Smart Glasses for Visually Impaired

Abstract The novel IoT-based assistive device presented in this research is intended to increase the mobility and independence of people who are blind or visually impaired. The wearable Smart Glasses system incorporates real-time object detection, obstacle avoidance, and audio feedback to facilitate users' navigation in unfamiliar environments. With the use of camera modules, ultrasonic sensors, Raspberry Pi, and sophisticated algorithms such as YOLO (You Only Look Once) for object identification, the suggested system provides an affordable and effective means of improving the lives of visually impaired individuals The primary goal of this system is to enable visually impaired users to navigate safely, avoid collisions, and recognize nearby objects. The system provides audio feedback for object recognition, positional information (left, right, or front), and buzzer alerts for obstacles that are too close (less than 30 cm). Keywords: Internet of Things, smart glasses, text to speech, object detection, obstacle avoidance, Raspberry Pi, ultrasonic sensors, visual impairment, and YOLO. 1. Introduction Over 285 million individuals worldwide suffer from visual impairment, which makes it difficult for them to independently move and interact with their environment. The current alternatives, such white canes or guiding dogs, can be expensive or difficult to maintain and only provide a limited amount of support. While some respite has been offered by the development of smartphone applications and electronic travel aids (ETAs), many of these tools lack real-time object detection and practical integration with everyday activities. This study presents an IoT based, low-cost, user-friendly Smart Glasses system designed to give visually impaired people dependable mobility and navigational aid. 2. Existing System Traditional mobility aids like white canes provide tactile feedback but are limited to identifying impediments within arm’s reach. Although they are more expensive and need ongoing training and care, guide dogs provide superior mobility aid. While some ETAs use wearable sensors and handheld ultrasonic devices to identify obstacles, they frequently can't recognize objects in real time. While smartphone based systems may identify items using camera apps, they need users to hold and direct their devices, which can be awkward in situations when things are moving quickly. Although the current iterations of smart glasses have promise, they are frequently large, expensive, and have limited features. 3. Problem Statement & Objectives A. Problem Statement Visually handicapped individuals confront difficulty when navigating unfamiliar areas due to a lack of realtime object detection and obstacle avoidance solutions. Limited mobility and independence result from existing solutions' inability to offer comprehensive support in locating and interpreting surroundings. B. Objectives The main objective of this project are as follows: Real-Time Object Detection and Identification: Recognize and identify objects in the environment using a YOLOv8n object detection model. Distance Measurement: Measure the distance of obstacles using an ultrasonic sensor. Object Position Awareness: Provide information on whether objects are located on the left, right, or front of the user. Audio Feedback: Announce the name of the detected objects through an audio system. Proximity Alert: Trigger a buzzer alert and provide an audio warning if an obstacle is within 30 cm of the user. Low Cost & Wearable: Develop an affordable, wearable, and compact device that can be used daily. 4. Literature Review As an advancement over more conventional assistive devices like guide dogs and white canes, smart glasses have become a popular choice for the blind and visually impaired. These conventional methods lack real-time object recognition, although they do offer basic obstacle detection. Recent innovations, such as wearable sensors and handheld ultrasonic devices, have boosted navigation but still fall short in giving total help. Smart glasses were presented for partial navigation support in studies by Nazim et al. (2022) and Yang et al. (2018), however these devices are still expensive or have limited capability. Using cutting-edge algorithms such as YOLO for real-time object identification is a viable way to make smart glasses that are more efficient and less expensive while yet offering real-time feedback and enhanced mobility. Paper 1, focuses on creating a guidance system that wears wearable smart glasses equipped with sensors to continuously take pictures of the surroundings. The smart glass has a processor that processes the photos that are taken, detecting things to provide the user with information about the image's outcome and a more thorough understanding of the process. In paper 2 Deep learning-based smart glasses application system for individuals with visual impairments. By uploading images to our backend object recognition system using the smart glasses' camera function, the system can provide visually impaired persons with voice replies about the items in front of them. It can then download text descriptions of the results and utilize the text-tospeech feature. In paper 3, They introduce a novel smart glass system designed for anyone with low eyesight or blindness. It can be challenging for those with visual impairments to interact with their surroundings. The blind and visually challenged primarily use their other senses—such as touch, hearing, and smell—to perceive and comprehend their environment. The smart glass in 4 employs ultrasonic sensors to communicate real-time information to the Raspberry Pi about objects or persons in front of it. With the help of these smart glasses, one may identify both the object's distance from the user and the image by using the database. Multiple detections are also feasible. In paper 5 a special smart eyewear that helps those with vision impairments overcome their travel challenges. With the help of an ultrasonic sensor and a microcontroller, it is able to precisely identify obstacles and estimate distances. P. N. Karthikayan and R. Pushpakumar in 6 carries out the implementation of two features: traffic light detection and currency recognition. An object detection model, image processing methods, and a convolution neutral network (CNN) make up the configuration of a machine learning (ML) model. The idea of the research work in 7 aims to create a sensor-equipped auxiliary device that can be attached to regular spectacles. The device's built-in camera continuously takes pictures of the surrounding environment. In research 8, They offer a novel wearable glass security system for people with vision impairments or blindness that is based on microprocessor technology. In order to improve the lives of those who are blind or visually impaired by giving them confidence and independence in managing their finances and shopping, the design places a strong emphasis on affordability and user accessibility in paper 9. Paper 10 suggests a wearable medication recognition device for visually challenged individuals that is based on deep learning. The wearable smart glasses, wearable drug pill detection device worn on the waist, mobile device application, and cloud-based management platform comprise the suggested system. 5. Proposed System The suggested method transforms mobility assistance for those with vision impairments by integrating cutting-edge detecting technologies into Smart Glasses. The central component is a Raspberry Pi 4 Model B, which uses the YOLO method to interpret video input from the Raspberry Pi Camera Module V2 in real-time object detection. Obstacle distance is measured by an HC-SR04 ultrasonic sensor, which sends out timely alerts. Users are guaranteed to receive constant updates on their surroundings without the need for manual intervention thanks to the integration of obstacle avoidance and object detection. This system provides a workable way to increase independence and mobility, and it is made to be inexpensive and simple to use. Fig.1: Proposed System 6. Working Operation 1.Object Detection: Live photos or videos of the user's environment are continuously captured by the Raspberry Pi Camera Module V2. The YOLO (You Only Look Once) algorithm is a cutting-edge, realtime object recognition technique that is used to process these photos. YOLO can detect several items within the camera’s range of view, recognizing them based on pre-trained data. For instance, the system is able to identify objects in the user's route such as doors, chairs, and passersby. Real-time picture processing by the YOLO method enables the system to swiftly recognize and name things in the user's immediate environment. The user has to know this information in order to comprehend their immediate environment.6 2.Obstacle Detection: The user's front-facing obstacles' distance is measured by the HC-SR04 ultrasonic sensor. It generates ultrasonic waves, which, when encountering an obstruction, return back. The sensor measures the time it takes for the waves to return in order to compute the obstacle's distance. If an object is identified within a particular threshold (for instance, within 1-2 meters), the system immediately informs the user to avoid potential collisions. This function is essential for identifying obstructions that the camera could miss, like items that are too small or too low for the YOLO algorithm to detect.7 3.Data processing: The camera's picture data and the ultrasonic sensor's distance data are both processed by the Raspberry Pi. Because the YOLO algorithm operates in real-time, objects are consistently recognized and categorized. In addition, the ultrasonic sensor alerts the user in real time regarding the proximity of impediments. This data is integrated by the Raspberry Pi to provide complete situational awareness.[8