A Framework for Devising, Evaluating and Fine-tuning Indoor Tracking Algorithms

TL;DR

This paper introduces MobiXIM, a comprehensive framework designed to standardize the development, evaluation, and fine-tuning of indoor tracking algorithms, addressing current challenges in reproducibility and diverse methodologies.

Contribution

The paper presents MobiXIM, a novel plugin-based framework that facilitates collaborative development and systematic evaluation of indoor tracking systems.

Findings

Achieved 4 m positioning accuracy with the proposed ITS

Improved accuracy by up to 33% over baseline algorithms

Demonstrated the framework's effectiveness with wireless, inertial, and collaborative ITS

Abstract

In recent years, we have observed a growing interest in Indoor Tracking Systems (ITS) for providing location-based services indoors. This is due to the limitations of Global Navigation and Satellite Systems, which do not operate in non-line-of-sight environments. Depending on their architecture, ITS can rely on expensive infrastructure, accumulate errors, or be challenging to evaluate in real-life environments. Building an ITS is a complex process that involves devising, evaluating and fine-tuning tracking algorithms. This process is not yet standard, as researchers use different types of equipment, deployment environments, and evaluation metrics. Therefore, it is challenging for researchers to build novel tracking algorithms and for the research community to reproduce the experiments. To address these challenges, we propose MobiXIM, a framework that provides a set of tools for devising, evaluating and fine-tuning tracking algorithms in a structured manner. For devising tracking algorithms, MobiXIM introduces a novel plugin architecture, allowing researchers to collaborate and extend existing algorithms. We assess our framework by building an ITS encompassing the key elements of wireless, inertial, and collaborative ITS. The proposed ITS achieves a positioning accuracy of 4 m, which is an improvement of up to 33% compared to a baseline Pedestrian Dead Reckoning algorithm.