基于变化检测和改进的GVF snake模型的运动目标轮廓提取
DOI:
CSTR:
作者:
作者单位:

作者简介:

祝世平(1970-),男,博士,副教授,主要从 事图像和视频处理,计算机视觉,机器视觉在精密测量中的应用等的研究.

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(61075011,60675018)和教育部留学回国人员科研启动基金资助项目 , 高洁 (北京航空航天大学 仪器科学与光电工程学院测控与信息技术系,北京 100191)


Moving object contour extraction based on change detection and improved GVF snake model
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了解决当前目标跟踪中目标轮廓提取不精确的问 题,在对传统GVF (gradient vector flow)snake活动轮廓模型改进的基础上,提 出一种基于变化检测和改进的GVF snake活动轮廓模型的视频目标轮廓提取算法。首先,通 过 基于t显著性检验的变化检测方 法消除背景边界的影响,并获取初始运动变化区域的临界四边形作为GVF snake的初始轮廓 。然后,对初始轮廓应用改进 的GVF snake模型以获得精确的轮廓边界。改进模型采用4方向各项异性扩散,并采用下降速 度较快的保真项系数以增强 GVF snake进入凹陷的能力,且保持对弱边界的收敛。本文方法克服了手动绘制初始轮廓的 缺点,对传统GVF snake方法进 行了改进,且空间准确度(SA)有很大提高。实验表明 ,本文方法成功分割出目标凹陷部分并对弱边界有较好的收敛效果,提高了轮廓提取的精确 度。

    Abstract:

    To deal with the problem of inaccuracy in current object contour extraction algorithms,a new approach based on improv ed gradient vector flow (GVF) snake and t-distribution significance test based cha nge detection is proposed.It firstly eliminates most background boundaries through t-distribution significance test based change det ection,an enclosed rectangle is obtained,and the rectangle is set to be the original boundary of the GVF snake model,which is obt ained by calculating four critical points of the change detection mask.Then the improved GVF snake model is applied to the rough boundar y to get the precise boundary.The improved GVF snake adopts anisotropic diffusion and a four-direction edge operator to so lve the blurry boundary and edge shifting caused by the traditional GVF snake,and makes use of a new coefficient of fidelity term wh ich has a faster descent speed to strengthen snake to segment the concave part.The proposed algorithm overcomes the disadvantages of drawing the initial contour manually.Furthermore,the GVF snake method in the spatial domain has been improved with higher accuracy.E xperimental results indicate that the new proposed method gains accurate segmentation results in both the concave region a nd the weak edge part.Experimental results with several test video sequences indicate the validity and extraction accuracy.

    参考文献
    相似文献
    引证文献
引用本文

祝世平,高洁.基于变化检测和改进的GVF snake模型的运动目标轮廓提取[J].光电子激光,2013,(9):1803~1810

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2013-01-25
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期:
  • 出版日期:
文章二维码