Assessing the Impact of Image Quality on Multi-Task Learning Models for 3D Object Detection and Drivable Area Segmentation

dc.contributor.authorJendoubi, Firas
dc.contributor.authorKhemmar, Redouane
dc.contributor.authorRossi, Romain
dc.contributor.authorHaddad, Madjid
dc.contributor.editorSkala, Václav
dc.date.accessioned2025-07-30T10:08:00Z
dc.date.available2025-07-30T10:08:00Z
dc.date.issued2025
dc.description.abstract-translatedIn autonomous driving, the quality of input images is crucial for the accuracy and reliability of perception systems, particularly in tasks like 3D object detection and drivable area segmentation. This study examines the impact of training Multi-Task Learning (M-TL) models exclusively on high-quality images for these applications. Using the KITTI dataset, we apply AI-based and traditional Image Quality Assessment (IQA) algorithms to filter and retain only high-quality images during training. Our experiments reveal that models trained on high-quality images achieve significantly better performance than those trained on the full dataset, including images of varying quality. These findings highlight the critical role of image quality in enhancing the accuracy and robustness of M-TL learning models for autonomous driving. Furthermore, this work emphasizes the importance of integrating image quality evaluation into the data-preprocessing pipeline to optimize model performance.en
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/CSRN.2025-22
dc.identifier.issn2464-4617 (Print)
dc.identifier.issn2464-4625 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62228
dc.language.isoenen
dc.publisherVaclav Skala - UNION Agencyen
dc.rights© Vaclav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectposouzení kvality obrazucs
dc.subjectmultitaskingové učenícs
dc.subjectdetekce 3D objektůcs
dc.subjectsegmentace pojízdné plochycs
dc.subjectinteligentní mobilitacs
dc.subject.translatedimage quality assessmenten
dc.subject.translatedmulti-task learningen
dc.subject.translated3D object detectionen
dc.subject.translateddrivable area segmentationen
dc.subject.translatedsmart mobilityen
dc.titleAssessing the Impact of Image Quality on Multi-Task Learning Models for 3D Object Detection and Drivable Area Segmentationen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size5593737*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
C53.pdf
Size:
5.33 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: