Corpus ID: 235458092

AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition

@article{Barros2021AttDLNetAD,
  title={AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition},
  author={Tiago Barros and L. Garrote and Ricardo Pereira and C. Premebida and U. Nunes},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.09637}
}
Deep networks have been progressively adapted to new sensor modalities, namely to 3D LiDAR, which led to unprecedented achievements in autonomous vehicle-related applications such as place recognition. One of the main challenges of deep models in place recognition is to extract efficient and descriptive feature representations that relate places based on their similarity. To address the problem of place recognition using LiDAR data, this paper proposes a novel 3D LiDAR-based deep learning… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 28 REFERENCES
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
TLDR
This work introduces a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors and proposes a novel loss function called HPHN quadruplet loss, that achieves better performance than the commonly used metric learning loss. Expand
RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation
TLDR
This paper proposes a novel post-processing algorithm that deals with problems arising from this intermediate representation of range images as an intermediate representation in combination with a Convolutional Neural Network exploiting the rotating LiDAR sensor model. Expand
OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
TLDR
This work introduces a novel method for oriented place recognition with 3D LiDAR scans that outperforms related state-of-the-art approaches based on both data-driven and handcrafted data representation in challenging long-term outdoor conditions. Expand
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
TLDR
A convolutional neural network architecture that is trainable in an end-to-end manner directly for the place recognition task and an efficient training procedure which can be applied on very large-scale weakly labelled tasks are developed. Expand
SpoxelNet: Spherical Voxel-based Deep Place Recognition for 3D Point Clouds of Crowded Indoor Spaces
TLDR
SpoxelNet is presented, a neural network architecture that encodes input voxels into global descriptor vectors by extracting the structural features in both fine and coarse scales and reinforces its performance in occluded places by concatenating feature vectors from multiple directions. Expand
On the performance of ConvNet features for place recognition
TLDR
It is confirmed that networks trained for semantic place categorization also perform better at (specific) place recognition when faced with severe appearance changes and provide a reference for which networks and layers are optimal for different aspects of the place recognition problem. Expand
Deep Supervised Hashing with Similar Hierarchy for Place Recognition
  • Lang Wu, Yihong Wu
  • Computer Science
  • 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2019
TLDR
This paper proposes deep supervised hashing for place recognition, where a similar hierarchy loss function to learn a model can distinguish the similar images more accurately and can learn high quality hash codes by maximizing the likelihood of triplet labels. Expand
LPD-AE: Latent Space Representation of Large-Scale 3D Point Cloud
TLDR
A novel deep neural network, LPD-AE(Large-scale Place Description AutoEncoder Network), to obtain meaningful local and contextual features for the generation of latent space from 3D point cloud directly, and demonstrates performance that is comparable to the state-of-the-art approaches. Expand
Point Attention Network for Semantic Segmentation of 3D Point Clouds
TLDR
The proposed point attention network consists of an encoder and decoder which, together with the LAE-Conv layers and the point-wise spatial attention modules, make it an end-to-end trainable network for predicting dense labels for 3D point cloud segmentation. Expand
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis
TLDR
A novel deep neural network, named LPD-Net (Large-scale Place Description Network), which can extract discriminative and generalizable global descriptors from the raw 3D point cloud and reaches the state-of-the-art. Expand
...
1
2
3
...