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

Recent developments and the beginning market introduction of high-resolutionimaging 4D (3+1D) radar sensors have initialized deep learning-based radarperception research. We investigate deep learning-based models operating onradar point clouds for 3D object detection. 3D object detection on lidar pointcloud data is a mature area of 3D vision. Many different architectures havebeen proposed, each with strengths and weaknesses. Due to similarities between3D lidar point clouds and 3+1D radar point clouds, those existing 3D objectdetectors are a natural basis to start deep learning-based 3D object detectionon radar data. Thus, the first step is to analyze the detection performance ofthe existing models on the new data modality and evaluate them in depth. Inorder to apply existing 3D point cloud object detectors developed for lidarpoint clouds to the radar domain, they need to be adapted first. While somedetectors, such as PointPillars, have already been adapted to be applicable toradar data, we have adapted others, e.g., Voxel R-CNN, SECOND, PointRCNN, andPV-RCNN. To this end, we conduct a cross-model validation (evaluating a set ofmodels on one particular data set) as well as a cross-data set validation(evaluating all models in the model set on several data sets). Thehigh-resolution radar data used are the View-of-Delft and Astyx data sets.Finally, we evaluate several adaptations of the models and their trainingprocedures. We also discuss major factors influencing the detection performanceon radar data and propose possible solutions indicating potential futureresearch avenues.

Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar