SEED: Structure-Entropy and DCT Enhanced Descriptor for Robust 4D Radar Place Recognition
Feipeng Chen, Lihui Wang, Zehua Ying, Song Xue, Kui Wang, Xueyong Xu, Renzhi Huang, Yuhang Xu
Abstract
Reliable place recognition in adverse weather remains a critical challenge for autonomous navigation. While 4D millimeter-wave radar provides robust sensing capabilities, its data is characterized by sparsity, multipath noise, and measurement uncertainty. To address these challenges, we propose SEED, a two-stage method for 4D radar place recognition. We first organize static radar returns in a polar voxel map and compute an entropy-weighted feature that combines density and geometric cues to suppress unstable clutter while enhancing informative structures. We then project the voxel map into range-elevation and range-azimuth matrices, from which compact descriptors are extracted using truncated DCT. A hierarchical search first performs coarse retrieval and then refines matches. Experiments on multiple 4D radar datasets, including snowy and unstructured scenes, show that SEED outperforms the compared baselines while maintaining real-time performance on embedded hardware.
BibTeX
@inproceedings{ral2026_seedstructureent,
title = {SEED: Structure-Entropy and DCT Enhanced Descriptor for Robust 4D Radar Place Recognition},
author = {Feipeng Chen and Lihui Wang and Zehua Ying and Song Xue and Kui Wang and Xueyong Xu and Renzhi Huang and Yuhang Xu},
booktitle = {RA-L 2026},
year = {2026}
}