Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning

Săftescu, Ştefan; Gadd, Matthew; Martini, Daniele De; Barnes, D. C.; Newman, P. R.

doi:10.48550/arxiv.2001.09438

Cited by 7 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, the selection criterion has to consider the specificities of both the application and the environment for the task in hand. In place recognition, the must used sensors are cameras [23], [24], [26], [27], [32], [41], [42], [63], [76], LiDARs [13], [28], [34], [46], [65], [77]- [80] and RADARs [14], [81]- [83]. Although in a broader AV context, these sensors are widely adopted [84], [85], in place recognition, cameras are the most popular in the literature, followed by LiDARs, while RADARs are a very recent technology in this domain.…”

Section: Sensorsmentioning

confidence: 99%

“…1) Loss functions: The loss function is in particular a major concern in the training phase, since it represents the matematical interpretation of the training objective, and thus determining the successful convergence of the optimization process. In place recognition loss functions include tripletbased [24], [34], [50], [65], [81], [96], [137], margin-based [25], quadruplet-based [49], and contrastive-based [13]. Figure 6 illustrates the various training strategies of the loss functions.…”

Section: B End-to-end Frameworkmentioning

confidence: 99%

“…Loss functions that drive from the triplet loss include Lazy triplet [65], weighted triplet loss [96] and weakly supervised triplet ranking loss [24]. The quadruplet is an extension of the triplet loss, introducing an additional constraint to push the negative pairs [145] from the positives pairs w.r.t different probe samples, while triplet CNN as in [120], [139] Triplet loss [140] KNN /Database NCLT [141]; KITTI [142]; [13] LocNet: Siamese network Contrastive loss function [143] L2 KNN /Database KITTI [142] inhouse dataset [144] Siamese network Contrastive loss [143] L2 KNN /Database KITTI [142]; inhouse dataset; RADAR [81] VGG-16 + NetVLAD layer Triplet loss KNN /Database Oxford Radar RobotCar [6] loss only pushes the negatives from the positives w.r.t from the same probe. The additional constrain of the quadruplet loss reduces the intra-class variations and enlarges the inter-class variations.…”

Section: B End-to-end Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Place recognition survey: An update on deep learning approaches

Barros¹,

Pereira²,

Garrote³

et al. 2021

Preprint

View full text Add to dashboard Cite

Autonomous Vehicles (AV) 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.

show abstract

Section: Sensorsmentioning

confidence: 99%

Section: B End-to-end Frameworkmentioning

confidence: 99%

Section: B End-to-end Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Place recognition survey: An update on deep learning approaches

Barros¹,

Pereira²,

Garrote³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Radars provide far longer range and robustness compared to cameras and LiDAR; however, radar place recognition methods are still not mature. Exploiting the image-like format of radar data, some studies leveraged computer vision techniques to describe a radar image at local [35] and global description [36,37] levels. However, the projection model of the radar image inevitably eliminates height information generating a top-down view.…”

Section: B Place Recognition For Range Sensingmentioning

confidence: 99%

“…Secondly, in SLAM applications, coarse global loop detection typically followed by the pose regression module, generates a metric constraint between the query and the map. If the loop candidate is detected too broadly (e.g., 25 m in [36]), then the accompanied fine localization module may fail. Considering these two aspects, we count the detected place as correct if a query place and a detected loop candidate place are less than 8 m apart.…”

Section: B Correctness Criteriamentioning

confidence: 99%

Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments

Kim¹,

Choi²,

Kim³

2021

Preprint

View full text Add to dashboard Cite

Place recognition is a key module in robotic navigation. The existing line of studies mostly focuses on visual place recognition to recognize previously visited places solely based on their appearance. In this paper, we address structural place recognition by recognizing a place based on structural appearance, namely from range sensors. Extending our previous work on a rotation invariant spatial descriptor, the proposed descriptor completes a generic descriptor robust to both rotation (heading) and translation when roll-pitch motions are not severe. We introduce two sub-descriptors and enable topological place retrieval followed by the 1-DOF semi-metric localization thereby bridging the gap between topological place retrieval and metric localization. The proposed method has been evaluated thoroughly in terms of environmental complexity and scale. The source code is available and can easily be integrated into existing LiDAR simultaneous localization and mapping (SLAM).

show abstract

Probabilistic Visual Place Recognition for Hierarchical Localization

Mei

Snderhauf

Milford

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Visual localization techniques often comprise a hierarchical localization pipeline, with a visual place recognition module used as a coarse localizer to initialize a pose refinement stage. While improving the pose refinement step has been the focus of much recent research, most work on the coarse localization stage has focused on improvements like increased invariance to appearance change, without improving what can be loose error tolerances. In this letter, we propose two methods which adapt image retrieval techniques used for visual place recognition to the Bayesian state estimation formulation for localization. We demonstrate significant improvements to the localization accuracy of the coarse localization stage using our methods, whilst retaining state-of-the-art performance under severe appearance change. Using extensive experimentation on the Oxford RobotCar dataset, results show that our approach outperforms comparable state-of-the-art methods in terms of precision-recall performance for localizing image sequences. In addition, our proposed methods provides the flexibility to contextually scale localization latency in order to achieve these improvements. The improved initial localization estimate opens up the possibility of both improved overall localization performance and modified pose refinement techniques that leverage this improved spatial prior.

show abstract

Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning

Cited by 7 publications

References 0 publications

Place recognition survey: An update on deep learning approaches

Place recognition survey: An update on deep learning approaches

Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments

Probabilistic Visual Place Recognition for Hierarchical Localization

Contact Info

Product

Resources

About