OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wei, Jiale, Zheng, Junwei, Liu, Ruiping, Hu, Jie, Zhang, Jiaming, Stiefelhagen, Rainer
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912039395393536
author Wei, Jiale
Zheng, Junwei
Liu, Ruiping
Hu, Jie
Zhang, Jiaming
Stiefelhagen, Rainer
author_facet Wei, Jiale
Zheng, Junwei
Liu, Ruiping
Hu, Jie
Zhang, Jiaming
Stiefelhagen, Rainer
contents In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted increasing attention in the community since it provides more comprehensive information compared with pinhole front-view images and panoramas. Traditional BEV methods, which rely on multiple narrow-field cameras and complex pose estimations, often face calibration and synchronization issues. To break the wall of the aforementioned challenges, in this work, we introduce OneBEV, a novel BEV semantic mapping approach using merely a single panoramic image as input, simplifying the mapping process and reducing computational complexities. A distortion-aware module termed Mamba View Transformation (MVT) is specifically designed to handle the spatial distortions in panoramas, transforming front-view features into BEV features without leveraging traditional attention mechanisms. Apart from the efficient framework, we contribute two datasets, i.e., nuScenes-360 and DeepAccident-360, tailored for the OneBEV task. Experimental results showcase that OneBEV achieves state-of-the-art performance with 51.1% and 36.1% mIoU on nuScenes-360 and DeepAccident-360, respectively. This work advances BEV semantic mapping in autonomous driving, paving the way for more advanced and reliable autonomous systems.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13912
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping
Wei, Jiale
Zheng, Junwei
Liu, Ruiping
Hu, Jie
Zhang, Jiaming
Stiefelhagen, Rainer
Computer Vision and Pattern Recognition
In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted increasing attention in the community since it provides more comprehensive information compared with pinhole front-view images and panoramas. Traditional BEV methods, which rely on multiple narrow-field cameras and complex pose estimations, often face calibration and synchronization issues. To break the wall of the aforementioned challenges, in this work, we introduce OneBEV, a novel BEV semantic mapping approach using merely a single panoramic image as input, simplifying the mapping process and reducing computational complexities. A distortion-aware module termed Mamba View Transformation (MVT) is specifically designed to handle the spatial distortions in panoramas, transforming front-view features into BEV features without leveraging traditional attention mechanisms. Apart from the efficient framework, we contribute two datasets, i.e., nuScenes-360 and DeepAccident-360, tailored for the OneBEV task. Experimental results showcase that OneBEV achieves state-of-the-art performance with 51.1% and 36.1% mIoU on nuScenes-360 and DeepAccident-360, respectively. This work advances BEV semantic mapping in autonomous driving, paving the way for more advanced and reliable autonomous systems.
title OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.13912