3D-FlowNet: Event-based optical flow estimation with 3D representation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

3D-FlowNet: Event-based optical flow estimation with 3D representation

Résumé

Event-based cameras can overpass frame-based cameras limitations for important tasks such as high-speed motion detection during self-driving cars navigation in low illumination conditions. The event cameras' high temporal resolution and high dynamic range, allow them to work in fast motion and extreme light scenarios. However, conventional computer vision methods, such as Deep Neural Networks, are not well adapted to work with event data as they are asynchronous and discrete. Moreover, the traditional 2D-encoding representation methods for event data, sacrifice the time resolution. In this paper, we first improve the 2D-encoding representation by expanding it into three dimensions to better preserve the temporal distribution of the events. We then propose 3D-FlowNet, a novel network architecture that can process the 3D input representation and output optical flow estimations according to the new encoding methods. A self-supervised training strategy is adopted to compensate the lack of labeled datasets for the event-based camera. Finally, the proposed network is trained and evaluated with the Multi-Vehicle Stereo Event Camera (MVSEC) dataset. The results show that our 3D-FlowNet outperforms state-of-the-art approaches with less training epoch (30 compared to 100 of Spike-FlowNet). The code is released in https://github.com/adosum/3D-FlowNet.
Fichier principal
Vignette du fichier
IV22_0145_MS.pdf (2.79 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03771319 , version 1 (07-09-2022)

Identifiants

Citer

Haixin Sun, Minh-Quan Dao, Vincent Frémont. 3D-FlowNet: Event-based optical flow estimation with 3D representation. 2022 IEEE Intelligent Vehicles Symposium (IV), Jun 2022, Aachen, Germany. pp.1845-1850, ⟨10.1109/IV51971.2022.9827380⟩. ⟨hal-03771319⟩
66 Consultations
17 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More