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

In 3D point cloud-based visual self-localization, pole landmarks have a greatpotential as landmarks for accurate and reliable localization due to theirlong-term stability under seasonal and weather changes. In this study, we aimto explore the use of recently developed deep learning models for poleclassification in the context of pole landmark-based self-localization.Specifically, the proposed scheme consists of two main modules: pole mapmatching and pole class matching. In the former module, local pole map isconstructed and its configuration is compared against a precomputed global polemap. An efficient RANSAC map matching is employed to achieve a good tradeoffbetween computational efficiency and accuracy. In the latter pole classmatching module, the local and global poles paired by the RANSAC map-matchingare further compared by means of pole attribute class. To this end, apredefined set of pseudo pole classes is learned via k-means clustering in aself-supervised manner. Experiments using publicly available NCLT datasetshowed that the pole-like landmark classification method has an improved effecton the visual self-localization system compared with the baseline method.

Detection and Classification of Pole-like Landmarks for Domain-invariant 3D Point Cloud Map Matching