Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion
Due to the correlation between friction reduction and the road-covering water film height, knowledge about the current wetness level is of relevance for drivers and autonomous systems. A promising approach for wetness quantification is based on capacitive transducer arrays that enable to detect wate...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9908566/ |
| _version_ | 1817985833113747456 |
|---|---|
| author | Jakob Doring Julia Scholtyssek Andreas Beering Karl-Ludwig Krieger |
| author_facet | Jakob Doring Julia Scholtyssek Andreas Beering Karl-Ludwig Krieger |
| author_sort | Jakob Doring |
| collection | DOAJ |
| description | Due to the correlation between friction reduction and the road-covering water film height, knowledge about the current wetness level is of relevance for drivers and autonomous systems. A promising approach for wetness quantification is based on capacitive transducer arrays that enable to detect water spray ejected by the tires. Even though previous studies on this approach have shown the feasibility of wetness classification, optimization opportunities exist. While these previous investigations were limited to one feature selection algorithm, we study various algorithms and demonstrate the potential for optimization. Besides an application-specific algorithm that is capable of determining class-dependent features resulting in a performance improvement of more than 0.03 for the considered evaluation metrics, sequential forward floating selection in particular yields the most significant performance increase of more than 0.06. In addition, prior studies were limited to a test track with constrained conditions. Thus, in order to study the transferability of the preceding results, we present investigations on new experimental data acquired on public roads. The unknown and varying environmental conditions on public roads as well as a larger wheel speed range and steering angle effects are shown to significantly decrease classifier performance. We demonstrate that fusing two transducer arrays of different wheel arch liners increases performance by around 0.02. Here, a considerable information benefit can be attributed to the different transducer positions with design-related advantages. Furthermore, we show that the fusion with additional sensor data available in the vehicle results in a further performance improvement of more than 0.02. |
| first_indexed | 2024-04-14T00:02:58Z |
| format | Article |
| id | doaj.art-5625d499576e4852ad233432a47ec3f9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T00:02:58Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5625d499576e4852ad233432a47ec3f92022-12-22T02:23:39ZengIEEEIEEE Access2169-35362022-01-011010624810625710.1109/ACCESS.2022.32116489908566Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor FusionJakob Doring0https://orcid.org/0000-0002-1418-749XJulia Scholtyssek1https://orcid.org/0000-0002-5335-9389Andreas Beering2https://orcid.org/0000-0002-8098-2926Karl-Ludwig Krieger3https://orcid.org/0000-0003-1776-0228Institute of Electrodynamics and Microelectronics, University of Bremen, Bremen, GermanyInstitute of Electrodynamics and Microelectronics, University of Bremen, Bremen, GermanyInstitute of Electrodynamics and Microelectronics, University of Bremen, Bremen, GermanyInstitute of Electrodynamics and Microelectronics, University of Bremen, Bremen, GermanyDue to the correlation between friction reduction and the road-covering water film height, knowledge about the current wetness level is of relevance for drivers and autonomous systems. A promising approach for wetness quantification is based on capacitive transducer arrays that enable to detect water spray ejected by the tires. Even though previous studies on this approach have shown the feasibility of wetness classification, optimization opportunities exist. While these previous investigations were limited to one feature selection algorithm, we study various algorithms and demonstrate the potential for optimization. Besides an application-specific algorithm that is capable of determining class-dependent features resulting in a performance improvement of more than 0.03 for the considered evaluation metrics, sequential forward floating selection in particular yields the most significant performance increase of more than 0.06. In addition, prior studies were limited to a test track with constrained conditions. Thus, in order to study the transferability of the preceding results, we present investigations on new experimental data acquired on public roads. The unknown and varying environmental conditions on public roads as well as a larger wheel speed range and steering angle effects are shown to significantly decrease classifier performance. We demonstrate that fusing two transducer arrays of different wheel arch liners increases performance by around 0.02. Here, a considerable information benefit can be attributed to the different transducer positions with design-related advantages. Furthermore, we show that the fusion with additional sensor data available in the vehicle results in a further performance improvement of more than 0.02.https://ieeexplore.ieee.org/document/9908566/Capacitive sensorsdriver assistanceroad surface wetness detectionvehicle safetywetness classification |
| spellingShingle | Jakob Doring Julia Scholtyssek Andreas Beering Karl-Ludwig Krieger Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion IEEE Access Capacitive sensors driver assistance road surface wetness detection vehicle safety wetness classification |
| title | Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion |
| title_full | Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion |
| title_fullStr | Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion |
| title_full_unstemmed | Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion |
| title_short | Optimization of Road Surface Wetness Classification Using Feature Selection Algorithms and Sensor Fusion |
| title_sort | optimization of road surface wetness classification using feature selection algorithms and sensor fusion |
| topic | Capacitive sensors driver assistance road surface wetness detection vehicle safety wetness classification |
| url | https://ieeexplore.ieee.org/document/9908566/ |
| work_keys_str_mv | AT jakobdoring optimizationofroadsurfacewetnessclassificationusingfeatureselectionalgorithmsandsensorfusion AT juliascholtyssek optimizationofroadsurfacewetnessclassificationusingfeatureselectionalgorithmsandsensorfusion AT andreasbeering optimizationofroadsurfacewetnessclassificationusingfeatureselectionalgorithmsandsensorfusion AT karlludwigkrieger optimizationofroadsurfacewetnessclassificationusingfeatureselectionalgorithmsandsensorfusion |