SMARTGUIDE: Revolutionizing the Depth and Dependability of Vision-Impaired Navigation
| dc.contributor.author | Gandham, Rishith | en |
| dc.contributor.committeechair | Meng, Na | en |
| dc.contributor.committeemember | Gipe, Andrew | en |
| dc.contributor.committeemember | Borunda Monsivais, Luis Ricardo | en |
| dc.contributor.committeemember | Brown, Dwayne Christian | en |
| dc.contributor.department | Computer Science and#38; Applications | en |
| dc.date.accessioned | 2025-01-04T09:00:33Z | en |
| dc.date.available | 2025-01-04T09:00:33Z | en |
| dc.date.issued | 2025-01-03 | en |
| dc.description.abstract | Globally, over 2.2 billion people face vision impairment, necessitating innovative solutions for safe, independent navigation. Traditional aids like canes, guide dogs, and GPS offer basic support but lack the sophistication to provide contextual understanding, precise navigation, or real-time hazard alerts. This project presents SmartGuide, a mobile app designed to enhance the independence of visually impaired users through AI-driven features. SmartGuide offers three main functions: (1) Smart Vision, using the GPT-4 Vision API to deliver spoken feedback about surroundings; (2) Navigation, combining QR code detection via YOLO with ZoeDepth for depth estimation, guiding users to destinations through the shortest path calculated by Dijkstra's algorithm; and (3) Obstacle Detection and Alerts, where YOLO identifies obstacles, and ZoeDepth estimates their distance to inform users of potential hazards. By adapting its responses based on user feedback, SmartGuide provides personalized, reliable guidance that empowers visually impaired individuals to navigate with confidence and safety, advancing the field of accessible technology. | en |
| dc.description.abstractgeneral | Navigating unfamiliar or crowded spaces is a major challenge for visually impaired individuals, who often rely on canes, guide dogs, or GPS tools. While useful, these aids offer only limited guidance and do not provide detailed information about surroundings, directions, or nearby obstacles. SmartGuide is a mobile application designed to address these gaps, enabling visually impaired users to navigate more independently and safely. SmartGuide includes three main features: Smart Vision, which gives audio feedback about the user's surroundings; Navigation, which uses QR codes and depth estimation to guide users to destinations along the shortest path; and Obstacle Alerts that detects obstacles, warning users of potential hazards. Using advanced AI technologies and feedback from visually impaired users, SmartGuide delivers clear, actionable guidance that supports confident, safe movement in both familiar and new environments. This research-driven tool demonstrates how technology can enhance accessibility, making navigation easier and safer for those with vision impairment. | en |
| dc.description.degree | Master of Science | en |
| dc.format.medium | ETD | en |
| dc.identifier.other | vt_gsexam:42232 | en |
| dc.identifier.uri | https://hdl.handle.net/10919/123896 | en |
| dc.language.iso | en | en |
| dc.publisher | Virginia Tech | en |
| dc.rights | In Copyright | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.subject | Indoor Navigation | en |
| dc.subject | Visually Impaired | en |
| dc.subject | Computer Vision | en |
| dc.title | SMARTGUIDE: Revolutionizing the Depth and Dependability of Vision-Impaired Navigation | en |
| dc.type | Thesis | en |
| thesis.degree.discipline | Computer Science & Applications | en |
| thesis.degree.grantor | Virginia Polytechnic Institute and State University | en |
| thesis.degree.level | masters | en |
| thesis.degree.name | Master of Science | en |