提出了一种利用序列图象从复杂背景中分割动目标图象的新算法。首先利用马尔科夫随机场（ＭＲＦ）模型和连续线过程建立较精确的目标函数，采用并行计算方法计算出速度场，然后以此为依据实现对目标图象的并行分割。实验结果表明：该算法不仅能适应多种复杂场景，而且分割精度高、速度快。 A new algorithm for segmenting moving target images from complex background using sequence images is proposed. First, the Markov random field (MRF) model and the continuous line process are used to establish a more accurate objective function. The parallel computing method is used to calculate the velocity field, and then the parallel segmentation of the target image is achieved. The experimental results show that this algorithm not only can adapt to a variety of complex scenes, but also has high segmentation accuracy and fast speed.