Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance

Gadd, Matthew; Martini, Daniele De; Newman, Paul

doi:10.1109/plans46316.2020.9109951

Cited by 36 publications

(29 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Sȃftescu et al (2020), NetVLAD (Arandjelovic et al, 2016) was used to achieve radar-to-radar (R2R) place recognition. Then, the researchers used sequential radar scans to improve the localization performance (Gadd et al, 2020). In this paper, a deep neural network is also proposed to extract feature embeddings, but the proposed framework aims at heterogeneous place recognition.…”

Section: Radar-based Mapping and Localizationmentioning

confidence: 99%

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Yin

Wang

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

Place recognition is critical for both offline mapping and online localization. However, current single-sensor based place recognition still remains challenging in adverse conditions. In this paper, a heterogeneous measurement based framework is proposed for long-term place recognition, which retrieves the query radar scans from the existing lidar (Light Detection and Ranging) maps. To achieve this, a deep neural network is built with joint training in the learning stage, and then in the testing stage, shared embeddings of radar and lidar are extracted for heterogeneous place recognition. To validate the effectiveness of the proposed method, we conducted tests and generalization experiments on the multi-session public datasets and compared them to other competitive methods. The experimental results indicate that our model is able to perform multiple place recognitions: lidar-to-lidar (L2L), radar-to-radar (R2R), and radar-to-lidar (R2L), while the learned model is trained only once. We also release the source code publicly: https://github.com/ZJUYH/radar-to-lidar-place-recognition.

show abstract

Section: Radar-based Mapping and Localizationmentioning

confidence: 99%

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Yin

Wang

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…The supervised learning framework presented in Reference [8,9] and which our work extends uses rotationally-invariant feature extraction and triplet-mining but does not solve for the rigid-body pose of the sensor. The cross-modal radar-satellite works presented in Reference [10,28] do solve for the metric pose.…”

Section: Radar-based Mapping and Localisationmentioning

confidence: 99%

“…Indeed, there is a burgeoning interest in exploiting FMCW radar to enable robust mobile autonomy, including ego-motion estimation [2][3][4][5][6][7], localisation [7][8][9][10][11], Simultaneous Localisation and Mapping (SLAM) [12], and scene understanding [13][14][15]. However, despite radar's promise to deliver such capabilities, the study of these tasks is only mature for cameras and Light Detection and Rangings (LiDARs), and relatively little attention has been paid to radar for the same application.…”

Section: Introductionmentioning

confidence: 99%

kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation

Martini

Gadd

Newman

2020

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents a novel two-stage system which integrates topological localisation candidates from a radar-only place recognition system with precise pose estimation using spectral landmark-based techniques. We prove that the—recently available—seminal radar place recognition (RPR) and scan matching sub-systems are complementary in a style reminiscent of the mapping and localisation systems underpinning visual teach-and-repeat (VTR) systems which have been exhibited robustly in the last decade. Offline experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community with performance comparing favourably with and even rivalling alternative state-of-the-art radar localisation systems. Specifically, we show the long-term durability of the approach and of the sensing technology itself to autonomous navigation. We suggest a range of sensible methods of tuning the system, all of which are suitable for online operation. For both tuning regimes, we achieve, over the course of a month of localisation trials against a single static map, high recalls at high precision, and much reduced variance in erroneous metric pose estimation. As such, this work is a necessary first step towards a radar teach-and-repeat (RTR) system and the enablement of autonomy across extreme changes in appearance or inclement conditions.

show abstract

“…Deep distance learning is of great significance in learning visual similarity. Recently, a specially designed triplet loss combined with CNN feature extraction has achieved good performance in face recognition [33], person re-identification [34,35], camera-LiDAR place recognition [36] and radar place recognition [37][38][39] tasks. The main concept behind the triplet loss is to minimize the distances of the same category images and maximize those of other categories in the Euclidean space.…”

Section: Introductionmentioning

confidence: 99%

Towards a Robust Visual Place Recognition in Large-Scale vSLAM Scenarios Based on a Deep Distance Learning

Chen

Jin

Xia

2021

Sensors

View full text Add to dashboard Cite

The application of deep learning is blooming in the field of visual place recognition, which plays a critical role in visual Simultaneous Localization and Mapping (vSLAM) applications. The use of convolutional neural networks (CNNs) achieve better performance than handcrafted feature descriptors. However, visual place recognition is still a challenging task due to two major problems, i.e., perceptual aliasing and perceptual variability. Therefore, designing a customized distance learning method to express the intrinsic distance constraints in the large-scale vSLAM scenarios is of great importance. Traditional deep distance learning methods usually use the triplet loss which requires the mining of anchor images. This may, however, result in very tedious inefficient training and anomalous distance relationships. In this paper, a novel deep distance learning framework for visual place recognition is proposed. Through in-depth analysis of the multiple constraints of the distance relationship in the visual place recognition problem, the multi-constraint loss function is proposed to optimize the distance constraint relationships in the Euclidean space. The new framework can support any kind of CNN such as AlexNet, VGGNet and other user-defined networks to extract more distinguishing features. We have compared the results with the traditional deep distance learning method, and the results show that the proposed method can improve the performance by 19–28%. Additionally, compared to some contemporary visual place recognition techniques, the proposed method can improve the performance by 40%/36% and 27%/24% in average on VGGNet/AlexNet using the New College and the TUM datasets, respectively. It’s verified the method is capable to handle appearance changes in complex environments.

show abstract

Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance

Cited by 36 publications

References 32 publications

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation

Towards a Robust Visual Place Recognition in Large-Scale vSLAM Scenarios Based on a Deep Distance Learning

Contact Info

Product

Resources

About