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.

翻译：移动目标分割（Moving Object Segmentation, MOS）是计算机视觉中的一个挑战性问题，尤其在动态背景、突变光照、阴影、伪装以及移动相机等场景中。尽管基于图的方法已在MOS中展现出良好前景，但它们主要依赖直推式学习（transductive learning），这种学习方式假设在评估时能够访问全部训练与测试数据。然而，在实际应用中，系统需要在部署过程中处理新增数据，这一假设并不现实。本文提出了一种基于图神经网络（Graph Neural Network, GNN）架构的新型归纳式移动目标分割算法（Graph Inductive Moving Object Segmentation, GraphIMOS）。我们的方法构建了一个通用模型，能够利用已训练模型对新增数据帧进行预测。GraphIMOS的性能优于先前的归纳式学习方法，且比以往的直推式技术更具通用性。所提出的算法使得基于图的MOS模型能够在实际应用中进行部署。