Visual Place Recognition: A Survey

By Stephanie M. Lowry, Niko Sünderhauf, Paul M. Newman, John J. Leonard, David D. Cox, Peter Corke, Michael Milford. 2016

1,147 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, neutral): “r than human demonstrations. Understanding the world is central to planning, control and (model-based) RL. In robotics, one often needs to locate or navigate itself by interpreting a map of the world [61, 87, 3]. Our exploration strategy borrows the high-level insight from robotics active localizati”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “[160], and some of its challenges are discussed in Section III.”
A Survey of Deep Learning Applications to Autonomous Vehicle Control (2019, background): “in autonomous vehicle applications, including planning and decision making [27]–[31], perception [32]–[36], as well as mapping and localisation [37]–[39].”
MulRan: Multimodal Range Dataset for Urban Place Recognition (2020, methodology): “We used the precision-recall curve [38] as the evaluation metric and the results are depicted in Fig.”
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis (2018, background): “Thanks to the feasibility of extracting visual feature descriptors from a query image of a local scene, vision-based approaches have achieved good retrieval performance for place recognitions with respect to the reference map [19, 9].”
Self-Supervised Visual Descriptor Learning for Dense Correspondence (2017, background): “[15] provide a useful overview of visual place recognition, the challenges involved, and the important to robotics of identifying correspondences.”
SegMatch: Segment based place recognition in 3D point clouds (2016, methodology): “[2] state that using descriptors at the level of segments or objects could provide the benefits of both local and global feature approaches.”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, background): “Given an image of a place, mobile robots are requested to recognize a previously seen place (Lowry et al., 2016).”
Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization (2022, neutral): “Established approaches for visual loop closure detection in robotics trace back to place recognition and image retrieval techniques in computer vision; these approaches are broadly adopted in SLAM pipelines but are known to suffer from appearance and viewpoint changes [36].”
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions (2018, background): “They are often used for place recognition [1, 17, 41, 55, 66, 69] and loop-closure detection [20,25,48].”
Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments (2021, methodology): “We used the precision-recall curve as a main evaluation metric [6].”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, neutral): “focus on how to deal with seasonal or weather changes and we refer our readers to this survey [93] for a detailed view of this field, independently of loop closure.”
Incremental Adversarial Domain Adaptation for Continually Changing Environments (2017, background): “Considerable efforts have been focused on designing and comparing various feature transformations with the goal of creating representations invariant to environmental change [13].”
A review of multimodal image matching: Methods and applications (2021, background): “Image localization mainly consists of the image processing module, the mapping framework, and the belief generation module [506].”
Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal (2018, methodology): “…places in the face of appearance and viewpoint change [36]; however, reducing perceptual aliasing and appearance differences is an active area of research in place recognition and SLAM [25] and many other techniques developed for that purpose may also provide improvements in work like ours.”
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition (2021, background): “VPR is typically framed as an image retrieval task [45, 59, 76, 24], where, given a query image, the most similar database image (alongside associated metadata such as the camera pose) is retrieved.”
Visual-Inertial Navigation: A Concise Review (2019, background): “In particular, whether or not performing loop closures in VINS either via mapping [83, 101, 102] and/or place recognition [103, 104, 105, 106, 107, 108] is one of the key differences between VIO and SLAM.”