Topological and Statistical Behavior Classifiers for Tracking Applications

TL;DR

This paper presents a unified approach combining topological data analysis, statistical modeling, and machine learning for target tracking, improving behavioral classification in complex scenarios.

Contribution

It introduces a novel framework integrating topological features with statistical models and existing classification methods for enhanced tracking accuracy.

Findings

Effective encoding of behavioral information using topological features

Successful application on synthetic vehicular data demonstrating improved classification

Integration of topological analysis within the tracking process enhances robustness

Abstract

We introduce the first unified theory for target tracking using Multiple Hypothesis Tracking, Topological Data Analysis, and machine learning. Our string of innovations are 1) robust topological features are used to encode behavioral information, 2) statistical models are fitted to distributions over these topological features, and 3) the target type classification methods of Wigren and Bar Shalom et al. are employed to exploit the resulting likelihoods for topological features inside of the tracking procedure. To demonstrate the efficacy of our approach, we test our procedure on synthetic vehicular data generated by the Simulation of Urban Mobility package.