EUVIMEDEUVIMED entdecken
Crossref

CapsLoc3D: Point Cloud Retrieval for Large-Scale Place Recognition Based on 3D Capsule Networks

Jinpeng Zhang, Yunzhou Zhang, Ming Liao, Rui Tian, Sonya Coleman, Dermot Kerr

IEEE Transactions on Intelligent Transportation Systems · 2024-07 · 25 (7) · 6811-6823

DOI: 10.1109/tits.2023.3346953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-07. Verfasst von Jinpeng Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Major Science and Technology Projects of Liaoning Province, Foundation of Key Laboratory of Aerospace System Simulation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point cloud-based place recognition can be used for global localization in large-scale scenes and loop-closure detection in simultaneous localization and mapping (SLAM) systems in the absence of GPS. Current learning-based approaches aim to extract global and local features from 3D point clouds to encode them as descriptors for point cloud retrieval. The key problems are that the occlusion of point clouds by dynamic objects in the scene affects the point cloud structure, a single perceptual field of the network cannot adequately extract point cloud features, and the correlation between features is not fully utilized. To overcome this, we propose a novel network called CapsLoc3D. We first use the static point cloud generation module to remove the occlusion effects of dynamic objects, and then obtain the point cloud descriptors by processing with the CapsLoc3D network which contains the point spatial transformation module, multi-scale feature fusion module, Capsnet module and a GeM Pooling layer. After validation using the Oxford RobotCar, KITTI, and NEU datasets, experiments show that our method performs better and also has good generalization performance and computational efficiency compared with current state-of-the-art algorithms.

Förderung

  • National Natural Science Foundation of China
  • Major Science and Technology Projects of Liaoning Province
  • Foundation of Key Laboratory of Aerospace System Simulation
  • Foundation of Key Laboratory of Equipment Reliability
  • Major Science and Technology Innovation Engineering Projects of Shandong Province

Zitieren

APA

Zhang, J., Zhang, Y., Liao, M., Tian, R., Coleman, S., & Kerr, D. (2024). CapsLoc3D: Point Cloud Retrieval for Large-Scale Place Recognition Based on 3D Capsule Networks. IEEE Transactions on Intelligent Transportation Systems, 25(7), 6811-6823. https://doi.org/10.1109/tits.2023.3346953

Vancouver

Zhang J, Zhang Y, Liao M, Tian R, Coleman S, Kerr D. CapsLoc3D: Point Cloud Retrieval for Large-Scale Place Recognition Based on 3D Capsule Networks. IEEE Transactions on Intelligent Transportation Systems. 2024;25(7):6811-6823. doi:10.1109/tits.2023.3346953

BibTeX
@article{Zhang2024,
  author = {Zhang, Jinpeng and Zhang, Yunzhou and Liao, Ming and Tian, Rui and Coleman, Sonya and Kerr, Dermot},
  title = {CapsLoc3D: Point Cloud Retrieval for Large-Scale Place Recognition Based on 3D Capsule Networks},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {7},
  pages = {6811--6823},
  doi = {10.1109/tits.2023.3346953}
}
Kostenlos starten →