Adaptive Voxelization Strategy for 3D Object Detection

Jyun Hong He; Xiu Zhi Chen; You Shiuan Lin; Chen Yu Yang; Yen Lin Chen; Hsin Han Chiang

doi:10.1109/ICCE-Taiwan55306.2022.9869047

Adaptive Voxelization Strategy for 3D Object Detection

Jyun Hong He
, Xiu Zhi Chen
, You Shiuan Lin
, Chen Yu Yang
, Yen Lin Chen^*
, Hsin Han Chiang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

3D object detection techniques rely on features obtained from point cloud data structures to identify and label the frame range of objects. Past techniques of converting point cloud data into voxel grids or image sets would make the data unnecessarily large, and it would be impractical to slice all space into a voxel grid of the same scale for objects of different types and depths. In this paper, the RGB-D depth camera is used to obtain the original point cloud information, and the mature 2D target detection technology and advanced 3D deep learning are used to locate the target. In addition, the voxel grid structure is improved, and the proportion and size of the voxel grid are appropriately adjusted by adopting the method of image category adaptation and spatial depth clustering to obtain more accurate point cloud features and achieve fast and accurate 3D object detection.

Original language	English
Title of host publication	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	423-424
Number of pages	2
ISBN (Electronic)	9781665470506
DOIs	https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869047
Publication status	Published - 2022
Externally published	Yes
Event	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, Taiwan Duration: 2022 Jul 6 → 2022 Jul 8

Publication series

Name	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Conference

Conference	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
Country/Territory	Taiwan
City	Taipei
Period	2022/07/06 → 2022/07/08

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Hardware and Architecture
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Media Technology
Health Informatics
Instrumentation

Access to Document

10.1109/ICCE-Taiwan55306.2022.9869047

Cite this

He, J. H., Chen, X. Z., Lin, Y. S., Yang, C. Y., Chen, Y. L., & Chiang, H. H. (2022). Adaptive Voxelization Strategy for 3D Object Detection. In Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 (pp. 423-424). (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869047

Adaptive Voxelization Strategy for 3D Object Detection. / He, Jyun Hong; Chen, Xiu Zhi; Lin, You Shiuan et al.
Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 423-424 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

He, JH, Chen, XZ, Lin, YS, Yang, CY, Chen, YL & Chiang, HH 2022, Adaptive Voxelization Strategy for 3D Object Detection. in Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Institute of Electrical and Electronics Engineers Inc., pp. 423-424, 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Taipei, Taiwan, 2022/07/06. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869047

He JH, Chen XZ, Lin YS, Yang CY, Chen YL, Chiang HH. Adaptive Voxelization Strategy for 3D Object Detection. In Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 423-424. (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). doi: 10.1109/ICCE-Taiwan55306.2022.9869047

He, Jyun Hong ; Chen, Xiu Zhi ; Lin, You Shiuan et al. / Adaptive Voxelization Strategy for 3D Object Detection. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 423-424 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

@inproceedings{1f15caeed58c44fe81d592442d8b87da,

title = "Adaptive Voxelization Strategy for 3D Object Detection",

abstract = "3D object detection techniques rely on features obtained from point cloud data structures to identify and label the frame range of objects. Past techniques of converting point cloud data into voxel grids or image sets would make the data unnecessarily large, and it would be impractical to slice all space into a voxel grid of the same scale for objects of different types and depths. In this paper, the RGB-D depth camera is used to obtain the original point cloud information, and the mature 2D target detection technology and advanced 3D deep learning are used to locate the target. In addition, the voxel grid structure is improved, and the proportion and size of the voxel grid are appropriately adjusted by adopting the method of image category adaptation and spatial depth clustering to obtain more accurate point cloud features and achieve fast and accurate 3D object detection.",

author = "He, \{Jyun Hong\} and Chen, \{Xiu Zhi\} and Lin, \{You Shiuan\} and Yang, \{Chen Yu\} and Chen, \{Yen Lin\} and Chiang, \{Hsin Han\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 ; Conference date: 06-07-2022 Through 08-07-2022",

year = "2022",

doi = "10.1109/ICCE-Taiwan55306.2022.9869047",

language = "English",

series = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "423--424",

booktitle = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

}

TY - GEN

T1 - Adaptive Voxelization Strategy for 3D Object Detection

AU - He, Jyun Hong

AU - Chen, Xiu Zhi

AU - Lin, You Shiuan

AU - Yang, Chen Yu

AU - Chen, Yen Lin

AU - Chiang, Hsin Han

PY - 2022

Y1 - 2022

N2 - 3D object detection techniques rely on features obtained from point cloud data structures to identify and label the frame range of objects. Past techniques of converting point cloud data into voxel grids or image sets would make the data unnecessarily large, and it would be impractical to slice all space into a voxel grid of the same scale for objects of different types and depths. In this paper, the RGB-D depth camera is used to obtain the original point cloud information, and the mature 2D target detection technology and advanced 3D deep learning are used to locate the target. In addition, the voxel grid structure is improved, and the proportion and size of the voxel grid are appropriately adjusted by adopting the method of image category adaptation and spatial depth clustering to obtain more accurate point cloud features and achieve fast and accurate 3D object detection.

AB - 3D object detection techniques rely on features obtained from point cloud data structures to identify and label the frame range of objects. Past techniques of converting point cloud data into voxel grids or image sets would make the data unnecessarily large, and it would be impractical to slice all space into a voxel grid of the same scale for objects of different types and depths. In this paper, the RGB-D depth camera is used to obtain the original point cloud information, and the mature 2D target detection technology and advanced 3D deep learning are used to locate the target. In addition, the voxel grid structure is improved, and the proportion and size of the voxel grid are appropriately adjusted by adopting the method of image category adaptation and spatial depth clustering to obtain more accurate point cloud features and achieve fast and accurate 3D object detection.

UR - https://www.scopus.com/pages/publications/85138727487

UR - https://www.scopus.com/pages/publications/85138727487#tab=citedBy

U2 - 10.1109/ICCE-Taiwan55306.2022.9869047

DO - 10.1109/ICCE-Taiwan55306.2022.9869047

M3 - Conference contribution

AN - SCOPUS:85138727487

T3 - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

SP - 423

EP - 424

BT - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Y2 - 6 July 2022 through 8 July 2022

ER -

Adaptive Voxelization Strategy for 3D Object Detection

Abstract

Publication series

Conference

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this