Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (28): 166-168.DOI: 10.3778/j.issn.1002-8331.2008.28.055

• 图形、图像、模式识别 • Previous Articles     Next Articles

Optical-flow field based snake algorithm

NIE Xuan1,WU Cheng-fu2   

  1. 1.College of Software and Microelectronics,Northwestern Polytechnical University,Xi’an 710072,China
    2.National Laboratory of UAV Special Technology,Northwestern Polytechnical University,Xi’an 710065,China
  • Received:2008-05-05 Revised:2008-07-25 Online:2008-10-01 Published:2008-10-01
  • Contact: NIE Xuan

一种基于运动场的snake算法

聂 烜1,吴成富2   

  1. 1.西北工业大学 软件与微电子学院,西安 710072
    2.西北工业大学 无人机特种技术国家重点实验室,西安 710065
  • 通讯作者: 聂 烜

Abstract: On the basis of optical flow field computation,we redefine outer energy function in the general snake model and utilize motion vector of light-fluid field to predict the initial values of snake algorithm in subsequent frames.Hence,fast extraction of objective contour is achieved.

Key words: snake model, optical flow, motion vector

摘要: 在计算光流场的基础上,提出了snake算法中一种新的外部能量函数,并利用光流场的运动矢量来预测下帧图像中snake的初始值,不仅与无预测的算法相比能提高收敛的速度,而且收敛结果更贴近于目标的本身。实验证明了该文算法的优越性。

关键词: snake模型, 光流场, 运动矢量