Where is your place, Visual Place Recognition?

TL;DR

This paper surveys Visual Place Recognition (VPR), emphasizing the influence of agent-specific, environmental, and task-related factors, and introduces a new definition based on visual overlap to guide future research.

Contribution

It characterizes VPR considering key drivers, proposes a new overlap-based definition, and highlights open challenges for advancing the field.

Findings

VPR depends on agent, environment, and task factors.

A new VPR definition based on visual overlap is proposed.

Identifies open challenges and future research directions.

Abstract

Visual Place Recognition (VPR) is often characterized as being able to recognize the same place despite significant changes in appearance and viewpoint. VPR is a key component of Spatial Artificial Intelligence, enabling robotic platforms and intelligent augmentation platforms such as augmented reality devices to perceive and understand the physical world. In this paper, we observe that there are three "drivers" that impose requirements on spatially intelligent agents and thus VPR systems: 1) the particular agent including its sensors and computational resources, 2) the operating environment of this agent, and 3) the specific task that the artificial agent carries out. In this paper, we characterize and survey key works in the VPR area considering those drivers, including their place representation and place matching choices. We also provide a new definition of VPR based on the visual overlap -- akin to spatial view cells in the brain -- that enables us to find similarities and differences to other research areas in the robotics and computer vision fields. We identify numerous open challenges and suggest areas that require more in-depth attention in future works.