UWSpace is currently experiencing technical difficulties resulting from its recent migration to a new version of its software. These technical issues are not affecting the submission and browse features of the site. UWaterloo community members may continue submitting items to UWSpace. We apologize for the inconvenience, and are actively working to resolve these technical issues.
 

LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

dc.contributor.authorPitropov, Matthew
dc.date.accessioned2022-02-09T14:20:18Z
dc.date.available2022-02-09T14:20:18Z
dc.date.issued2022-02-09
dc.date.submitted2022-02-02
dc.description.abstractThe estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods in 3D object detection remains challenging due to timing and computational constraints. To tackle this issue, we propose LiDAR-MIMO, an adaptation of the multi-input multi-output (MIMO) uncertainty estimation method to the LiDAR-based 3D object detection task. Our method modifies the original MIMO by performing multi-input at the feature level to ensure the detection, uncertainty estimation, and runtime performance benefits are retained despite the limited capacity of the underlying detector and the large computational costs of point cloud processing. We compare LiDAR-MIMO with MC dropout and ensembles as baselines and show comparable uncertainty estimation results with only a small number of output heads. Further, LiDAR-MIMO can be configured to be twice as fast as MC dropout and ensembles, while achieving higher mAP than MC dropout and approaching that of ensembles.en
dc.identifier.urihttp://hdl.handle.net/10012/18062
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.subjectobject detectionen
dc.subjectuncertainty estimationen
dc.subjectdeep learningen
dc.titleLiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detectionen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Applied Scienceen
uws-etd.degree.departmentElectrical and Computer Engineeringen
uws-etd.degree.disciplineElectrical and Computer Engineeringen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.embargo.terms0en
uws.contributor.advisorCzarnecki, Krzysztof
uws.contributor.advisorWaslander, Steven
uws.contributor.affiliation1Faculty of Engineeringen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Pitropov_Matthew.pdf
Size:
1.35 MB
Format:
Adobe Portable Document Format
Description:
MASc Thesis
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.4 KB
Format:
Item-specific license agreed upon to submission
Description: