Enhanced Normalized Mutual Information for Localization in Noisy Environments

TL;DR

This paper introduces an enhanced normalized mutual information method for vehicle localization using inexpensive cameras in noisy environments, improving accuracy with statistical signal processing techniques.

Contribution

It extends existing mutual information schemes by utilizing shade likelihoods, enabling more reliable localization with low-cost sensors in noisy conditions.

Findings

Significant performance improvements demonstrated in simulations.

Validation on Ford image dataset confirms effectiveness.

Enhanced robustness in noisy environments.

Abstract

Fine localization is a crucial task for autonomous vehicles. Although many algorithms have been explored in the literature for this specific task, the goal of getting accurate results from commodity sensors remains a challenge. As autonomous vehicles make the transition from expensive prototypes to production items, the need for inexpensive, yet reliable solutions is increasing rapidly. This article considers scenarios where images are captured with inexpensive cameras and localization takes place using pre-loaded fine maps of local roads as side information. The techniques proposed herein extend schemes based on normalized mutual information by leveraging the likelihood of shades rather than exact sensor readings for localization in noisy environments. This algorithmic enhancement, rooted in statistical signal processing, offers substantial gains in performance. Numerical simulations are used to highlight the benefits of the proposed techniques in representative application scenarios. Analysis of a Ford image set is performed to validate the core findings of this work.