File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2024.3377812
- Scopus: eid_2-s2.0-85188533229
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection
Title | Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection |
---|---|
Authors | |
Keywords | Autonomous driving BEV perception Estimation Feature extraction Layout Roads segmentation Task analysis Three-dimensional displays Transformers |
Issue Date | 1-Sep-2024 |
Publisher | Institute of Electrical and Electronics Engineers |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, v. 46, n. 9, p. 6109-6125 How to Cite? |
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. |
Persistent Identifier | http://hdl.handle.net/10722/351846 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Wenxi | - |
dc.contributor.author | Li, Qi | - |
dc.contributor.author | Yang, Weixiang | - |
dc.contributor.author | Cai, Jiaxin | - |
dc.contributor.author | Yu, Yuanlong | - |
dc.contributor.author | Ma, Yuexin | - |
dc.contributor.author | He, Shengfeng | - |
dc.contributor.author | Pan, Jia | - |
dc.date.accessioned | 2024-12-03T00:35:16Z | - |
dc.date.available | 2024-12-03T00:35:16Z | - |
dc.date.issued | 2024-09-01 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, v. 46, n. 9, p. 6109-6125 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/351846 | - |
dc.description.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. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | Autonomous driving | - |
dc.subject | BEV perception | - |
dc.subject | Estimation | - |
dc.subject | Feature extraction | - |
dc.subject | Layout | - |
dc.subject | Roads | - |
dc.subject | segmentation | - |
dc.subject | Task analysis | - |
dc.subject | Three-dimensional displays | - |
dc.subject | Transformers | - |
dc.title | Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TPAMI.2024.3377812 | - |
dc.identifier.scopus | eid_2-s2.0-85188533229 | - |
dc.identifier.volume | 46 | - |
dc.identifier.issue | 9 | - |
dc.identifier.spage | 6109 | - |
dc.identifier.epage | 6125 | - |
dc.identifier.eissn | 1939-3539 | - |
dc.identifier.issnl | 0162-8828 | - |