采用映射参数模型实现图象运动分割

The Implementation of Image Motion Segmentation with Mapping Parametric Models

介绍了采用映射参数模型进行分层结构型分割的方法，并采用Matlab语言对该算法的部分内容进行了验证。该方法利用时空图象亮度梯度和运动信息来估算三维运动和结构参数。分割区域用运动和位置参数定义，这些参数被称为映射参数。通过变化检测，映射参数估算，运动区域和背景检测来实现运动分割。

The hierarchically structured motion segmentation methods based on mapping parametric models are introduced. Experimental results on part of the algorithm with MATLAB language are shown. The methods utilize the spatio-temporal image intensity gradients and motion information to estimate the 3-D motion and structure parameters. An area to be segmented is defined by a set of uniform motion and position parameters denoted as mapping parameters. Change detection, mapping parameter estimation, moving objects and background detection are used to implement image motion segmentation.