F-3DNet: Leveraging Inner Order of Point Clouds for 3D Object Detection

Chen, Y; Liu, R; Li, Z; Song, A

F-3DNet: Leveraging Inner Order of Point Clouds for 3D Object Detection

Chen, Y Liu, R Li, Z Song, A

Permalink

Publisher:: Springer Nature
Publication Type:: Chapter
Citation:: Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track, 2023, 14174 LNAI, pp. 346-359
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	978-3-031-43427-3_21.pdf	Published version	4.15 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chen, Y
dc.contributor.author	Liu, R
dc.contributor.author	Li, Z
dc.contributor.author	Song, A
dc.date.accessioned	2024-06-04T05:03:43Z
dc.date.available	2024-06-04T05:03:43Z
dc.date.issued	2023-01-01
dc.identifier.citation	Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track, 2023, 14174 LNAI, pp. 346-359
dc.identifier.isbn	9783031434266
dc.identifier.uri	http://hdl.handle.net/10453/179386
dc.description.abstract	Point clouds are often perceived as irregular and disorderly data in Internet of Things (IoT) applications. However, these point clouds possess implicit order and context information due to the laser arrangement and sequential scanning process, which are often overlooked. In this paper, we propose a novel method called Frustum 3DNet (F-3DNet) for 3D object detection from point clouds in IoT. Our approach utilizes the inner order of point clouds to construct a rearranged feature matrix and generate a pseudo panorama from LiDAR data. Based on the pseudo image, we extend 2D region proposals to 3D space and obtain frustum regions of interest. For each frustum, we generate a sequence of small frustums by slicing over distance, and introduce a novel local context feature extraction module to incorporate context information. The extracted context features are then concatenated with frustum features and fed to a fully convolutional network (FCN), followed by a classifier and a regressor. We further refine and fuse the output with RGB input to improve the outcome. Ablation studies verify the effectiveness of our proposed components. Experimental results on KITTI and nuScenes datasets demonstrate that F-3DNet outperforms existing methods in IoT.
dc.language	en
dc.publisher	Springer Nature
dc.relation.ispartof	Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track
dc.relation.ispartofseries	Lecture Notes in Computer Science
dc.relation.isbasedon	10.1007/978-3-031-43427-3_21
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	46 Information and computing sciences
dc.title	F-3DNet: Leveraging Inner Order of Point Clouds for 3D Object Detection
dc.type	Chapter
utslib.citation.volume	14174 LNAI
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2024-06-04T05:03:41Z
pubs.publication-status	Published
pubs.volume	14174 LNAI

Abstract:

Point clouds are often perceived as irregular and disorderly data in Internet of Things (IoT) applications. However, these point clouds possess implicit order and context information due to the laser arrangement and sequential scanning process, which are often overlooked. In this paper, we propose a novel method called Frustum 3DNet (F-3DNet) for 3D object detection from point clouds in IoT. Our approach utilizes the inner order of point clouds to construct a rearranged feature matrix and generate a pseudo panorama from LiDAR data. Based on the pseudo image, we extend 2D region proposals to 3D space and obtain frustum regions of interest. For each frustum, we generate a sequence of small frustums by slicing over distance, and introduce a novel local context feature extraction module to incorporate context information. The extracted context features are then concatenated with frustum features and fed to a fully convolutional network (FCN), followed by a classifier and a regressor. We further refine and fuse the output with RGB input to improve the outcome. Ablation studies verify the effectiveness of our proposed components. Experimental results on KITTI and nuScenes datasets demonstrate that F-3DNet outperforms existing methods in IoT.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/179386