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

Most 6-DoF localization and SLAM systems use static landmarks but ignoredynamic objects because they cannot be usefully incorporated into a typicalpipeline. Where dynamic objects have been incorporated, typical approaches haveattempted relatively sophisticated identification and localization of theseobjects, limiting their robustness or general utility. In this research, wepropose a middle ground, demonstrated in the context of autonomous vehicles,using dynamic vehicles to provide limited pose constraint information in a6-DoF frame-by-frame PnP-RANSAC localization pipeline. We refine initial poseestimates with a motion model and propose a method for calculating thepredicted quality of future pose estimates, triggered based on whether or notthe autonomous vehicle's motion is constrained by the relative frame-to-framelocation of dynamic vehicles in the environment. Our approach detects andidentifies suitable dynamic vehicles to define these pose constraints to modifya pose filter, resulting in improved recall across a range of localizationtolerances from $0.25m$ to $5m$, compared to a state-of-the-art baseline singleimage PnP method and its vanilla pose filtering. Our constraint detectionsystem is active for approximately $35\%$ of the time on the Ford AV datasetand localization is particularly improved when the constraint detection isactive.

Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization