Inductive Graph Neural Networks for Moving Object Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Inductive Graph Neural Networks for Moving Object Segmentation

Résumé

Moving Object Segmentation (MOS) is a challenging problem in computer vision, particularly in scenarios with dynamic backgrounds, abrupt lighting changes, shadows, camouflage, and moving cameras. While graph-based methods have shown promising results in MOS, they have mainly relied on transductive learning which assumes access to the entire training and testing data for evaluation. However, this assumption is not realistic in real-world applications where the system needs to handle new data during deployment. In this paper, we propose a novel Graph Inductive Moving Object Segmentation (GraphIMOS) algorithm based on a Graph Neural Network (GNN) architecture. Our approach builds a generic model capable of performing prediction on newly added data frames using the already trained model. GraphI-MOS outperforms previous inductive learning methods and is more generic than previous transductive techniques. Our proposed algorithm enables the deployment of graph-based MOS models in real-world applications.

Dates et versions

hal-04500437 , version 1 (12-03-2024)

Identifiants

Citer

Wieke Prummel, Jhony Giraldo, Anastasia Zakharova, Thierry Bouwmans. Inductive Graph Neural Networks for Moving Object Segmentation. 2023 IEEE International Conference on Image Processing (ICIP), IEEE, Oct 2023, Kuala Lumpur, France. pp.2730-2734, ⟨10.1109/ICIP49359.2023.10222668⟩. ⟨hal-04500437⟩

Collections

UNIV-ROCHELLE
3 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More