ShanghaiTech University Knowledge Management System
Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection | |
2024 | |
Source Publication | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
![]() |
ISSN | 1939-3539 |
EISSN | 1939-3539 |
Volume | PPIssue:99Pages:1-17 |
Status | 已发表 |
DOI | 10.1109/TPAMI.2024.3377812 |
Abstract | HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to expensive sensors and time-consuming computation. Camera-based methods usually need to perform road segmentation and view transformation separately, which often causes distortion and missing content. To push the limits of the technology, we present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view given a front-view monocular image only. We propose a front-to-top view projection (FTVP) module, which takes the constraint of cycle consistency between views into account and makes full use of their correlation to strengthen the view transformation and scene understanding. In addition, we apply multi-scale FTVP modules to propagate the rich spatial information of low-level features to mitigate spatial deviation of the predicted object location. Experiments on public benchmarks show that our method achieves various tasks on road layout estimation, vehicle occupancy estimation, and multi-class semantic estimation, at a performance level comparable to the state-of-the-arts, while maintaining superior efficiency. IEEE |
Keyword | Autonomous driving BEV perception segmentation Autonomous vehicles Benchmarking Feature extraction Job analysis Roads and streets Semantics Features extraction Layout Road Segmentation Task analysis Three-dimensional display Top views Transformer |
URL | 查看原文 |
Indexed By | EI ; SCI |
Language | 英语 |
Funding Project | National Natural Science Foundation of China["62072110","U21A20471","U21A20472"] |
WOS Research Area | Computer Science ; Engineering |
WOS Subject | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS ID | WOS:001290498900007 |
Publisher | IEEE Computer Society |
EI Accession Number | 20241315813803 |
EI Keywords | Three dimensional displays |
EI Classification Number | 406.2 Roads and Streets ; 432 Highway Transportation ; 722.2 Computer Peripheral Equipment ; 731.6 Robot Applications |
Original Document Type | Article in Press |
Source Data | IEEE |
Document Type | 期刊论文 |
Identifier | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354975 |
Collection | 信息科学与技术学院_PI研究组_马月昕 |
Affiliation | 1.College of Computer and Data Science, Fuzhou University, China 2.ShanghaiTech University, China 3.Singapore Management University, Singapore 4.University of Hong Kong, HKSAR, Hong Kong |
Recommended Citation GB/T 7714 | Wenxi Liu,Qi Li,Weixiang Yang,et al. Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,PP(99):1-17. |
APA | Wenxi Liu.,Qi Li.,Weixiang Yang.,Jiaxin Cai.,Yuanlong Yu.,...&Jia Pan.(2024).Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,PP(99),1-17. |
MLA | Wenxi Liu,et al."Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE PP.99(2024):1-17. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License |
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.