Uncertainty estimation in multi-modal 3D object detection

Visa enkel post
dc.contributor.authorRosén, Anton
dc.contributor.departmentChalmers tekniska högskola / Institutionen för elektrotekniksv
dc.contributor.examinerHammarstrand, Lars
dc.contributor.supervisorJohnander, Joakim
dc.contributor.supervisorFatemi, Maryam
dc.contributor.supervisorLindström, Carl
dc.date.accessioned2024-06-28T07:17:23Z
dc.date.available2024-06-28T07:17:23Z
dc.date.issued2024
dc.date.submitted
dc.description.abstractAbstract Object detection is an important part of many autonomous driving systems, providing condensed information about the vehicle’s surroundings. For good performance in different environmental conditions, multi-modal object detection is often used, where information from different sensors are fused. Due to factors such as sensor noise, occlusion, and adverse weather conditions, there is an inherent uncertainty in the object detection task. Most state-of-the-art approaches for multi-modal 3D object detection do not model these uncertainties for regression. Explicitly modeling and estimating the uncertainties leads to higher interpretability, allows analysis of difficult situations, and can improve the performance of downstream tasks. In this work, we explore how uncertainty can be modeled and estimated in multimodal 3D object detection. We show that directly modeling the uncertainties of bounding box parameters can provide meaningful uncertainty estimates without sacrificing neither predictive performance nor computational efficiency. We compare modeling the uncertainties both separately per detection, using normally distributed random vectors, and jointly per frame, using Poisson multi-Bernoulli random finite sets. Our results show that separate modeling enhances predictive performance, while joint modeling yields more accurate uncertainty estimates. Additionally, we demonstrate that these predicted uncertainties can identify unlabeled data where the model performs poorly, underscoring their importance for more interpretable and safe autonomous driving systems.
dc.identifier.coursecodeEENX30
dc.identifier.urihttp://hdl.handle.net/20.500.12380/308114
dc.language.isoeng
dc.setspec.uppsokTechnology
dc.subjectKeywords: 3D Object Detection, Sensor Fusion, Uncertainty Estimation
dc.titleUncertainty estimation in multi-modal 3D object detection
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeData science and AI (MPDSC), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
Uncertainty_estimation_in_multi_modal_3D_object_detection.pdf
Storlek:
23.47 MB
Format:
Adobe Portable Document Format
Beskrivning:
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen