Abstract: Gaussian mixture background model is an online parameterized statistical model, and the presenting way of pixel sample pattern observed from time window has great influence on the model's learning result. According to the characteristics of dynamic background changes, issues such as the stability and plasticity of modal learning, the modal residual and activation, which affected the model's adaptive ability, were studied. The simulation results show that Gaussian mixture background model has a robust selective adaptability to gradual change, but a limited adaptability to transient variation of background configuration provided by modal residual and activation mechanism.

Key words: Gaussian mixture background model, motion segmentation, adaptive ability, modal residual

摘要： 高斯混合背景模型是一种参数化统计模型，观察时间窗内像素样本模式呈现规律决定了背景模型的学习结果。针对背景动态变化的特点，研究了影响背景模型适应能力的模态稳定性与可塑性、模态残留与激活问题。仿真实验表明高斯混合背景模型具有较强的渐变选择性适应能力，而模态残留与激活机制为模型提供了有限的背景结构短时变化适应能力。

关键词: 高斯混合背景模型, 运动分割, 适应能力, 模态残留