Comparative Analysis of Point Sampling Strategies in Point-based 3D Object Detection

dc.contributor.authorZhu, Rui
dc.contributor.supervisorLi, Kin Fun
dc.date.accessioned2023-12-11T22:35:43Z
dc.date.available2023-12-11T22:35:43Z
dc.date.copyright2023en_US
dc.date.issued2023-12-11
dc.degree.departmentDepartment of Electrical and Computer Engineering
dc.degree.levelMaster of Applied Science M.A.Sc.en_US
dc.description.abstractPoint-based 3D object detection has been receiving increasing attention as it can preserve the geometric information of a point cloud and avoid quantization errors or information loss caused by voxelization or projection. Point sampling plays an important role in point-based 3D detectors yet has not been thoroughly explored. In this research, we conduct a comparative analysis of three point sampling strategies to gain a deep understanding of the effect that each strategy imposes on the final performance and intermediate stages of the network. We introduce density-aware sampling and semantic-aware sampling strategies and fit them into the backbone of a lightweight and effective baseline model, aiming to reduce the density imbalance of the point cloud and better utilize semantic information. The density-aware strategy effectively balances the density but the inference time is not applicable for real-time application. Semantic-aware sampling biased on foreground points achieves a 0.19\% improvement on the baseline. Analysis on statistics and visualization reveals future research direction. We build our models on MMDetection3D platform and evaluate the performance on KITTI dataset.en_US
dc.description.scholarlevelGraduateen_US
dc.identifier.urihttp://hdl.handle.net/1828/15695
dc.languageEnglisheng
dc.language.isoenen_US
dc.rightsAvailable to the World Wide Weben_US
dc.subject3D object detectionen_US
dc.subjectpoint samplingen_US
dc.subjectpoint clouden_US
dc.subjectdeep learningen_US
dc.titleComparative Analysis of Point Sampling Strategies in Point-based 3D Object Detectionen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Rui_Zhu_MASc_2023.pdf
Size:
2.36 MB
Format:
Adobe Portable Document Format
Description:
Main article
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2 KB
Format:
Item-specific license agreed upon to submission
Description: