The Ad-free city - A technical proof-of-concept for real-time detection and blocking of advertisements using AR technology

Abstract

Overexposure to advertisements in urban environments contributes to visual clutter, information overload, and cognitive strain. While digital environments offer tools to filter ads, equivalent solutions for physical spaces are limited. This thesis explores the feasibility of using Meta Quest 3 and Augmented Reality to develop a proof-of-concept system for real-time advertisement filtering in urban environments. The system combines object detection, optical character recognition, and semantic text classification to distinguish commercial advertisements from socially relevant information. An online survey (N = 122) was conducted to examine user attitudes toward ad filtering and preferred visualization methods. The project is evaluated as a technical proof-of-concept in terms of detection accuracy, performance, and safety. Results show that a modular pipeline can successfully identify and classify advertisements, but hardware limitations, geographical constraints, and the lack of a formal user study mean the system remains a proof-of-concept rather than a deployable product.