Optimizing Fiducial Marker Placement for Improved Visual Localization

TL;DR

This paper introduces a novel framework and algorithm for automatically optimizing fiducial marker placement in scenes to enhance visual localization accuracy, outperforming traditional manual placement methods.

Contribution

The paper presents a new camera localizability model and a greedy algorithm for optimized marker placement, along with a simulation framework for testing in synthetic scenes.

Findings

Improved localization rate by up to 20% across four scenes.

Demonstrated effectiveness of the optimized placement algorithm.

Framework integrates natural features and fiducial markers for better localization.

Abstract

Adding fiducial markers to a scene is a well-known strategy for making visual localization algorithms more robust. Traditionally, these marker locations are selected by humans who are familiar with visual localization techniques. This paper explores the problem of automatic marker placement within a scene. Specifically, given a predetermined set of markers and a scene model, we compute optimized marker positions within the scene that can improve accuracy in visual localization. Our main contribution is a novel framework for modeling camera localizability that incorporates both natural scene features and artificial fiducial markers added to the scene. We present optimized marker placement (OMP), a greedy algorithm that is based on the camera localizability framework. We have also designed a simulation framework for testing marker placement algorithms on 3D models and images generated from synthetic scenes. We have evaluated OMP within this testbed and demonstrate an improvement in the localization rate by up to 20 percent on four different scenes.