Label-Efficient 3D Object Detection For Road-Side Units - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Label-Efficient 3D Object Detection For Road-Side Units

Label-Efficient 3D Object Detection For Road-Side Units

Résumé

Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU), thus minimizing the impact of occlusion. While significant advancement has been made, the data-hungry nature of these methods creates a major hurdle for their real-world deployment, particularly due to the need for annotated RSU data. Manually annotating the vast amount of RSU data required for training is prohibitively expensive, given the sheer number of intersections and the effort involved in annotating point clouds. We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery. Our paper introduces two new modules: one for object discovery based on a spatial temporal aggregation of point clouds, and another for refinement. Furthermore, we demonstrate that fine-tuning on a small portion of annotated data allows our object discovery models to narrow
Fichier principal
Vignette du fichier
2024___Minh____Semi_supervised_3D_object_detection_for_road_side_units.pdf (1.55 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY NC SA - Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales

Dates et versions

hal-04538861 , version 1 (09-04-2024)

Identifiants

  • HAL Id : hal-04538861 , version 1

Citer

Minh-Quan Dao, Holger Caesar, Julie Stephany Berrio, Mao Shan, Stewart Worrall, et al.. Label-Efficient 3D Object Detection For Road-Side Units. IV 2024 - IEEE Intelligent Vehicles Symposium, Jun 2024, Jeju Island (South Korea), South Korea. ⟨hal-04538861⟩
22 Consultations
6 Téléchargements

Partager

Gmail Facebook X LinkedIn More