EUVIMEDEUVIMED entdecken
Crossref

Self-Supervised Deep Visual Odometry Based on Geometric Attention Model

Jiajia Dai, Xiaoxi Gong, Yida Li, Jun Wang, Mingqiang Wei

IEEE Transactions on Intelligent Transportation Systems · 2023-03 · 24 (3) · 3157-3166

DOI: 10.1109/tits.2022.3227917 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-03. Verfasst von Jiajia Dai und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Key Research and Development Program of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing learning-based algorithms have a certain potential in visual odometry. In this work, we propose the solution of the learning-based method, which contains the attention mechanism and pose graph optimization. We set a self-supervised network as our backbone to cope with image data and error-heavy estimation pose for pose correction. The pre-processing camera poses involved in the network can provide prior information. Combining the advantages of the abundant feature information and efficient attention mechanism, we design a geometric attention module that is sensitive to geometrical structure from images to accurately regress the rotation matrix. Then we improve the loss function with the weights of the attention module to consider the diversity of the data. Experimental results demonstrate the effectiveness and reliability of our approach on the public datasets KITTI with monocular task and stereo task. In comparison, the proposed method is superior to the existing methods in the translation component. In the self-supervised network, learning an attention mechanism can extract an effective connect relation of feature maps. We conduct ablation experiments under the self-supervised network backbone setting different strategies, and conclude that the proposed attention module is applicable to various sequences, and provide loss function improvements on the visual odometry task.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Key Research and Development Program of Jiangsu Province

Zitieren

APA

Dai, J., Gong, X., Li, Y., Wang, J., & Wei, M. (2023). Self-Supervised Deep Visual Odometry Based on Geometric Attention Model. IEEE Transactions on Intelligent Transportation Systems, 24(3), 3157-3166. https://doi.org/10.1109/tits.2022.3227917

Vancouver

Dai J, Gong X, Li Y, Wang J, Wei M. Self-Supervised Deep Visual Odometry Based on Geometric Attention Model. IEEE Transactions on Intelligent Transportation Systems. 2023;24(3):3157-3166. doi:10.1109/tits.2022.3227917

BibTeX
@article{Dai2023,
  author = {Dai, Jiajia and Gong, Xiaoxi and Li, Yida and Wang, Jun and Wei, Mingqiang},
  title = {Self-Supervised Deep Visual Odometry Based on Geometric Attention Model},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {3},
  pages = {3157--3166},
  doi = {10.1109/tits.2022.3227917}
}
Kostenlos starten →