Self-supervised masked occupancy encoder for 3D object detection

Dianang Li

doi:10.1117/12.3039058

13 September 2024 Self-supervised masked occupancy encoder for 3D object detection

Dianang Li

Proceedings Volume 13254, Fourth International Conference on Optics and Image Processing (ICOIP 2024); 132540B (2024) https://doi.org/10.1117/12.3039058
Event: Fourth International Conference on Optics and Image Processing (ICOIP 2024), 2024, Chongqing, China

Abstract

Because of the sparse distribution and lack of organization in point clouds, 3D object detection has been a challenging task. Current detection models heavily rely on 3D labeled data, while in real-world complex scenarios, issues such as point cloud sparsity and occlusions make feature extraction difficult. In this study, we propose a pre-training approach based on self-supervised masking. We compute the distance between voxels and the LiDAR device to regulate the masking ratio of voxels, randomly masking voxels accordingly. Predicting the occupancy status of voxels enables the prediction of the masked occupancy structure for the entire 3D scene. This masking strategy enables self-supervised model training, achieving the effect of data augmentation. We conducted thorough experiments using the KITTI datasets, specifically targeting the 3D object detection task. We achieved a significant +2.11% improvement in the Hard category of Car detection. mAP across three difficulty levels also increased by +0.74%, illustrating the efficiency of our method in handling complex circumstances.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dianang Li "Self-supervised masked occupancy encoder for 3D object detection", Proc. SPIE 13254, Fourth International Conference on Optics and Image Processing (ICOIP 2024), 132540B (13 September 2024); https://doi.org/10.1117/12.3039058

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

3D mask effects

Voxels

Object detection

Point clouds

3D modeling

LIDAR

RGB color model

Show All Keywords

Keywords/Phrases

Search In:

Publication Years