English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Estimating the camera's pose given images of a single camera is a traditionaltask in mobile robots and autonomous vehicles. This problem is called monocularvisual odometry and it often relies on geometric approaches that requireconsiderable engineering effort for a specific scenario. Deep learning methodshave shown to be generalizable after proper training and a large amount ofavailable data. Transformer-based architectures have dominated thestate-of-the-art in natural language processing and computer vision tasks, suchas image and video understanding. In this work, we deal with the monocularvisual odometry as a video understanding task to estimate the 6-DoF camera'spose. We contribute by presenting the TSformer-VO model based onspatio-temporal self-attention mechanisms to extract features from clips andestimate the motions in an end-to-end manner. Our approach achieved competitivestate-of-the-art performance compared with geometry-based and deeplearning-based methods on the KITTI visual odometry dataset, outperforming theDeepVO implementation highly accepted in the visual odometry community.

Transformer-based model for monocular visual odometry: a video understanding approach