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

Online 3D multi-object tracking (MOT) has recently received significantresearch interests due to the expanding demand of 3D perception in advanceddriver assistance systems (ADAS) and autonomous driving (AD). Among theexisting 3D MOT frameworks for ADAS and AD, conventional point object tracking(POT) framework using the tracking-by-detection (TBD) strategy has been wellstudied and accepted for LiDAR and 4D imaging radar point clouds. In contrast,extended object tracking (EOT), another important framework which accepts thejoint-detection-and-tracking (JDT) strategy, has rarely been explored foronline 3D MOT applications. This paper provides the first systematicalinvestigation of the EOT framework for online 3D MOT in real-world ADAS and ADscenarios. Specifically, the widely accepted TBD-POT framework, the recentlyinvestigated JDT-EOT framework, and our proposed TBD-EOT framework are comparedvia extensive evaluations on two open source 4D imaging radar datasets:View-of-Delft and TJ4DRadSet. Experiment results demonstrate that theconventional TBD-POT framework remains preferable for online 3D MOT with hightracking performance and low computational complexity, while the proposedTBD-EOT framework has the potential to outperform it in certain situations.However, the results also show that the JDT-EOT framework encounters multipleproblems and performs inadequately in evaluation scenarios. After analyzing thecauses of these phenomena based on various evaluation metrics andvisualizations, we provide possible guidelines to improve the performance ofthese MOT frameworks on real-world data. These provide the first benchmark andimportant insights for the future development of 4D imaging radar-based online3D MOT.

Which Framework is Suitable for Online 3D Multi-Object Tracking for Autonomous Driving with Automotive 4D Imaging Radar?