Visual Place Recognition

TL;DR

This paper investigates a visual place recognition algorithm using Hidden Markov Model (HMM) filter and smoother to improve vehicle localization accuracy in urban environments, enhancing autonomous driving safety.

Contribution

It introduces a novel application of HMM filter and smoother for visual place recognition and compares their effectiveness in urban traffic scenarios.

Findings

HMM smoother outperforms HMM filter in prediction accuracy

Constructed traffic situation models for Canberra city

Validated the effectiveness of HMM-based algorithms in vehicle positioning

Abstract

Visual position recognition affects the safety and accuracy of automatic driving. To accurately identify the location, this paper studies a visual place recognition algorithm based on HMM filter and HMM smoother. Firstly, we constructed the traffic situations in Canberra city. Then the mathematical models of the HMM filter and HMM smoother were performed. Finally, the vehicle position was predicted based on the algorithms. Experiment results show that HMM smoother is better than HMM filter in terms of prediction accuracy.