Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras
In this paper, an efficient normal estimation and filtering method for depth images acquired by Time-of-Flight (ToF) cameras is proposed. The method is based on a common feature pyramid networks (FPN) architecture. The normal estimation method is called ToFNest, and the filtering method ToFClean. Bo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/18/6257 |
| _version_ | 1797517209077022720 |
|---|---|
| author | Szilárd Molnár Benjamin Kelényi Levente Tamas |
| author_facet | Szilárd Molnár Benjamin Kelényi Levente Tamas |
| author_sort | Szilárd Molnár |
| collection | DOAJ |
| description | In this paper, an efficient normal estimation and filtering method for depth images acquired by Time-of-Flight (ToF) cameras is proposed. The method is based on a common feature pyramid networks (FPN) architecture. The normal estimation method is called ToFNest, and the filtering method ToFClean. Both of these low-level 3D point cloud processing methods start from the 2D depth images, projecting the measured data into the 3D space and computing a task-specific loss function. Despite the simplicity, the methods prove to be efficient in terms of robustness and runtime. In order to validate the methods, extensive evaluations on public and custom datasets were performed. Compared with the state-of-the-art methods, the ToFNest and ToFClean algorithms are faster by an order of magnitude without losing precision on public datasets. |
| first_indexed | 2024-03-10T07:13:33Z |
| format | Article |
| id | doaj.art-7960f61fcbad4d6187c77b3e340a45d2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T07:13:33Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7960f61fcbad4d6187c77b3e340a45d22023-11-22T15:14:06ZengMDPI AGSensors1424-82202021-09-012118625710.3390/s21186257Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth CamerasSzilárd Molnár0Benjamin Kelényi1Levente Tamas2Department of Automation, Technical University of Cluj-Napoca, Memorandumului St. 28, 400114 Cluj-Napoca, RomaniaDepartment of Automation, Technical University of Cluj-Napoca, Memorandumului St. 28, 400114 Cluj-Napoca, RomaniaDepartment of Automation, Technical University of Cluj-Napoca, Memorandumului St. 28, 400114 Cluj-Napoca, RomaniaIn this paper, an efficient normal estimation and filtering method for depth images acquired by Time-of-Flight (ToF) cameras is proposed. The method is based on a common feature pyramid networks (FPN) architecture. The normal estimation method is called ToFNest, and the filtering method ToFClean. Both of these low-level 3D point cloud processing methods start from the 2D depth images, projecting the measured data into the 3D space and computing a task-specific loss function. Despite the simplicity, the methods prove to be efficient in terms of robustness and runtime. In order to validate the methods, extensive evaluations on public and custom datasets were performed. Compared with the state-of-the-art methods, the ToFNest and ToFClean algorithms are faster by an order of magnitude without losing precision on public datasets.https://www.mdpi.com/1424-8220/21/18/6257normal estimationfilteringdepth imagepoint cloudFPN |
| spellingShingle | Szilárd Molnár Benjamin Kelényi Levente Tamas Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras Sensors normal estimation filtering depth image point cloud FPN |
| title | Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras |
| title_full | Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras |
| title_fullStr | Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras |
| title_full_unstemmed | Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras |
| title_short | Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras |
| title_sort | feature pyramid network based efficient normal estimation and filtering for time of flight depth cameras |
| topic | normal estimation filtering depth image point cloud FPN |
| url | https://www.mdpi.com/1424-8220/21/18/6257 |
| work_keys_str_mv | AT szilardmolnar featurepyramidnetworkbasedefficientnormalestimationandfilteringfortimeofflightdepthcameras AT benjaminkelenyi featurepyramidnetworkbasedefficientnormalestimationandfilteringfortimeofflightdepthcameras AT leventetamas featurepyramidnetworkbasedefficientnormalestimationandfilteringfortimeofflightdepthcameras |