Add abstract
Want to add your dissertation abstract to this database? It only takes a minute!
Search abstract
Search for abstracts by subject, author or institution
Want to add your dissertation abstract to this database? It only takes a minute!
Search for abstracts by subject, author or institution
CenterPoint-based 3D Object Detection in ONCE Dataset
by Yuwei Du
| Institution: | KTH |
|---|---|
| Department: | Electrical Engineering and Computer Science (EECS) |
| Degree: | |
| Year: | 2022 |
| Keywords: | 3D Object Detection; Keypoint Detector; Class Balance; Self-Calibrated Convolution; IoU-aware Detector; Box Ensembles; 3D-Objektdetektering; Nyckelpunktsdetektor; Klassbalans; Självkalibrerad Faltning; IoU-medveten Detektor; Boxensembler; Electrical Engin |
| Posted: | 3/25/2025 |
| Record ID: | 2267673 |
| Full text PDF: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-320371 |
High-efficiency point cloud 3D object detection is important for autonomous driving. 3D object detection based on point cloud data is naturally more complex and difficult than the 2D task based on images. Researchers keep working on improving 3D object detection performance in autonomous driving scenarios recently. In this report, we present our optimized point cloud 3D object detection model based on CenterPoint method. CenterPoint detects centers of objects using a keypoint detector on top of a voxel-based backbone, then regresses to other attributes. On the basis of this, our modified model is featured with an improved Region Proposal Network (RPN) with extended receptive field, an added sub-head that produces an IoU-aware confidence score, as well as box ensemble inference strategies with more accurate predictions. These model enhancements, together with class-balanced data pre-processing, lead to a competitive accuracy of 72.02 mAP on ONCE Validation Split, and 79.09 mAP on ONCE Test Split. Our model gains the fifth place of ICCV 2021 Workshop SSLAD Track 3D Object Detection Challenge. Högeffektiv punktmoln 3D-objektdetektering är viktig för autonom körning. 3D-objektdetektering baserad på punktmolnsdata är naturligtvis mer komplex och svårare än 2D-uppgiften baserad på bilder. Forskare fortsätter att arbeta med att förbättra 3D-objektdetekteringsprestandan i scenarier för autonom körning nyligen. I den här rapporten presenterar vi vår optimerade 3D-objektdetekteringsmodell baserad på CenterPoint. CenterPoint upptäcker objektcentrum med hjälp av en nyckelpunktsdetektor ovanpå en voxelbaserad ryggrad och går sedan tillbaka till andra attribut. På grundval av detta presenteras vår modifierade modell med ett förbättrat regionförslagsnätverk med utökat receptivt fält, en extra underrubrik som producerar en IoU-medveten konfidenspoäng och ensemblestrategier med mer exakta förutsägelser. Dessa modellförbättringar, tillsammans med klassbalanserad dataförbehandling, leder till en konkurrenskraftig noggrannhet på 72,02 mAP på ONCE Validation Split och 79,09 mAP på ONCE Test Split. Vår modell vinner femteplatsen i ICCV 2021 Workshop SSLAD Track 3D Object Detection Challenge.
Want to add your dissertation abstract to this database? It only takes a minute!
Search for abstracts by subject, author or institution
|
|
Predicting the Admission Decision of a Participant...
|
|
|
Development of New Models Using Machine Learning M...
|
|
|
The Adaptation Process of a Resettled Community to...
A Study of the Nubian Experience in Egypt
|
|
|
Development of an Artificial Intelligence System f...
|
|
|
Theoretical and Experimental Analysis of Dissipati...
|
|
|
Optical Fiber Sensors for Residential Environments
|
|
|
Calibration of Deterministic Parameters
Reassessment of Offshore Platforms in the Arabian ...
|
|
|
How Passion Relates to Performance
A Study of Consultant Civil Engineers
|