Publications
Detailed Information
MD3D: Mixture-Density-Based 3D Object Detection in Point Clouds
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Jaeseok | - |
dc.contributor.author | Song, Yeji | - |
dc.contributor.author | Kim, Yerim | - |
dc.contributor.author | Yoo, Jaeyoung | - |
dc.contributor.author | Kwak, No Jun | - |
dc.date.accessioned | 2024-08-08T01:22:03Z | - |
dc.date.available | 2024-08-08T01:22:03Z | - |
dc.date.created | 2022-11-23 | - |
dc.date.created | 2022-11-23 | - |
dc.date.issued | 2022-09 | - |
dc.identifier.citation | IEEE Access, Vol.10, pp.104011-104022 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://hdl.handle.net/10371/205436 | - |
dc.description.abstract | The design factors of anchor boxes, such as shape, placement, and target assignment policy, greatly influence the performance and latency of the 3D object detectors. Unlike image-based 2D anchors, 3D anchors must be placed in a 3D space and determined differently for each class of different sizes. This imposes a significant burden on the design complexity. To tackle this issue, various studies have been conducted on how to set the anchor form. However, for practical reasons, anchor-based methods select the anchor design by compromising between performance and latency. Consequently, only objects that are similar in shape and size to an anchor can obtain high accuracy. In this paper, we propose a Mixture-Density-based 3D Object Detection (MD3D) in point clouds to predict the distribution of 3D bounding boxes using a Gaussian Mixture Model (GMM). With an anchor-free detection head, MD3D requires few hand-crafted design factors and eliminates the inefficiency of separating the regression channel for each class, and thus offering both latency and memory benefits. MD3D is designed to utilize various types of feature encoding; therfore, it can be applied flexibly by replacing only the detection head of the existing detectors. Experimental results on the KITTI and Waymo open datasets show that the proposed method outperforms its counterparts that are based on the conventional anchor-based detection head in its overall performance, latency, and memory. The code is publicly available at https://github.com/sky77764/MD3D | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | MD3D: Mixture-Density-Based 3D Object Detection in Point Clouds | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3210108 | - |
dc.citation.journaltitle | IEEE Access | - |
dc.identifier.wosid | 000865072800001 | - |
dc.identifier.scopusid | 2-s2.0-85139450118 | - |
dc.citation.endpage | 104022 | - |
dc.citation.startpage | 104011 | - |
dc.citation.volume | 10 | - |
dc.description.isOpenAccess | Y | - |
dc.contributor.affiliatedAuthor | Kwak, No Jun | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Three-dimensional displays | - |
dc.subject.keywordAuthor | Detectors | - |
dc.subject.keywordAuthor | Point cloud compression | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | Autonomous vehicles | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Autonomous vehicles | - |
dc.subject.keywordAuthor | object detection | - |
dc.subject.keywordAuthor | visual perception | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Related Researcher
- Graduate School of Convergence Science & Technology
- Department of Intelligence and Information
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.