Efficient Pose Tracking from Natural Features in Standard Web Browsers

TL;DR

This paper introduces a real-time natural feature tracking system for web browsers using HTML5 and WebAssembly, enabling efficient augmented reality experiences on tablets and smartphones without specialized hardware.

Contribution

It presents a novel web-based natural feature tracking pipeline that achieves real-time performance on standard devices, advancing browser-based augmented reality capabilities.

Findings

Achieves up to 60 Hz tracking on tablets

Operates at 25 Hz on smartphones

Demonstrates practical web-based AR applications

Abstract

Computer Vision-based natural feature tracking is at the core of modern Augmented Reality applications. Still, Web-based Augmented Reality typically relies on location-based sensing (using GPS and orientation sensors) or marker-based approaches to solve the pose estimation problem. We present an implementation and evaluation of an efficient natural feature tracking pipeline for standard Web browsers using HTML5 and WebAssembly. Our system can track image targets at real-time frame rates tablet PCs (up to 60 Hz) and smartphones (up to 25 Hz).