NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

TL;DR

This paper introduces the NYU-VPR benchmark dataset for long-term visual place recognition, analyzing how view direction and data anonymization affect VPR performance in urban environments.

Contribution

It provides a new large-scale dataset and benchmark for studying long-term VPR, highlighting the impact of view direction and anonymization on recognition accuracy.

Findings

Side views are more challenging for current VPR algorithms.

Data anonymization has minimal impact on VPR performance.

Benchmark results offer insights into factors affecting long-term VPR.

Abstract

Visual place recognition (VPR) is critical in not only localization and mapping for autonomous driving vehicles, but also in assistive navigation for the visually impaired population. To enable a long-term VPR system on a large scale, several challenges need to be addressed. First, different applications could require different image view directions, such as front views for self-driving cars while side views for the low vision people. Second, VPR in metropolitan scenes can often cause privacy concerns due to the imaging of pedestrian and vehicle identity information, calling for the need for data anonymization before VPR queries and database construction. Both factors could lead to VPR performance variations that are not well understood yet. To study their influences, we present the NYU-VPR dataset that contains more than 200,000 images over a 2km by 2km area near the New York University campus, taken within the whole year of 2016. We present benchmark results on several popular VPR algorithms showing that side views are significantly more challenging for current VPR methods while the influence of data anonymization is almost negligible, together with our hypothetical explanations and in-depth analysis.