage and structure were more standardized. Last, the workers preferred describing images using QID and found the task easier. Therefore, explicit instruction on image-description guidelines is not sufficient to produce quality image descriptions when using novice Web workers. Instead, it is better to provide information about images, then generate descriptions from responses using templates.
We present in this paper the state of the art and an analysis of recent research work and achievements performed in the domain of AI-based and vision-based systems for helping blind and visually ...impaired people (BVIP). We start by highlighting the recent and tremendous importance that AI has acquired following the use of convolutional neural networks (CNN) and their ability to solve image classification tasks efficiently. After that, we also note that VIP have high expectations about AI-based systems as a possible way to ease the perception of their environment and to improve their everyday life. Then, we set the scope of our survey: we concentrate our investigations on the use of CNN or related methods in a vision-based system for helping BVIP. We analyze the existing surveys, and we study the current work (a selection of 30 case studies) using several dimensions such as acquired data, learned models, and human–computer interfaces. We compare the different approaches, and conclude by analyzing future trends in this domain.