Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RaPlace: Place Recognition for Imaging Radar using Radon Transform and Mutable Threshold

About

Due to the robustness in sensing, radar has been highlighted, overcoming harsh weather conditions such as fog and heavy snow. In this paper, we present a novel radar-only place recognition that measures the similarity score by utilizing Radon-transformed sinogram images and cross-correlation in frequency domain. Doing so achieves rigid transform invariance during place recognition, while ignoring the effects of radar multipath and ring noises. In addition, we compute the radar similarity distance using mutable threshold to mitigate variability of the similarity score, and reduce the time complexity of processing a copious radar data with hierarchical retrieval. We demonstrate the matching performance for both intra-session loop-closure detection and global place recognition using a publicly available imaging radar datasets. We verify reliable performance compared to existing stable radar place recognition method. Furthermore, codes for the proposed imaging radar place recognition is released for community.

Hyesu Jang, Minwoo Jung, Ayoung Kim• 2023

Related benchmarks

TaskDatasetResultRank
Place RecognitionHeRCULES Multi-session
Retrieval Rate @1 (SC 01->02)2.4
13
Place RecognitionHeRCULES Sports Complex Single-session (02)
Recall@15.6
8
Place RecognitionHeRCULES Sports Complex Single-session (01)
Recall@14.2
8
Place RecognitionHeRCULES Sports Complex Single-session (03)
Recall@12.5
8
Place RecognitionHeRCULES Library Single-session 01
Recall@13.5
8
Place RecognitionHeRCULES Library Single-session (02)
Recall@14
8
Place RecognitionHeRCULES Library Single-session (03)
Recall@11.6
8
Place RecognitionHeRCULES River Island Single-session (01)
Retrieval Rate @10.2
8
Place RecognitionHeRCULES River Island Single-session (03)
Recall@10.4
8
Place RecognitionHeRCULES River Island Single-session (02)
Recall@10.00e+0
8
Showing 10 of 10 rows

Other info

Follow for update