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

This paper presents novel hybrid architectures that combine grid- andpoint-based processing to improve the detection performance and orientationestimation of radar-based object detection networks. Purely grid-baseddetection models operate on a bird's-eye-view (BEV) projection of the inputpoint cloud. These approaches suffer from a loss of detailed informationthrough the discrete grid resolution. This applies in particular to radarobject detection, where relatively coarse grid resolutions are commonly used toaccount for the sparsity of radar point clouds. In contrast, point-based modelsare not affected by this problem as they process point clouds withoutdiscretization. However, they generally exhibit worse detection performancesthan grid-based methods.  We show that a point-based model can extract neighborhood features,leveraging the exact relative positions of points, before grid rendering. Thishas significant benefits for a subsequent grid-based convolutional detectionbackbone. In experiments on the public nuScenes dataset our hybrid architectureachieves improvements in terms of detection performance (19.7% higher mAP forcar class than next-best radar-only submission) and orientation estimates(11.5% relative orientation improvement) over networks from previousliterature.

Improved Orientation Estimation and Detection with Hybrid Object Detection Networks for Automotive Radar