Phenomenological Modelling of Camera Performance for Road Marking Detection
With the development of autonomous driving technology, the requirements for machine perception have increased significantly. In particular, camera-based lane detection plays an essential role in autonomous vehicle trajectory planning. However, lane detection is subject to high complexity, and it is...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/1/194 |
_version_ | 1797499169984741376 |
---|---|
author | Hexuan Li Kanuric Tarik Sadegh Arefnezhad Zoltan Ferenc Magosi Christoph Wellershaus Darko Babic Dario Babic Viktor Tihanyi Arno Eichberger Marcel Carsten Baunach |
author_facet | Hexuan Li Kanuric Tarik Sadegh Arefnezhad Zoltan Ferenc Magosi Christoph Wellershaus Darko Babic Dario Babic Viktor Tihanyi Arno Eichberger Marcel Carsten Baunach |
author_sort | Hexuan Li |
collection | DOAJ |
description | With the development of autonomous driving technology, the requirements for machine perception have increased significantly. In particular, camera-based lane detection plays an essential role in autonomous vehicle trajectory planning. However, lane detection is subject to high complexity, and it is sensitive to illumination variation, appearance, and age of lane marking. In addition, the sheer infinite number of test cases for highly automated vehicles requires an increasing portion of test and validation to be performed in simulation and X-in-the-loop testing. To model the complexity of camera-based lane detection, physical models are often used, which consider the optical properties of the imager as well as image processing itself. This complexity results in high efforts for the simulation in terms of modelling as well as computational costs. This paper presents a Phenomenological Lane Detection Model (PLDM) to simulate camera performance. The innovation of the approach is the modelling technique using Multi-Layer Perceptron (MLP), which is a class of Neural Network (NN). In order to prepare input data for our neural network model, massive driving tests have been performed on the M86 highway road in Hungary. The model’s inputs include vehicle dynamics signals (such as speed and acceleration, etc.). In addition, the difference between the reference output from the digital-twin map of the highway and camera lane detection results is considered as the target of the NN. The network consists of four hidden layers, and scaled conjugate gradient backpropagation is used for training the network. The results demonstrate that PLDM can sufficiently replicate camera detection performance in the simulation. The modelling approach improves the realism of camera sensor simulation as well as computational effort for X-in-the-loop applications and thereby supports safety validation of camera-based functionality in automated driving, which decreases the energy consumption of vehicles. |
first_indexed | 2024-03-10T03:43:36Z |
format | Article |
id | doaj.art-961541ef2fe64bd0b5e53614858329d3 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T03:43:36Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-961541ef2fe64bd0b5e53614858329d32023-11-23T11:26:56ZengMDPI AGEnergies1996-10732021-12-0115119410.3390/en15010194Phenomenological Modelling of Camera Performance for Road Marking DetectionHexuan Li0Kanuric Tarik1Sadegh Arefnezhad2Zoltan Ferenc Magosi3Christoph Wellershaus4Darko Babic5Dario Babic6Viktor Tihanyi7Arno Eichberger8Marcel Carsten Baunach9Institute of Automotive Engineering, TU Graz, 8010 Graz, AustriaInstitute of Automotive Engineering, TU Graz, 8010 Graz, AustriaInstitute of Automotive Engineering, TU Graz, 8010 Graz, AustriaInstitute of Automotive Engineering, TU Graz, 8010 Graz, AustriaInstitute of Automotive Engineering, TU Graz, 8010 Graz, AustriaFaculty of Transport and Traffic Sciences, University of Zagreb, 10000 Zagreb, CroatiaFaculty of Transport and Traffic Sciences, University of Zagreb, 10000 Zagreb, CroatiaDepartment of Automotive Technologies, Budapest University of Technology and Economics, 1111 Budapest, HungaryInstitute of Automotive Engineering, TU Graz, 8010 Graz, AustriaInstitute of Technical Informatics, TU Graz, 8010 Graz, AustriaWith the development of autonomous driving technology, the requirements for machine perception have increased significantly. In particular, camera-based lane detection plays an essential role in autonomous vehicle trajectory planning. However, lane detection is subject to high complexity, and it is sensitive to illumination variation, appearance, and age of lane marking. In addition, the sheer infinite number of test cases for highly automated vehicles requires an increasing portion of test and validation to be performed in simulation and X-in-the-loop testing. To model the complexity of camera-based lane detection, physical models are often used, which consider the optical properties of the imager as well as image processing itself. This complexity results in high efforts for the simulation in terms of modelling as well as computational costs. This paper presents a Phenomenological Lane Detection Model (PLDM) to simulate camera performance. The innovation of the approach is the modelling technique using Multi-Layer Perceptron (MLP), which is a class of Neural Network (NN). In order to prepare input data for our neural network model, massive driving tests have been performed on the M86 highway road in Hungary. The model’s inputs include vehicle dynamics signals (such as speed and acceleration, etc.). In addition, the difference between the reference output from the digital-twin map of the highway and camera lane detection results is considered as the target of the NN. The network consists of four hidden layers, and scaled conjugate gradient backpropagation is used for training the network. The results demonstrate that PLDM can sufficiently replicate camera detection performance in the simulation. The modelling approach improves the realism of camera sensor simulation as well as computational effort for X-in-the-loop applications and thereby supports safety validation of camera-based functionality in automated driving, which decreases the energy consumption of vehicles.https://www.mdpi.com/1996-1073/15/1/194lane detectionsimulation and modellingmulti-layer perceptron |
spellingShingle | Hexuan Li Kanuric Tarik Sadegh Arefnezhad Zoltan Ferenc Magosi Christoph Wellershaus Darko Babic Dario Babic Viktor Tihanyi Arno Eichberger Marcel Carsten Baunach Phenomenological Modelling of Camera Performance for Road Marking Detection Energies lane detection simulation and modelling multi-layer perceptron |
title | Phenomenological Modelling of Camera Performance for Road Marking Detection |
title_full | Phenomenological Modelling of Camera Performance for Road Marking Detection |
title_fullStr | Phenomenological Modelling of Camera Performance for Road Marking Detection |
title_full_unstemmed | Phenomenological Modelling of Camera Performance for Road Marking Detection |
title_short | Phenomenological Modelling of Camera Performance for Road Marking Detection |
title_sort | phenomenological modelling of camera performance for road marking detection |
topic | lane detection simulation and modelling multi-layer perceptron |
url | https://www.mdpi.com/1996-1073/15/1/194 |
work_keys_str_mv | AT hexuanli phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT kanurictarik phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT sadegharefnezhad phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT zoltanferencmagosi phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT christophwellershaus phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT darkobabic phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT dariobabic phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT viktortihanyi phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT arnoeichberger phenomenologicalmodellingofcameraperformanceforroadmarkingdetection AT marcelcarstenbaunach phenomenologicalmodellingofcameraperformanceforroadmarkingdetection |