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

A reliable perception has to be robust against challenging environmentalconditions. Therefore, recent efforts focused on the use of radar sensors inaddition to camera and lidar sensors for perception applications. However, thesparsity of radar point clouds and the poor data availability remainchallenging for current perception methods. To address these challenges, anovel graph neural network is proposed that does not just use the informationof the points themselves but also the relationships between the points. Themodel is designed to consider both point features and point-pair features,embedded in the edges of the graph. Furthermore, a general approach forachieving transformation invariance is proposed which is robust against unseenscenarios and also counteracts the limited data availability. Thetransformation invariance is achieved by an invariant data representationrather than an invariant model architecture, making it applicable to othermethods. The proposed RadarGNN model outperforms all previous methods on theRadarScenes dataset. In addition, the effects of different invariances on theobject detection and semantic segmentation quality are investigated. The codeis made available as open-source software underhttps://github.com/TUMFTM/RadarGNN.

RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception