Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation
Radar data can provide additional depth information for monocular depth estimation. It provides a cost-effective solution and is robust in various weather conditions, particularly when compared with lidar. Given the sparse and limited vertical field of view of radar signals, existing methods employ...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/6/1864 |
| _version_ | 1797239349253767168 |
|---|---|
| author | Chen-Chou Lo Patrick Vandewalle |
| author_facet | Chen-Chou Lo Patrick Vandewalle |
| author_sort | Chen-Chou Lo |
| collection | DOAJ |
| description | Radar data can provide additional depth information for monocular depth estimation. It provides a cost-effective solution and is robust in various weather conditions, particularly when compared with lidar. Given the sparse and limited vertical field of view of radar signals, existing methods employ either a vertical extension of radar points or the training of a preprocessing neural network to extend sparse radar points under lidar supervision. In this work, we present a novel radar expansion technique inspired by the joint bilateral filter, tailored for radar-guided monocular depth estimation. Our approach is motivated by the synergy of spatial and range kernels within the joint bilateral filter. Unlike traditional methods that assign a weighted average of nearby pixels to the current pixel, we expand sparse radar points by calculating a confidence score based on the values of spatial and range kernels. Additionally, we propose the use of a range-aware window size for radar expansion instead of a fixed window size in the image plane. Our proposed method effectively increases the number of radar points from an average of 39 points in a raw radar frame to an average of 100 K points. Notably, the expanded radar exhibits fewer intrinsic errors when compared with raw radar and previous methodologies. To validate our approach, we assess our proposed depth estimation model on the nuScenes dataset. Comparative evaluations with existing radar-guided depth estimation models demonstrate its state-of-the-art performance. |
| first_indexed | 2024-04-24T17:50:07Z |
| format | Article |
| id | doaj.art-06f31dc25d0c48d89f71e97fa8fbda27 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T17:50:07Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-06f31dc25d0c48d89f71e97fa8fbda272024-03-27T14:03:59ZengMDPI AGSensors1424-82202024-03-01246186410.3390/s24061864Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth EstimationChen-Chou Lo0Patrick Vandewalle1Processing Speech and Images (PSI), Department of Electrical Engineering (ESAT), KU Leuven, 3001 Leuven, BelgiumProcessing Speech and Images (PSI), Department of Electrical Engineering (ESAT), KU Leuven, 3001 Leuven, BelgiumRadar data can provide additional depth information for monocular depth estimation. It provides a cost-effective solution and is robust in various weather conditions, particularly when compared with lidar. Given the sparse and limited vertical field of view of radar signals, existing methods employ either a vertical extension of radar points or the training of a preprocessing neural network to extend sparse radar points under lidar supervision. In this work, we present a novel radar expansion technique inspired by the joint bilateral filter, tailored for radar-guided monocular depth estimation. Our approach is motivated by the synergy of spatial and range kernels within the joint bilateral filter. Unlike traditional methods that assign a weighted average of nearby pixels to the current pixel, we expand sparse radar points by calculating a confidence score based on the values of spatial and range kernels. Additionally, we propose the use of a range-aware window size for radar expansion instead of a fixed window size in the image plane. Our proposed method effectively increases the number of radar points from an average of 39 points in a raw radar frame to an average of 100 K points. Notably, the expanded radar exhibits fewer intrinsic errors when compared with raw radar and previous methodologies. To validate our approach, we assess our proposed depth estimation model on the nuScenes dataset. Comparative evaluations with existing radar-guided depth estimation models demonstrate its state-of-the-art performance.https://www.mdpi.com/1424-8220/24/6/1864depth estimationnuScenesmultimodalityradarsignal expansionjoint bilateral filter |
| spellingShingle | Chen-Chou Lo Patrick Vandewalle Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation Sensors depth estimation nuScenes multimodality radar signal expansion joint bilateral filter |
| title | Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation |
| title_full | Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation |
| title_fullStr | Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation |
| title_full_unstemmed | Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation |
| title_short | Expanding Sparse Radar Depth Based on Joint Bilateral Filter for Radar-Guided Monocular Depth Estimation |
| title_sort | expanding sparse radar depth based on joint bilateral filter for radar guided monocular depth estimation |
| topic | depth estimation nuScenes multimodality radar signal expansion joint bilateral filter |
| url | https://www.mdpi.com/1424-8220/24/6/1864 |
| work_keys_str_mv | AT chenchoulo expandingsparseradardepthbasedonjointbilateralfilterforradarguidedmonoculardepthestimation AT patrickvandewalle expandingsparseradardepthbasedonjointbilateralfilterforradarguidedmonoculardepthestimation |