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

We present an iterative overlap estimation technique to augment existingpoint cloud registration algorithms that can achieve high performance indifficult real-world situations where large pose displacement andnon-overlapping geometry would otherwise cause traditional methods to fail. Ourapproach estimates overlapping regions through an iterative ExpectationMaximization procedure that encodes the sensor field-of-view into theregistration process. The proposed technique, Expected Overlap Estimation(EOE), is derived from the observation that differences in field-of-viewviolate the iid assumption implicitly held by all maximum likelihood basedregistration techniques. We demonstrate how our approach can augment manypopular registration methods with minimal computational overhead. Throughexperimentation on both synthetic and real-world datasets, we find that addingan explicit overlap estimation step can aid robust outlier handling andincrease the accuracy of both ICP-based and GMM-based registration methods,especially in large unstructured domains and where the amount of overlapbetween point clouds is very small.

EOE: Expected Overlap Estimation over Unstructured Point Cloud Data