BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autononomous Driving - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autononomous Driving

Résumé

Current research in semantic bird's-eye view segmentation for autonomous driving focuses solely on optimizing neural network models using a single dataset, typically nuScenes. This practice leads to the development of highly specialized models that may fail when faced with different environments or sensor setups, a problem known as domain shift. In this paper, we conduct a comprehensive cross-dataset evaluation of state-of-the-art BEV segmentation models to assess their performance across different training and testing datasets and setups, as well as different semantic categories. We investigate the influence of different sensors, such as cameras and LiDAR, on the models' ability to generalize to diverse conditions and scenarios. Additionally, we conduct multi-dataset training experiments that improve models' BEV segmentation performance compared to single-dataset training. Our work addresses the gap in evaluating BEV segmentation models under cross-dataset validation. And our findings underscore the importance of enhancing model generalizability and adaptability to ensure more robust and reliable BEV segmentation approaches for autonomous driving applications.
Fichier principal
Vignette du fichier
root.pdf (4.78 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04677808 , version 1 (28-08-2024)
hal-04677808 , version 2 (30-08-2024)

Licence

Identifiants

Citer

Manuel Alejandro Diaz-Zapata, Wenqian Liu, Robin Baruffa, Christian Laugier. BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autononomous Driving. 18th International Conference on Control, Automation, Robotics and Vision., Dec 2024, Dubai, United Arab Emirates. ⟨hal-04677808v1⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More