【论文阅读】Place recognition survey: An update on deeplearning approaches

论文下载：PDF
[1] Barros T , Pereira R , Garrote L , et al. Place recognition survey: An update on deep learning approaches:, 10.48550/arXiv.2106.10458[P]. 2021.

Abstract

Abstract—Autonomous Vehicles (A V) are becoming more capable of navigating in complex environments with dynamic and changing conditions. A key component that enables these intelligent vehicles to overcome such conditions and become more autonomous is the sophistication of the perception and localization systems. As part of the localization system, place recognition has benefited from recent developments in other perception tasks such as place categorization or object recognition, namely with the emergence of deep learning (DL) frameworks. This paper surveys recent approaches and methods used in place recognition, particularly those based on deep learning. The contributions of this work are twofold: surveying recent sensors such as 3D LiDARs and RADARs, applied in place recognition; and categorizing the various DL-based place recognition works into supervised, unsupervised, semi-supervised, parallel, and hierarchical categories. First, this survey introduces key place recognition concepts to contextualize the reader. Then, sensor characteristics are addressed. This survey proceeds by elaborating on the various DL-based works, presenting summaries for each framework. Some lessons learned from this survey include: the importance of NetVLAD for supervised end-to-end learning; the advantages of unsupervised approaches in place recognition, namely for cross-domain applications; or the increasing tendency of recent works to seek, not only for higher performance but also for higher efficiency.

Introduction

Self-driving vehicles are increasingly able to deal with unstructured and dynamic environments, which is mainly due to the development of more robust long-term localization and perception systems. A critical aspect of long-term localization is to guarantee coherent mapping and bounded error over time, which is achieved by finding loops in revisited areas. Revisited places are detected in long-term localization systems by resorting to approaches such as place recognition and loop closure. Namely, place recognition is a perception based approach that recognizes previously visited places based on visual, structural, or semantic cues.
自动驾驶汽车能够处理非结构化和动态环境，主要是由于更稳健的长期定位和感知系统的发展。 长期定位的关键在于保证建图的连贯性和随时间累计的有限误差，可以通过识别以前到达过的地方形成闭环实现的。在长期定位中通过场景识别和闭环检测等方法来判断是否经过同一个位置。 也就是说，地点识别是一种基于感知的方法，根据视觉，结构和语义信息来识别以前到达过的地方。

Despite the recent achievements, the fundamental challenges remain unsolved, which occur when:
− two distinct places look similar (also known as perceptual aliasing);两个看起来相似的不同场景
− the same places exhibit significant appearance changes over time due to day-night variation, weather, seasonal or structural changes (as shown in Fig. 2);有明显外观变化的相同场景
− same places are perceived from different viewpoints or positions. 不同视角和位置

文章结构

The remainder of this paper is organized as follows.
Section II is dedicated to the key concepts regarding place recognition. 地点识别的概念
Section III addresses the supervised place recognition approaches, which include pre-trained and end-to-end frameworks. 监督方法
Section V addresses the unsupervised place recognition approaches. 非监督方法
Section VI addresses approaches that combine both supervised and unsupervised.监督和非监督结合方法
Section VII addresses alternative frameworks that resort to parallel and hierarchical architectures. 其他并行和分层的替代框架介绍
Section VIII concludes the paper.总结