Radar-only ego-motion estimation in difficult settings via graph matching
<p style="text-align:justify;"> Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
IEEE
2019
|
| _version_ | 1797057933122469888 |
|---|---|
| author | Cen, S Newman, P |
| author_facet | Cen, S Newman, P |
| author_sort | Cen, S |
| collection | OXFORD |
| description | <p style="text-align:justify;"> Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to radar artifacts (e.g., speckle noise and false positives) and requires only one input parameter. We demonstrate its ability to adapt across diverse settings, from urban UK to off-road Iceland, achieving a scan matching accuracy of approximately 5.20 cm and 0.0929 deg when using GPS as ground truth (compared to visual odometry’s 5.77 cm and 0.1032 deg). We present algorithms for key point extraction and data association, framing the latter as a graph matching optimization problem, and provide an in-depth system analysis. </p> |
| first_indexed | 2024-03-06T19:43:23Z |
| format | Conference item |
| id | oxford-uuid:216cf226-3b70-486e-92b8-a1bb65e51299 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T19:43:23Z |
| publishDate | 2019 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:216cf226-3b70-486e-92b8-a1bb65e512992022-03-26T11:33:25ZRadar-only ego-motion estimation in difficult settings via graph matchingConference itemhttp://purl.org/coar/resource_type/c_5794uuid:216cf226-3b70-486e-92b8-a1bb65e51299Symplectic Elements at OxfordIEEE2019Cen, SNewman, P <p style="text-align:justify;"> Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to radar artifacts (e.g., speckle noise and false positives) and requires only one input parameter. We demonstrate its ability to adapt across diverse settings, from urban UK to off-road Iceland, achieving a scan matching accuracy of approximately 5.20 cm and 0.0929 deg when using GPS as ground truth (compared to visual odometry’s 5.77 cm and 0.1032 deg). We present algorithms for key point extraction and data association, framing the latter as a graph matching optimization problem, and provide an in-depth system analysis. </p> |
| spellingShingle | Cen, S Newman, P Radar-only ego-motion estimation in difficult settings via graph matching |
| title | Radar-only ego-motion estimation in difficult settings via graph matching |
| title_full | Radar-only ego-motion estimation in difficult settings via graph matching |
| title_fullStr | Radar-only ego-motion estimation in difficult settings via graph matching |
| title_full_unstemmed | Radar-only ego-motion estimation in difficult settings via graph matching |
| title_short | Radar-only ego-motion estimation in difficult settings via graph matching |
| title_sort | radar only ego motion estimation in difficult settings via graph matching |
| work_keys_str_mv | AT cens radaronlyegomotionestimationindifficultsettingsviagraphmatching AT newmanp radaronlyegomotionestimationindifficultsettingsviagraphmatching |