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

LiDAR-based place recognition (LPR) is one of the most crucial components ofautonomous vehicles to identify previously visited places in GPS-deniedenvironments. Most existing LPR methods use mundane representations of theinput point cloud without considering different views, which may not fullyexploit the information from LiDAR sensors. In this paper, we propose across-view transformer-based network, dubbed CVTNet, to fuse the range imageviews (RIVs) and bird's eye views (BEVs) generated from the LiDAR data. Itextracts correlations within the views themselves using intra-transformers andbetween the two different views using inter-transformers. Based on that, ourproposed CVTNet generates a yaw-angle-invariant global descriptor for eachlaser scan end-to-end online and retrieves previously seen places by descriptormatching between the current query scan and the pre-built database. We evaluateour approach on three datasets collected with different sensor setups andenvironmental conditions. The experimental results show that our methodoutperforms the state-of-the-art LPR methods with strong robustness toviewpoint changes and long-time spans. Furthermore, our approach has a goodreal-time performance that can run faster than the typical LiDAR frame rate.The implementation of our method is released as open source at:https://github.com/BIT-MJY/CVTNet.

CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data