• search hit 1 of 177
Back to Result List

Analysis of the Impact of Lens Blur on Safety-Critical Automotive Object Detection

  • Camera-based object detection is widely used in safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous vehicle research. Road infrastructure has been designed for human vision, so computer vision, with RGB cameras, is a vital source of semantic information from the environment. Sensors, such as LIDAR and RADAR, are also often utilized for these applications; however, cameras provide a higher spatial resolution and color information. The spatial frequency response (SFR), or sharpness of a camera, utilized in object detection systems must be sufficient to allow a detection algorithm to localize objects in the environment over its lifetime reliably. This study explores the relationship between object detection performance and SFR. Six state-of-the-art object detection models are evaluated with varying levels of lens defocus. A novel raw image dataset is created and utilized, containing pedestrians and cars over a range of distances up to 100-m fromCamera-based object detection is widely used in safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous vehicle research. Road infrastructure has been designed for human vision, so computer vision, with RGB cameras, is a vital source of semantic information from the environment. Sensors, such as LIDAR and RADAR, are also often utilized for these applications; however, cameras provide a higher spatial resolution and color information. The spatial frequency response (SFR), or sharpness of a camera, utilized in object detection systems must be sufficient to allow a detection algorithm to localize objects in the environment over its lifetime reliably. This study explores the relationship between object detection performance and SFR. Six state-of-the-art object detection models are evaluated with varying levels of lens defocus. A novel raw image dataset is created and utilized, containing pedestrians and cars over a range of distances up to 100-m from the sensor. Object detection performance for each defocused dataset is analyzed over a range of distances to determine the minimum SFR necessary in each case. Results show that the relationship between object detection performance and lens blur is much more complex than previous studies have found due to lens field curvature, chromatic aberration, and astigmatisms. We have found that smaller objects are disproportionately impacted by lens blur, and different object detection models have differing levels of robustness to lens blurshow moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Dara Molloy, Patrick Müller, Brian Deegan, Darragh Mullins, Jonathan Horgan, Enda Ward, Edward Jones, Alexander BraunORCiD, Martin Glavin
open access (DINI-Set):open_access
Qualitätssicherung:peer reviewed
open access :Gold - Erstveröffentlichung mit Lizenzhinweis
Fachbereich/Einrichtung:Hochschule Düsseldorf / Fachbereich - Elektro- & Informationstechnik
Document Type:Article
Year of Completion:2024
Language of Publication:English
Publisher:IEEE
Parent Title (English):IEEE Access
Volume:12
Page Number:16
First Page:3554
Last Page:3569
URN:urn:nbn:de:hbz:due62-opus-42999
DOI:https://doi.org/10.1109/ACCESS.2023.3348663
ISSN:2169-3536
Tag:DOAJ
ADAS; Object detection; autonomous vehicles; intelligent transportation system; lens blur
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 62 Ingenieurwissenschaften / 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Licence (German):Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International
Release Date:2024/01/17
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.