Inductive Graph Neural Networks for Moving Object Segmentation
This work addresses the need for real-world deployment of graph-based moving object segmentation systems by overcoming the limitations of transductive learning, though it appears incremental as it builds on existing graph-based methods with a focus on inductive capabilities.
The paper tackles the problem of moving object segmentation in dynamic and challenging scenarios by proposing GraphIMOS, a graph neural network-based algorithm that enables inductive learning for handling new data during deployment, outperforming previous inductive methods and offering greater generality than transductive techniques.
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. GraphIMOS 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.