Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection

doi:10.1109/TPAMI.2024.3377812

	Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection
	Wenxi Liu 1; Qi Li 1; Weixiang Yang 1; Jiaxin Cai 1; Yuanlong Yu 1; Yuexin Ma2 ; Shengfeng He 3; Jia Pan 4
	2024
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (IF:20.8[JCR-2023],22.2[5-Year])
ISSN	1939-3539
EISSN	1939-3539
卷号	PP 期号:99 页码:1-17
发表状态	已发表
DOI	10.1109/TPAMI.2024.3377812
摘要	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
关键词	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
收录类别	EI ; SCI
语种	英语
资助项目	National Natural Science Foundation of China["62072110","U21A20471","U21A20472"]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001290498900007
出版者	IEEE Computer Society
EI入藏号	20241315813803
EI主题词	Three dimensional displays
EI分类号	406.2 Roads and Streets ; 432 Highway Transportation ; 722.2 Computer Peripheral Equipment ; 731.6 Robot Applications
原始文献类型	Article in Press
来源库	IEEE
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354975
专题	信息科学与技术学院_PI研究组_马月昕
作者单位	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
推荐引用方式 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.