基于马尔可夫随机场模型的运动对象分割算法

Moving object segmentation algorithm based on Markov random field model

提出了一种基于马尔可夫随机场(MRF)模型的运动分割算法,仅使用了压缩流中的运动矢量和块编码模式信息,可以在复杂场景下对运动对象有很好的分割效果。利用运动矢量量化的方法来对运动矢量进行预处理,对运动矢量进行马尔可夫建模,利用能量最小函数进行优化得到运动对象分割的效果。实验表明:与现有的方法相比,该方法可从复杂场景中更准确地对运动对象进行分割。

Propose a motion segmentation algorithm based on Markov random model,it can has good segmentation effect in complex scenarios on moving objects only using motion vectors and block coding mode information in compressed stream. Preprocessing motion vector using motion vector quantization method,and Markov modeling is carried out on motion vector,the minimum energy function is used for optimization to obtain effect of moving object segmentation. Experiment shows that this method can segment moving object more accurately from complex scene compared with existing methods.