基于Snake模型的视频对象分割和跟踪算法  

Video object segmentation and tracking algorithm based on snake model

作　　者：王建中[1] 姜昱明[1] 

机构地区：[1]西安电子科技大学计算机学院,陕西西安710071

出　　处：《计算机工程与设计》2005年第7期1928-1930,共3页Computer Engineering and Design

摘　　要：视频对象的分割是基于内容的视频处理中重要的组成部分。提出并实现了一种半自动视频对象分割和跟踪算法。算法主要基于Williams活动轮廓模型,通过求取轮廓点的局部能量最小值对轮廓线进行更新。轮廓扩张技术用来追踪变形的轮廓边缘。通过对轮廓中心点运动的统计,预测对象的运动方向和大小。实验仿真结果表明,这种改进的Snake算法能够收缩到图像的凹陷部分,而且能较好地跟踪视频对象的运动。Video object segmentation is essential for content-based video processing. A framework for semiautomatic approach to this problem is presented. The contour model is based on williams＇ method by Greedy model for the minimal energy in the local position.Contour relaxation is used to deal with the object deformation flame by flame. The motion direction and magnitude are predicted by the center position of contour in the previous flames. The experiment shows this method has a large capture range and is able to move snakes into boundary concavities, and also this method can use video object tracking and segmentation.

关 键 词：SNAKE 活动轮廓模板 对象追踪 对象分割 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]