Point-Voxel and Bird-Eye-View Representation Aggregation Network for Single Stage 3D Object Detection
IEEE Transactions on Intelligent Transportation Systems · 2023-03 · 24 (3) · 3223-3235
DOI: 10.1109/tits.2022.3225880 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-03. Verfasst von Kanglin Ning und 3 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: Natural Science Basic Research Project Fully Distributed Multi-Objective State Estimation under Information Naive and Spurious Measurements.
Abstract (Originalsprache)
3D object detectors based on LiDAR have been extensively used in autonomous and robotic systems. Efficient voxel-based models must downsample their feature space to reduce computation, which leads to the loss of geometric information and limit their accuracy. To solve this problem, this paper presents a 3D detection framework, point-voxel and bird’s-eye-view representation aggregation network for single stage 3D object detection (PVB-SSD), in which a position information input branch generates Fourier embedding features from the origin point cloud to supplement the lost information. A global-former module integrates embedded Fourier features with bird’s-eye-view features extracted by a 3D convolution backbone. Considering that in the deeper layer of the neural network, the spatial level features will be replaced by semantic level features, a windows transformer spatial-semantic aggregate module fuses them dynamically. Extensive experiments on the KITTI, Waymo and NuScences datasets show that our model has excellent accuracy and relatively low computational consumption.
Förderung
- Natural Science Basic Research Project Fully Distributed Multi-Objective State Estimation under Information Naive and Spurious Measurements
Zitieren
APA
Ning, K., Liu, Y., Su, Y., & Jiang, K. (2023). Point-Voxel and Bird-Eye-View Representation Aggregation Network for Single Stage 3D Object Detection. IEEE Transactions on Intelligent Transportation Systems, 24(3), 3223-3235. https://doi.org/10.1109/tits.2022.3225880
Vancouver
Ning K, Liu Y, Su Y, Jiang K. Point-Voxel and Bird-Eye-View Representation Aggregation Network for Single Stage 3D Object Detection. IEEE Transactions on Intelligent Transportation Systems. 2023;24(3):3223-3235. doi:10.1109/tits.2022.3225880
BibTeX
@article{Ning2023,
author = {Ning, Kanglin and Liu, Yanfei and Su, Yanzhao and Jiang, Ke},
title = {Point-Voxel and Bird-Eye-View Representation Aggregation Network for Single Stage 3D Object Detection},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2023},
volume = {24},
number = {3},
pages = {3223--3235},
doi = {10.1109/tits.2022.3225880}
}
EUVIMED