Point-voxel feature set abstraction with hybrid cross feature fusion module for 3D object detection

Guangtao Chen; Zhenglin Li; Shilin Shao; Tianxin Yuan; Yang Zhou

doi:10.1117/12.3021443

19 February 2024 Point-voxel feature set abstraction with hybrid cross feature fusion module for 3D object detection

Guangtao Chen, Zhenglin Li, Shilin Shao, Tianxin Yuan, Yang Zhou

Proceedings Volume 13063, Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023); 130631R (2024) https://doi.org/10.1117/12.3021443
Event: Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023), 2023, Changchun, China

Abstract

This paper focuses on high-precision 3D object detector. In two-stage 3D object detection algorithms based on point-voxel method, the concatenation of multiple types and scales of features is often limited to simple concatenation, which fails to capture rich semantic information. To better utilize multi-scale voxel features, raw point feature and BEV feature, we introduce a method called hybrid cross feature fusion module (HCFF). This method leverages a gating module to fuse raw point feature, multi-scale voxel features, and BEV feature, resulting in more comprehensive semantic feature information, which improves the accuracy of object detection in all classes in KITTI. It is especially good at smaller classes. In the end, we enhance the original PV-RCNN and propose a higher-precision point-voxel based 3Dobject detection algorithm. The results demonstrate that our HCFF-Det3D network outperforms PV-RCNN in terms of accuracy.

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

Citation Download Citation

Guangtao Chen, Zhenglin Li, Shilin Shao, Tianxin Yuan, and Yang Zhou "Point-voxel feature set abstraction with hybrid cross feature fusion module for 3D object detection", Proc. SPIE 13063, Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023), 130631R (19 February 2024); https://doi.org/10.1117/12.3021443

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