Reproduce “RaMOD: Moving-Object Detection from Raw mmWave Radar Cubes under Ego Motion” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yuan Fang, Long Zhuang, Lingzi Xing, Xijia Wei, Jingqi Jiang, Fangzhan Shi, Simon Julier, Kevin Chetty
RaMOD detects road users and estimates their motion from raw range–azimuth–Doppler (RAD) cubes while accounting for radar ego motion and Doppler wrapping. It predicts static-scene Doppler to suppress consistent returns, then detects objects and selects raw or unwrapped velocity estimates. On BRIDGE-Liv, it achieves 80.8% cube mAP at 3D IoU 0.30 versus 65.1% for Mamba-RODNet, within that benchmark protocol.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.