Comparative Analysis of Point Sampling Strategies in Point-based 3D Object Detection
| dc.contributor.author | Zhu, Rui | |
| dc.contributor.supervisor | Li, Kin Fun | |
| dc.date.accessioned | 2023-12-11T22:35:43Z | |
| dc.date.available | 2023-12-11T22:35:43Z | |
| dc.date.copyright | 2023 | en_US |
| dc.date.issued | 2023-12-11 | |
| dc.degree.department | Department of Electrical and Computer Engineering | |
| dc.degree.level | Master of Applied Science M.A.Sc. | en_US |
| dc.description.abstract | Point-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.scholarlevel | Graduate | en_US |
| dc.identifier.uri | http://hdl.handle.net/1828/15695 | |
| dc.language | English | eng |
| dc.language.iso | en | en_US |
| dc.rights | Available to the World Wide Web | en_US |
| dc.subject | 3D object detection | en_US |
| dc.subject | point sampling | en_US |
| dc.subject | point cloud | en_US |
| dc.subject | deep learning | en_US |
| dc.title | Comparative Analysis of Point Sampling Strategies in Point-based 3D Object Detection | en_US |
| dc.type | Thesis | en_US |