Cargando…

Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles

For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the princip...

Descripción completa

Detalles Bibliográficos
Autores principales: Ponn, Thomas, Kröger, Thomas, Diermeyer, Frank
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7374332/
https://www.ncbi.nlm.nih.gov/pubmed/32630350
http://dx.doi.org/10.3390/s20133699
_version_ 1783561674307928064
author Ponn, Thomas
Kröger, Thomas
Diermeyer, Frank
author_facet Ponn, Thomas
Kröger, Thomas
Diermeyer, Frank
author_sort Ponn, Thomas
collection PubMed
description For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the principle of the camera, performance depends highly on the environmental conditions and can be poor, for example in heavy fog. However, there are other factors influencing the performance of camera-based object detection, which will be comprehensively investigated for the first time in this paper. Furthermore, a precise modeling of the detection performance and the explanation of individual detection results is not possible due to the artificial intelligence based algorithms used. Therefore, a modeling approach based on the investigated influence factors is proposed and the newly developed SHapley Additive exPlanations (SHAP) approach is adopted to analyze and explain the detection performance of different object detection algorithms. The results show that many influence factors such as the relative rotation of an object towards the camera or the position of an object on the image have basically the same influence on the detection performance regardless of the detection algorithm used. In particular, the revealed weaknesses of the tested object detectors can be used to derive challenging and critical scenarios for the testing and type approval of automated vehicles.
format Online
Article
Text
id pubmed-7374332
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-73743322020-08-06 Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles Ponn, Thomas Kröger, Thomas Diermeyer, Frank Sensors (Basel) Article For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the principle of the camera, performance depends highly on the environmental conditions and can be poor, for example in heavy fog. However, there are other factors influencing the performance of camera-based object detection, which will be comprehensively investigated for the first time in this paper. Furthermore, a precise modeling of the detection performance and the explanation of individual detection results is not possible due to the artificial intelligence based algorithms used. Therefore, a modeling approach based on the investigated influence factors is proposed and the newly developed SHapley Additive exPlanations (SHAP) approach is adopted to analyze and explain the detection performance of different object detection algorithms. The results show that many influence factors such as the relative rotation of an object towards the camera or the position of an object on the image have basically the same influence on the detection performance regardless of the detection algorithm used. In particular, the revealed weaknesses of the tested object detectors can be used to derive challenging and critical scenarios for the testing and type approval of automated vehicles. MDPI 2020-07-01 /pmc/articles/PMC7374332/ /pubmed/32630350 http://dx.doi.org/10.3390/s20133699 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ponn, Thomas
Kröger, Thomas
Diermeyer, Frank
Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title_full Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title_fullStr Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title_full_unstemmed Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title_short Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles
title_sort identification and explanation of challenging conditions for camera-based object detection of automated vehicles
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7374332/
https://www.ncbi.nlm.nih.gov/pubmed/32630350
http://dx.doi.org/10.3390/s20133699
work_keys_str_mv AT ponnthomas identificationandexplanationofchallengingconditionsforcamerabasedobjectdetectionofautomatedvehicles
AT krogerthomas identificationandexplanationofchallengingconditionsforcamerabasedobjectdetectionofautomatedvehicles
AT diermeyerfrank identificationandexplanationofchallengingconditionsforcamerabasedobjectdetectionofautomatedvehicles