东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2012, Vol. 33 ›› Issue (3): 327-331.DOI: -

• 论著 • 上一篇    下一篇

蚁群优化在超声图像运动矢量估计中的应用

张耀楠;杨乐;康雁;   

  1. 东北大学中荷生物医学与信息工程学院;
  • 收稿日期:2013-06-19 修回日期:2013-06-19 发布日期:2013-04-04
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(61071213)

Application of ant colony optimization in estimating motion vectors of ultrasound images

Zhang, Yao-Nan (1); Yang, Le (1); Kang, Yan (1)   

  1. (1) School of Sino-Dutch Biomedical and Information Engineering, Northeastern University, Shenyang 110819, China
  • Received:2013-06-19 Revised:2013-06-19 Published:2013-04-04
  • Contact: Zhang, Y.-N.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

653

摘要： 为了在超声图像序列中找到稳健的运动矢量,提出将运动矢量估计的块匹配法表示为蚁群优化.序列方向上的运动矢量平滑约束和局部区域运动矢量相似性被表示为蚁群优化的残留信息浓度而不断更新,而相应两区域块的绝对差值和(SAD)被表示为蚁群优化的启发值来驱动蚁群.利用C++和ITK对提出的算法进行了实现,使用颈动脉超声图像序列进行了实验验证.结果较为理想,证明了新方法的可行性.

关键词: 运动估计, 蚁群优化, 超声, 块匹配法, SAD

Abstract: In order to find out the robust motion vectors in ultrasound image sequence, a block matching method of the motion estimation under ant colony optimization (ACO) paradigm was proposed. The motion vector smoothness along sequence and the local similarity of the motion vectors are represented as pheromone values, and the sum of absolute difference (SAD) was used as heuristic value to drive ants to targets. The proposed method was implemented by using C++ and ITK and verified by experiments on real ultrasound images of carotid artery. Experimental results are fairly good, which indicates the feasibility of the proposed method.

中图分类号: