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 point clouds can effectively depict the motion and posture of objectsin three-dimensional space. Many studies accomplish the 3D object detection byvoxelizing point clouds. However, in autonomous driving scenarios, the sparsityand hollowness of point clouds create some difficulties for voxel-basedmethods. The sparsity of point clouds makes it challenging to describe thegeometric features of objects. The hollowness of point clouds posesdifficulties for the aggregation of 3D features. We propose a two-stage 3Dobject detection framework, called MS23D. (1) We propose a method using voxelfeature points from multi-branch to construct the 3D feature layer. Using voxelfeature points from different branches, we construct a relatively compact 3Dfeature layer with rich semantic features. Additionally, we propose adistance-weighted sampling method, reducing the loss of foreground pointscaused by downsampling and allowing the 3D feature layer to retain moreforeground points. (2) In response to the hollowness of point clouds, wepredict the offsets between deep-level feature points and the object'scentroid, making them as close as possible to the object's centroid. Thisenables the aggregation of these feature points with abundant semanticfeatures. For feature points from shallow-level, we retain them on the object'ssurface to describe the geometric features of the object. To validate ourapproach, we evaluated its effectiveness on both the KITTI and ONCE datasets.

MS23D: : A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer