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

Accurate and robust pose estimation plays a crucial role in many roboticsystems. Popular algorithms for pose estimation typically rely on high-fidelityand high-frequency signals from various sensors. Inclusion of these sensorsmakes the system less affordable and much more complicated. In this work weintroduce a novel approach for the robotic odometry which only requires asingle camera and, importantly, can produce reliable estimates given evenextremely low-frequency signal of around one frame per second. The approach isbased on matching image features between the consecutive frames of the videostream using deep feature matching models. The resulting coarse estimate isthen adjusted by a convolutional neural network, which is also responsible forestimating the scale of the transition, otherwise irretrievable using only thefeature matching information. We evaluate the performance of the approach inthe AISG-SLA Visual Localisation Challenge and find that while beingcomputationally efficient and easy to implement our method shows competitiveresults with only around $3^{\circ}$ of orientation estimation error and $2m$of translation estimation error taking the third place in the challenge.

Match and Locate: low-frequency monocular odometry based on deep feature matching