SeqSphereVLAD: Sequence Matching Enhanced Orientation-invariant Place Recognition

Yin, Peng; Wang, Fuying; Egorov, Anton; Hou, Jiafan; Ji, Zhang; Choset, Howie

doi:10.1109/iros45743.2020.9341727

Cited by 22 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PointNetVLAD [11] applies metric learning to generate a discriminative and compact global descriptor from an unordered input 3D point cloud and proposes a novel loss function that make descriptors more discriminative and generalizable. SphereVLAD [12] uses spherical projection and a neural network with four Spherical Convolution Layers, four WAG Pooling Layers and a Flatten Layer to generate an orientation-invariant place descriptor. GOSMatch [13] proposes a semantic-based graph descriptor, which pays attention to the transformation relationship between semantics and semantics in the scene, and gives a 6-DOF initial pose estimation.…”

Section: Related Workmentioning

confidence: 99%

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Yuan¹,

Zhang²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Place recognition technology endows a SLAM algorithm with the ability to eliminate accumulated errors and to relocalize itself. Existing methods on point cloud-based place recognition often leverage the matching of global descriptors which are lidar-centric. These methods have the following two major defects: place recognition cannot be performed when the distance between the two point clouds is far, and only the rotation angle can be calculated without the offset in the X and Y direction. To solve these two problems, we propose a novel global descriptor, which is built around the Main Object, in this way, descriptors are no longer dependent on the observation position. We analyze the theory that this method can perfectly solve the above two problems, and conduct a lot of experiments in KITTI and some extreme scenarios, which show that our method has obvious advantages over traditional methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Yuan¹,

Zhang²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…SeqLPD [35] is a sequence matching the enhancing version of LPD [19]. SeqSphereVLAD [36] follows the particle filter framework to complete sequence matching.…”

Section: Sequence Enhanced Place Recognitionmentioning

confidence: 99%

Sequence matching enhanced 3D place recognition using candidate rearrangement

Yan

Zhuang

2022

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

Deep-learning-based 3D place recognition has received more attention since the datadriven fashion is widely used for the 3D point cloud applications. Most of the existing deep-learning-based 3D place recognition methods only utilise a single scene for place recognition. However, a single scene may have measurement noise or observable dynamic object differences, which may lead to a reduction in recognition accuracy. To improve the performance of 3D place recognition, a sequence matching based rearrangement method is proposed. Our sequence matching method is based on an assignment algorithm and guides the candidate rearrangement in searching for a similar place. The global descriptor extraction adapts the effective sparse tensor representation and a simple pooling layer to obtain the global descriptor. A new loss function combination is employed to train the network. The proposed approach is evaluated on the popular 3D place recognition benchmarks, which proves the effectiveness of the proposed approach.

show abstract

“…More recently, Yin et al [35] propose FusionVLAD to generate multi-view representations with dense submaps from sequential LiDAR scans, and encode both the top-down and spherical views of LiDAR scans. They later also propose SeqSphereVLAD [36], [37], which locates the best match using a particle filter-based method in the global searching thus improving the place recognition robustness. These methods have achieved comparable performance by combining singlescan/submap-based place recognition methods with sequence matching.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we propose an end-to-end sequence-enhanced place recognition method. Different to the existing sequence-enhanced methods [12], [8], [36], [37], [9], we fuse the spatial and temporal information using yaw-rotation-invariant transformer networks, and directly generate one single global descriptor for each LiDAR sequence in an end-to-end fashion for fast LiDAR sequencebased place recognition.…”

Section: Related Workmentioning

confidence: 99%

SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data

Ma¹,

Chen²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Place recognition is an important component for autonomous vehicles to achieve loop closing or global localization. In this paper, we tackle the problem of place recognition based on sequential 3D LiDAR scans obtained by an onboard LiDAR sensor. We propose a transformer-based network named SeqOT to exploit the temporal and spatial information provided by sequential range images generated from the LiDAR data. It uses multi-scale transformers to generate a global descriptor for each sequence of LiDAR range images in an end-to-end fashion. During online operation, our SeqOT finds similar places by matching such descriptors between the current query sequence and those stored in the map. We evaluate our approach on four datasets collected with different types of LiDAR sensors in different environments. The experimental results show that our method outperforms the state-of-the-art LiDAR-based place recognition methods and generalizes well across different environments. Furthermore, our method operates online faster than the frame rate of the sensor. The implementation of our method is released as open source at: https://github.com/BIT-MJY/SeqOT.

show abstract

SeqSphereVLAD: Sequence Matching Enhanced Orientation-invariant Place Recognition

Cited by 22 publications

References 11 publications

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Sequence matching enhanced 3D place recognition using candidate rearrangement

SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data

Contact Info

Product

Resources

About