The PASCAL Visual Object Classes Challenge

The development of walking assistants for visually impaired people has become a prominent research area due to the rapid growth of these individuals in recent decades. Although numerous frameworks have been developed to aid visually impaired people, a considerable portion of these is limited in their scopes. In this review, we exhibit a similar review of walking assistants for visually impaired people to demonstrate the advancement of such technologies. This review discusses the recent innovative technologies developed for the visually impaired to aid them in walking with their merits and demerits. With the help of this review, a schema is drawn for upcoming development in the field of sensors, computer vision, and smartphone-based walking assistants. This review aims to present the majority of the issues of such frameworks to serve as a basis for different researchers to develop walking assistants that ensure movability and safety of visually impaired people.

Developing Walking Assistants for Visually Impaired People: A Review

Over the last decades, the development of navigation devices capable of guiding the blind through indoor and/or outdoor scenarios has remained a challenge. In this context, this paper’s objective is to provide an updated, holistic view of this research, in order to enable developers to exploit the different aspects of its multidisciplinary nature. To that end, previous solutions will be briefly described and analyzed from a historical perspective, from the first “Electronic Travel Aids” and early research on sensory substitution or indoor/outdoor positioning, to recent systems based on artificial vision. Thereafter, user-centered design fundamentals are addressed, including the main points of criticism of previous approaches. Finally, several technological achievements are highlighted as they could underpin future feasible designs. In line with this, smartphones and wearables with built-in cameras will then be indicated as potentially feasible options with which to support state-of-art computer vision solutions, thus allowing for both the positioning and monitoring of the user’s surrounding area. These functionalities could then be further boosted by means of remote resources, leading to cloud computing schemas or even remote sensing via urban infrastructure.

https://www.mdpi.com/1424-8220/19/15/3404/pdf

Navigation Systems for the Blind and Visually Impaired: Past Work, Challenges, and Open Problems.

Assistive devices for visually impaired people (VIP) which support daily traveling and improve social inclusion are developing fast. Most of them try to solve the problem of navigation or obstacle avoidance, and other works focus on helping VIP to recognize their surrounding objects. However, very few of them couple both capabilities (i.e., navigation and recognition). Aiming at the above needs, this paper presents a wearable assistive device that allows VIP to (i) navigate safely and quickly in unfamiliar environment, and (ii) to recognize the objects in both indoor and outdoor environments. The device consists of a consumer Red, Green, Blue and Depth (RGB-D) camera and an Inertial Measurement Unit (IMU), which are mounted on a pair of eyeglasses, and a smartphone. The device leverages the ground height continuity among adjacent image frames to segment the ground accurately and rapidly, and then search the moving direction according to the ground. A lightweight Convolutional Neural Network (CNN)-based object recognition system is developed and deployed on the smartphone to increase the perception ability of VIP and promote the navigation system. It can provide the semantic information of surroundings, such as the categories, locations, and orientations of objects. Human–machine interaction is performed through audio module (a beeping sound for obstacle alert, speech recognition for understanding the user commands, and speech synthesis for expressing semantic information of surroundings). We evaluated the performance of the proposed system through many experiments conducted in both indoor and outdoor scenarios, demonstrating the efficiency and safety of the proposed assistive system.

Wearable Travel Aid for Environment Perception and Navigation of Visually Impaired People

The development of navigation tools for people who are visually impaired had become an important concern in the research area of assistive technologies. This paper gives a comprehensive review of d...

https://www.tandfonline.com/doi/pdf/10.1080/02564602.2020.1819893

Tools and Technologies for Blind and Visually Impaired Navigation Support: A Review

Visually impaired people are often unaware of dangers in front of them, even in familiar environments. Furthermore, in unfamiliar environments, such people require guidance to reduce the risk of colliding with obstacles. This study proposes a simple smartphone-based guiding system for solving the navigation problems for visually impaired people and achieving obstacle avoidance to enable visually impaired people to travel smoothly from a beginning point to a destination with greater awareness of their surroundings. In this study, a computer image recognition system and smartphone application were integrated to form a simple assisted guiding system. Two operating modes, online mode and offline mode, can be chosen depending on network availability. When the system begins to operate, the smartphone captures the scene in front of the user and sends the captured images to the backend server to be processed. The backend server uses the faster region convolutional neural network algorithm or the you only look once algorithm to recognize multiple obstacles in every image, and it subsequently sends the results back to the smartphone. The results of obstacle recognition in this study reached 60%, which is sufficient for assisting visually impaired people in realizing the types and locations of obstacles around them.

Simple Smartphone-Based Guiding System for Visually Impaired People

Preserving privacy of online digital physiological signals using blind and reversible steganography.

This study proposes a modular data glove system to accurately and reliably capture hand kinematics. This data glove system’s modular design enhances its flexibility. It can provide the hand’s angular velocities, accelerations, and joint angles to physicians for adjusting rehabilitation treatments. Three validations—raw data verification, static angle verification, and dynamic angle verification—were conducted to verify the reliability and accuracy of the data glove. Furthermore, to ensure the wearability of the data glove, 15 healthy participants and 15 participants with stroke were recruited to test the data glove and fill out a questionnaire. The errors of the finger ROMs obtained from the fusion algorithm were less than 2°, proving that the fusion algorithm can measure the wearer’s range of motion accurately. The result of the questionnaire shows the participants’ high satisfaction with the data glove. Moreover, a comparison between the proposed data glove and related research shows that the proposed data glove is superior to other data glove systems.

/pdf/a-modular-data-glove-system-for-finger-and-hand-motion-4juf8r347d.pdf

A Modular Data Glove System for Finger and Hand Motion Capture Based on Inertial Sensors

Energy expenditure (EE) monitoring is crucial to tracking physical activity (PA). Accurate EE monitoring may help people engage in adequate activity and therefore avoid obesity and reduce the risk of chronic diseases. This study proposes a depth-camera-based system for EE estimation of PA in gyms. Most previous studies have used inertial measurement units for EE estimation. By contrast, the proposed system can be used to conveniently monitor subjects’ treadmill workouts in gyms without requiring them to wear any devices. A total of 21 subjects were recruited for the experiment. Subjects’ skeletal data acquired using the depth camera and oxygen consumption data simultaneously obtained using the K4b2 device were used to establish an EE predictive model. To obtain a robust EE estimation model, depth cameras were placed in the side view, rear side view, and rear view. A comparison of five different predictive models and these three camera locations showed that the multilayer perceptron model was the best predictive model and that placing the camera in the rear view provided the best EE estimation performance. The measured and predicted metabolic equivalents of task exhibited a strong positive correlation, with r = 0.94 and coefficient of determination r 2 = 0.89. Furthermore, the mean absolute error was 0.61 MET, mean squared error was 0.67 MET, and root mean squared error was 0.76 MET. These results indicate that the proposed system is handy and reliable for monitoring user's EE when performing treadmill workouts.

Pei-Ying Chiang

Papers

Simple Smartphone-Based Guiding System for Visually Impaired People

Preserving privacy of online digital physiological signals using blind and reversible steganography.

A Modular Data Glove System for Finger and Hand Motion Capture Based on Inertial Sensors

Depth-Camera-Based System for Estimating Energy Expenditure of Physical Activities in Gyms