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

As an important technology in 3D mapping, autonomous driving, and robotnavigation, LiDAR odometry is still a challenging task. Appropriate datastructure and unsupervised deep learning are the keys to achieve an easyadjusted LiDAR odometry solution with high performance. Utilizing compact 2Dstructured spherical ring projection model and voxel model which preserves theoriginal shape of input data, we propose a fully unsupervised ConvolutionalAuto-Encoder based LiDAR Odometry (CAE-LO) that detects interest points fromspherical ring data using 2D CAE and extracts features from multi-resolutionvoxel model using 3D CAE. We make several key contributions: 1) experimentsbased on KITTI dataset show that our interest points can capture more localdetails to improve the matching success rate on unstructured scenarios and ourfeatures outperform state-of-the-art by more than 50% in matching inlier ratio;2) besides, we also propose a keyframe selection method based on matching pairstransferring, an odometry refinement method for keyframes based on extendedinterest points from spherical rings, and a backward pose update method. Theodometry refinement experiments verify the proposed ideas' feasibility andeffectiveness.

CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description