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

This work presents a novel RGB-D-inertial dynamic SLAM method that can enableaccurate localisation when the majority of the camera view is occluded bymultiple dynamic objects over a long period of time. Most dynamic SLAMapproaches either remove dynamic objects as outliers when they account for aminor proportion of the visual input, or detect dynamic objects using semanticsegmentation before camera tracking. Therefore, dynamic objects that causelarge occlusions are difficult to detect without prior information. Theremaining visual information from the static background is also not enough tosupport localisation when large occlusion lasts for a long period. To overcomethese problems, our framework presents a robust visual-inertial bundleadjustment that simultaneously tracks camera, estimates cluster-wise densesegmentation of dynamic objects and maintains a static sparse map by combiningdense and sparse features. The experiment results demonstrate that our methodachieves promising localisation and object segmentation performance compared toother state-of-the-art methods in the scenario of long-term large occlusion.

RGB-D-Inertial SLAM in Indoor Dynamic Environments with Long-term Large Occlusion