RSSi-based visitor tracking in museums via cascaded AI classifiers and coloured graph representations

TL;DR

This paper introduces a novel RSSi-based visitor tracking method in museums that combines cascaded AI classifiers and coloured graph representations to achieve high accuracy with low antenna density.

Contribution

It presents a new approach that integrates ensemble localisers with museum topology encoding to improve indoor localisation accuracy in challenging conditions.

Findings

Achieves over 96% localisation accuracy in a real museum setting.

Significantly outperforms previous RSSi-based tracking methods.

Effective with low-density antenna deployments.

Abstract

Individual tracking of museum visitors based on portable radio beacons, an asset for behavioural analyses and comfort/performance improvements, is seeing increasing diffusion. Conceptually, this approach enables room-level localisation based on a network of small antennas (thus, without invasive modification of the existent structures). The antennas measure the intensity (RSSi) of self-advertising signals broadcasted by beacons individually assigned to the visitors. The signal intensity provides a proxy for the distance to the antennas and thus indicative positioning. However, RSSi signals are well-known to be noisy, even in ideal conditions (high antenna density, absence of obstacles, absence of crowd, ...). In this contribution, we present a method to perform accurate RSSi-based visitor tracking when the density of antennas is relatively low, e.g. due to technical constraints imposed by historic buildings. We combine an ensemble of "simple" localisers, trained based on ground-truth, with an encoding of the museum topology in terms of a total-coloured graph. This turns the localisation problem into a cascade process, from large to small scales, in space and in time. Our use case is visitors tracking in Galleria Borghese, Rome (Italy), for which our method manages >96% localisation accuracy, significantly improving on our previous work (J. Comput. Sci. 101357, 2021).