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

At present, the anchor-based or anchor-free models that use LiDAR pointclouds for 3D object detection use the center assigner strategy to infer the 3Dbounding boxes. However, in a real world scene, the LiDAR can only acquire alimited object surface point clouds, but the center point of the object doesnot exist. Obtaining the object by aggregating the incomplete surface pointclouds will bring a loss of accuracy in direction and dimension estimation. Toaddress this problem, we propose a corner-guided anchor-free single-stage 3Dobject detection model (CG-SSD ).Firstly, 3D sparse convolution backbonenetwork composed of residual layers and sub-manifold sparse convolutionallayers are used to construct bird's eye view (BEV) features for further deeperfeature mining by a lite U-shaped network; Secondly, a novel corner-guidedauxiliary module (CGAM) is proposed to incorporate corner supervision signalsinto the neural network. CGAM is explicitly designed and trained to detectpartially visible and invisible corners to obtains a more accurate objectfeature representation, especially for small or partial occluded objects;Finally, the deep features from both the backbone networks and CGAM module areconcatenated and fed into the head module to predict the classification and 3Dbounding boxes of the objects in the scene. The experiments demonstrate CG-SSDachieves the state-of-art performance on the ONCE benchmark for supervised 3Dobject detection using single frame point cloud data, with 62.77%mAP.Additionally, the experiments on ONCE and Waymo Open Dataset show that CGAM canbe extended to most anchor-based models which use the BEV feature to detectobjects, as a plug-in and bring +1.17%-+14.27%AP improvement.

CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point Cloud