Traditional White Cane Research Articles

Reading Assistant for Visually Challenged Peoples with Advance Image Capturing Technique Using Machine Learning

Since blindness prevents a person from learning about their surroundings, it is difficult for them to independently navigate, recognise items, avoid hazards, and read. In this essay, we provide a ground-breaking system for visually impaired people who use assistive technology. The concept incorporates a camera, sensors, and effective image processing algorithms that use Raspberry Pi for object detection and obstacle avoidance. Ultrasonic sensors and the camera both measure the user's distance from the obstruction. The system consists of integrated reading help that first generates an audio response before converting images to text. The complete apparatus is small and light, and it can be easily and inexpensively mounted on a regular pair of eyeglasses. The entire system is affordable, easy to use, and can be attached to a regular pair of eyeglasses. It is also portable and lightweight. Ten people who are completely blind will be used to compare the performance of the suggested device to the traditional white cane. The evaluations are conducted in controlled environments intended to mimic day-to-day activities for blind persons. The findings show that the proposed device provides more accessibility, comfort, and simplicity of navigation for the blind when compared to the white cane.

Design and evaluation of two obstacle detection devices for visually impaired people

Smart devices can assist visually impaired individuals with self-guidance and safe mobility. This study presents two remarkable electronic devices, a smart belt and smart stick, that were designed and developed for obstacle detection in the path of visually impaired using the assistive technology options. They were designed with affordability, portability, and ease of use without requiring an internet connection. In an experimental test conducted with blind participants, the two smart devices were compared to the traditional white cane in terms of accuracy (obstacle avoidance) and usability (ease of use). Participants were randomly assigned obstacles and navigated the same path to test all tools. Based on the test and among evaluation, it was determined that the smart stick was the most user-friendly tool while the smart belt was found to be more accurate, and the two smart devices are a step forward in enhancing the mobility for visual impairments.

Deep learning based object detection and surrounding environment description for visually impaired people

Object detection, one of the most significant contributions of computer vision and machine learning, plays an immense role in identifying and locating objects in an image or a video. We recognize distinct objects and precisely get their information through object detection, such as their size, shape, and location. This paper developed a low-cost assistive system of obstacle detection and the surrounding environment depiction to help blind people using deep learning techniques. TensorFlow object detection API and SSDLite MobileNetV2 have been used to create the proposed object detection model. The pre-trained SSDLite MobileNetV2 model is trained on the COCO dataset, with almost 328,000 images of 90 different objects. The gradient particle swarm optimization (PSO) technique has been used in this work to optimize the final layers and their corresponding hyperparameters of the MobileNetV2 model. Next, we used the Google text-to-speech module, PyAudio, playsound, and speech recognition to generate the audio feedback of the detected objects. A Raspberry Pi camera captures real-time video where real-time object detection is done frame by frame with Raspberry Pi 4B microcontroller. The proposed device is integrated into a head cap, which will help visually impaired people to detect obstacles in their path, as it is more efficient than a traditional white cane. Apart from this detection model, we trained a secondary computer vision model and named it the “ambiance mode.” In this mode, the last three convolutional layers of SSDLite MobileNetV2 are trained through transfer learning on a weather dataset. The dataset comprises around 500 images from four classes: cloudy, rainy, foggy, and sunrise. In this mode, the proposed system will narrate the surrounding scene elaborately, almost like a human describing a landscape or a beautiful sunset to a visually impaired person. The performance of the object detection and ambiance description modes are tested and evaluated in a desktop computer and Raspberry Pi embedded system. Detection accuracy and mean average precision, frame rate, confusion matrix, and ROC curve measure the model's accuracy on both setups. This low-cost proposed system is believed to help visually impaired people in their day-to-day life.

Millimeter-Wave Radar Cane: A Blind People Aid With Moving Human Recognition Capabilities

This contribution presents an electronic travel aid for blind and visually-impaired people based on a millimeter wave radar and a traditional white-cane. It not only represents an advanced system able to warn the user of potential obstacles, but also discerns between human and nonhuman targets. Since real scenarios would likely have moving targets, a new range alignment technique has been proposed with the aim of detecting the tiny chest displacement due to the physiological activity as the key sign of the human presence. The proposed system is able to properly recognize humans in complex environments with multiple moving targets, thus providing to the user a complete set of information, namely presence, position and nature of the available targets. The operating principle and the effectiveness of the system are shown both by simulated case studies and by employing a 122 GHz radar board for carrying out suitable measurements.

An AI-Based Visual Aid With Integrated Reading Assistant for the Completely Blind

Blindness prevents a person from gaining knowledge of the surrounding environment and makes unassisted navigation, object recognition, obstacle avoidance, and reading tasks a major challenge. In this work, we propose a novel visual aid system for the completely blind. Because of its low cost, compact size, and ease-of-integration, Raspberry Pi 3 Model B+ has been used to demonstrate the functionality of the proposed prototype. The design incorporates a camera and sensors for obstacle avoidance and advanced image processing algorithms for object detection. The distance between the user and the obstacle is measured by the camera as well as ultrasonic sensors. The system includes an integrated reading assistant, in the form of the image-to-text converter, followed by an auditory feedback. The entire setup is lightweight and portable and can be mounted onto a regular pair of eyeglasses, without any additional cost and complexity. Experiments are carried out with 60 completely blind individuals to evaluate the performance of the proposed device with respect to the traditional white cane. The evaluations are performed in controlled environments that mimic real-world scenarios encountered by a blind person. Results show that the proposed device, as compared with the white cane, enables greater accessibility, comfort, and ease of navigation for the visually impaired.

Automated Hardware Module (Cane) for Visually Impaired Person to Detect Obstacles and Movement

Blindness can be termed as a visual disorder, in which an individual is unable to see the surrounding environment fully or partially due to some medical factors. In general cases it is observed that for a blind person to walk conveniently him /her uses traditional white blind cane, but most of the times this cane is not useful. In a surrounding which is not familiar, visually impaired person might get confused. So, this restricts their mobility. This hardware project is based on helping and guiding all the blind community. The blind stick is integrated with multiple sensors. The proposed module will reduce the number of accidents taking place with the visually blind community to a great extent.

Are electronic white canes better than traditional canes? A comparative study with blind and blindfolded participants

Visually impaired individuals often rely on assistive technologies such as white canes for independent navigation. Many electronic enhancements to the traditional white cane have been proposed. However, only a few of these proof-of-concept technologies have been tested with authentic users, as most studies rely on blindfolded non-visually impaired participants or no testing with participants at all. Experiments involving blind users are usually not contrasted with the traditional white cane. This study set out to compare an ultrasound-based electronic cane with a traditional white cane. Moreover, we also compared the performance of a group of visually impaired participants (N = 10) with a group of blindfolded participants without visual impairments (N = 31). The results show that walking speed with the electronic cane is significantly slower compared to the traditional white cane. Moreover, the results show that the performance of the participants without visual impairments is significantly slower than for the visually impaired participants. No significant differences in obstacle detection rates were observed across participant groups and device types for obstacles on the ground, while 79% of the hanging obstacles were detected by the electronic cane. The results of this study thus suggest that electronic canes present only one advantage over the traditional cane, namely in its ability to detect hanging obstacles, at least without prolonged practice. Next, blindfolded participants are insufficient substitutes for blind participants who are expert cane users. The implication of this study is that research into digital white cane enhancements should include blind participants. These participants should be followed over time in longitudinal experiments to document if practice will lead to improvements that surpass the performance achieved with traditional canes.

Design and Construction of Electronic Aid for Visually Impaired People

The NavGuide is a novel electronic device to assist visually impaired people with obstacle free path-finding. The highlight of the NavGuide system is that it provides simplified information on the surrounding environment and deduces priority information without causing information overload. The priority information is provided to the user through vibration and audio feedback mechanisms. The proof-of-concept device consists of a low power embedded system with ultrasonic sensors, vibration motors, and a battery. To test the effectiveness of the NavGuide system in daily-life mobility of visually impaired people, we performed an evaluation using 70 blind people of the “school & home for the blind.” All evaluations were performed in controlled, real-world test environments with the NavGuide and traditional white cane. The evaluation results show that NavGuide is a useful aid in the detection of obstacles, wet floors, and ascending staircases and its performance is better than that of a white cane.

An Electromagnetic Sensor Prototype to Assist Visually Impaired and Blind People in Autonomous Walking

The feasibility of an electromagnetic sensor to assist the autonomous walking of visually impaired and blind users is demonstrated in this paper. It is known that the people affected by visual diseases usually walk assisted by some supports, among which the white cane is the most common. Our idea consists in applying a microwave radar on the traditional white cane making aware the user about the presence of an obstacle in a wider and safer range. Compared to the already existing electronic travel aids devices, the proposed system exhibits better performance, noise tolerance, and reduced dimensions. In the following, the latest developments of this research activity are presented, with special concern for the miniaturization of circuit board and antennas. A laboratory prototype has been designed and realized and the first test results of obstacle detection are hereby shown to demonstrate the effectiveness of the system.

A Haptic Solution to Assist Visually Impaired in Mobility Tasks

Electronic travel aids are used for detecting obstacles, identifying services, and, generally, obtaining useful information from the surroundings, thus enabling a safe and effective exploitation of the environment. A drawback is unnatural codification, which may lead to usability concerns. This paper introduces a haptic device aimed to provide the user with information on the presence of obstacles inside the environment. The haptic interface is intended to reproduce the stimuli provided by a traditional white cane, without any contact with the environment. A prototype, implemented through a short cane with an embedded smart sensing strategy and an active handle, is presented. Twenty-five blindfolded normally sighted users participated to assess system performance in detecting obstacles and correctly conveying their position by the haptic interface. With respect to detecting obstacles and their positions, the average values of the sensitivity in the case of left, center, and right positioned obstacles are 0.735, 0.803, and 0.830, while the specificity values are 0.924, 0.835, and 0.827, respectively.

Wearable Virtual White Cane Network for navigating people with visual impairment.

Navigating the world with visual impairments presents inconveniences and safety concerns. Although a traditional white cane is the most commonly used mobility aid due to its low cost and acceptable functionality, electronic traveling aids can provide more functionality as well as additional benefits. The Wearable Virtual Cane Network is an electronic traveling aid that utilizes ultrasound sonar technology to scan the surrounding environment for spatial information. The Wearable Virtual Cane Network is composed of four sensing nodes: one on each of the user's wrists, one on the waist, and one on the ankle. The Wearable Virtual Cane Network employs vibration and sound to communicate object proximity to the user. While conventional navigation devices are typically hand-held and bulky, the hands-free design of our prototype allows the user to perform other tasks while using the Wearable Virtual Cane Network. When the Wearable Virtual Cane Network prototype was tested for distance resolution and range detection limits at various displacements and compared with a traditional white cane, all participants performed significantly above the control bar (p < 4.3 × 10(-5), standard t-test) in distance estimation. Each sensor unit can detect an object with a surface area as small as 1 cm(2) (1 cm × 1 cm) located 70 cm away. Our results showed that the walking speed for an obstacle course was increased by 23% on average when subjects used the Wearable Virtual Cane Network rather than the white cane. The obstacle course experiment also shows that the use of the white cane in combination with the Wearable Virtual Cane Network can significantly improve navigation over using either the white cane or the Wearable Virtual Cane Network alone (p < 0.05, paired t-test).

Design, development, and clinical evaluation of the electronic mobility cane for vision rehabilitation.

This paper proposes a new electronic mobility cane (EMC) for providing obstacle detection and way-finding assistance to the visually impaired people. The main feature of this cane is that it constructs the logical map of the surrounding environment to deduce the priority information. It provides a simplified representation of the surrounding environment without causing any information overload. It conveys this priority information to the subject by using intuitive vibration, audio or voice feedback. The other novel features of the EMC are staircase detection and nonformal distance scaling scheme. It also provides information about the floor status. It consists of a low power embedded system with ultrasonic sensors and safety indicators. The EMC was subjected to series of clinical evaluations in order to verify its design and to assess its ability to assist the subjects in their daily-life mobility. Clinical evaluations were performed with 16 totally blind and four low vision subjects. All subjects walked controlled and the real-world test environments with the EMC and the traditional white cane. The evaluation results and significant scores of subjective measurements have shown the usefulness of the EMC in vision rehabilitation services.

The "EyeCane", a new electronic travel aid for the blind: Technology, behavior & swift learning.

Independent mobility is one of the most pressing problems facing people who are blind. We present the EyeCane, a new mobility aid aimed at increasing perception of environment beyond what is provided by the traditional White Cane for tasks such as distance estimation, navigation and obstacle detection. The "EyeCane" enhances the traditional White Cane by using tactile and auditory output to increase detectable distance and angles. It circumvents the technical pitfalls of other devices, such as weight, short battery life, complex interface schemes, and slow learning curve. It implements multiple beams to enables detection of obstacles at different heights, and narrow beams to provide active sensing that can potentially increase the user's spatial perception of the environment. Participants were tasked with using the EyeCane for several basic tasks with minimal training. Blind and blindfolded-sighted participants were able to use the EyeCane successfully for distance estimation, simple navigation and simple obstacle detection after only several minutes of training. These results demonstrate the EyeCane's potential for mobility rehabilitation. The short training time is especially important since available mobility training resources are limited, not always available, and can be quite expensive and/or entail long waiting periods.

Location based Services for the Blind Supported by RFID Technology

Nowadays, navigation systems are widely used to find the correct path, or the quickest, between two places. These systems use the Global Positioning System (GPS) and only work well in outdoor environment since GPS signals cannot easily penetrate and/or are greatly degraded inside of buildings. Several technologies have been proposed to make navigation inside of buildings possible. One such technology is Radio-Frequency Identification (RFID). In the case of outside environments, some hybrid systems have been proposed that use GPS as main information source and RFID for corrections and location error minimization. In this article we propose a navigation system that uses RFID as the main technology to guide people with visual impairment in unfamiliar environments, both indoor and outdoor, complementing the traditional white cane and providing information about the user's geographical context.

A smartphone-based virtual white cane

The objective of our research was to develop assistive technology for visually impaired people, with a high appreciation for the human potential to achieve, to learn, and to achieve goals. In this document, we describe a virtual white cane made of a combination of a Smartphone and a laser pointer. In our device, the laser pointer beam reflection is captured by the Smartphone camera. The distance from the virtual white cane to the reflection is computed through active triangulation. Then, a personalized vibration, the magnitude of which corresponds to distance, is generated in the Smartphone. In this way, the users receive information that could prevent collisions with obstacles in the environment. Our contributions include the development of a virtual white cane around a Smartphone and other off-the-shelf accessories and a methodology to provide personalized vibratory feedback to the user. Our experiments show that to navigate, our instrument is better option, in terms of travel time, that the use of the hands. However, the travel time is still better using a traditional white cane than our instrument.

Blind Navigation Support System based on Microsoft Kinect

This paper presents a system which extends the use of the traditional white cane by the blind for navigation purposes in indoor environments. Depth data of the scene in front of the user is acquired using the Microsoft Kinect sensor which is then mapped into a pattern representation. Using neural networks, the proposed system uses this information to extract relevant features from the scene, enabling the detection of possible obstacles along the way. The results show that the neural network is able to correctly classify the type of pattern presented as input.