SPDAS: A YOLOv5-Powered Smart Pothole Detection and Blind Assistance System Grounded in the RDD2022 Global Road Damage Benchmark

Author(s)	Mr. Saad Ahmad Khan, Mr. Alok Gupta
Country	India
Abstract	Every day, blind pedestrians navigate streets full of hidden dangers — broken pavements, puddles, and sunken manhole covers that a white cane simply can't detect in time. We built SPDAS to change that. SPDAS turns an ordinary smartphone camera into a real-time eyes-on-the-ground assistant. It watches the road ahead, spots hazards instantly, and speaks up — no internet needed. Under the hood, it uses a lightweight AI model trained on nearly 47,000 real road images from six countries, with a special step to handle dark or poorly lit conditions. When a hazard is detected, the system figures out how close it is and where it sits in your path, then tells you in plain spoken words. It runs smoothly on a regular laptop CPU, processes nearly 30 frames per second, and delivers reliable results. The Android app is ready to use today — built on hardware people already own, making road safety more accessible without costing a fortune.
Keywords	pothole detection, blind pedestrian navigation, YOLOv5, RDD2022, CLAHE, offline text-to-speech, Flutter, road damage detection, real-time assistive system
Field	Engineering
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-25

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research