Development and Experimental Validation of an Intelligent Camera Model for Automated Driving

The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Simon Genser, Stefan Muckenhuber, Selim Solmaz, Jakob Reckenzaun
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	automotive perception sensors sensor model virtual testing ADAS/AD function automotive camera Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/d88de2dbc47842d9a93cd5f7c8bb2092
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d88de2dbc47842d9a93cd5f7c8bb2092
record_format	dspace
spelling	oai:doaj.org-article:d88de2dbc47842d9a93cd5f7c8bb20922021-11-25T18:57:36ZDevelopment and Experimental Validation of an Intelligent Camera Model for Automated Driving10.3390/s212275831424-8220https://doaj.org/article/d88de2dbc47842d9a93cd5f7c8bb20922021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7583https://doaj.org/toc/1424-8220The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a large measurement campaign on a Hungarian highway to support the development and experimental validation of the new approach. The quality of the model was tested and compared to reference measurements, leading to a pointwise position error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.60</mn><mo>%</mo></mrow></semantics></math></inline-formula> in the lateral and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.57</mn><mo>%</mo></mrow></semantics></math></inline-formula> in the longitudinal direction. Additionally, the modeling of the natural scattering of the sensor model output was satisfying. In particular, the deviations of the position measurements were well modeled with this approach.Simon GenserStefan MuckenhuberSelim SolmazJakob ReckenzaunMDPI AGarticleautomotive perception sensorssensor modelvirtual testingADAS/AD functionautomotive cameraChemical technologyTP1-1185ENSensors, Vol 21, Iss 7583, p 7583 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	automotive perception sensors sensor model virtual testing ADAS/AD function automotive camera Chemical technology TP1-1185
spellingShingle	automotive perception sensors sensor model virtual testing ADAS/AD function automotive camera Chemical technology TP1-1185 Simon Genser Stefan Muckenhuber Selim Solmaz Jakob Reckenzaun Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
description	The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a large measurement campaign on a Hungarian highway to support the development and experimental validation of the new approach. The quality of the model was tested and compared to reference measurements, leading to a pointwise position error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.60</mn><mo>%</mo></mrow></semantics></math></inline-formula> in the lateral and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.57</mn><mo>%</mo></mrow></semantics></math></inline-formula> in the longitudinal direction. Additionally, the modeling of the natural scattering of the sensor model output was satisfying. In particular, the deviations of the position measurements were well modeled with this approach.
format	article
author	Simon Genser Stefan Muckenhuber Selim Solmaz Jakob Reckenzaun
author_facet	Simon Genser Stefan Muckenhuber Selim Solmaz Jakob Reckenzaun
author_sort	Simon Genser
title	Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
title_short	Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
title_full	Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
title_fullStr	Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
title_full_unstemmed	Development and Experimental Validation of an Intelligent Camera Model for Automated Driving
title_sort	development and experimental validation of an intelligent camera model for automated driving
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d88de2dbc47842d9a93cd5f7c8bb2092
work_keys_str_mv	AT simongenser developmentandexperimentalvalidationofanintelligentcameramodelforautomateddriving AT stefanmuckenhuber developmentandexperimentalvalidationofanintelligentcameramodelforautomateddriving AT selimsolmaz developmentandexperimentalvalidationofanintelligentcameramodelforautomateddriving AT jakobreckenzaun developmentandexperimentalvalidationofanintelligentcameramodelforautomateddriving
_version_	1718410493725507584

Development and Experimental Validation of an Intelligent Camera Model for Automated Driving

Ejemplares similares