Saved in:
Bibliographic Details
Main Authors: Chen, Jiwei, Sun, Yubao, Ding, Laiyan, Huang, Rui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.10298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908422868303872
author Chen, Jiwei
Sun, Yubao
Ding, Laiyan
Huang, Rui
author_facet Chen, Jiwei
Sun, Yubao
Ding, Laiyan
Huang, Rui
contents Vision-based Bird's-Eye-View (BEV) 3D object detection has recently become popular in autonomous driving. However, objects with a high similarity to the background from a camera perspective cannot be detected well by existing methods. In this paper, we propose a BEV-based 3D Object Detection Network with 2D Region-Oriented Attention (ROA-BEV), which enables the backbone to focus more on feature learning of the regions where objects exist. Moreover, our method further enhances the information feature learning ability of ROA through multi-scale structures. Each block of ROA utilizes a large kernel to ensure that the receptive field is large enough to catch information about large objects. Experiments on nuScenes show that ROA-BEV improves the performance based on BEVDepth. The source codes of this work will be available at https://github.com/DFLyan/ROA-BEV.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10298
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection
Chen, Jiwei
Sun, Yubao
Ding, Laiyan
Huang, Rui
Computer Vision and Pattern Recognition
Vision-based Bird's-Eye-View (BEV) 3D object detection has recently become popular in autonomous driving. However, objects with a high similarity to the background from a camera perspective cannot be detected well by existing methods. In this paper, we propose a BEV-based 3D Object Detection Network with 2D Region-Oriented Attention (ROA-BEV), which enables the backbone to focus more on feature learning of the regions where objects exist. Moreover, our method further enhances the information feature learning ability of ROA through multi-scale structures. Each block of ROA utilizes a large kernel to ensure that the receptive field is large enough to catch information about large objects. Experiments on nuScenes show that ROA-BEV improves the performance based on BEVDepth. The source codes of this work will be available at https://github.com/DFLyan/ROA-BEV.
title ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.10298