计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (28): 206-209.

• 工程与应用 • 上一篇    下一篇

基于PC的实时超声全景成像系统中的图像配准

邵 斌1,2,唐 娉2,曾庆业2,张送根3,姚克纯4   

  1. 1.中国科学院 研究生院,北京 100049
    2.中国科学院 遥感应用研究所,北京 100101
    3.北京天惠华数字技术有限公司,北京 100085
    4.中国人民解放军空军总医院,北京 100036
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-01 发布日期:2007-10-01
  • 通讯作者: 邵 斌

Image registration algorithm in PC-based real-time US-EFOV system

SHAO Bin1,2,TANG Ping2,ZENG Qing-ye2,ZHANG Song-gen3,YAO Ke-chun4   

  1. 1.Graduate University of the Chinese Academy of Sciences,Beijing 100049,China
    2.Institute of Remote Sensing Applications,Chinese Academy of Sciences,Beijing 100101,China
    3.Teknova Medical Systems Ltd.,Beijing 100085,China
    4.The General Hospital of the Air Force P L A.,Beijing 100036,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-01 Published:2007-10-01
  • Contact: SHAO Bin

摘要: 图像配准技术是超声宽视野成像技术的核心。结合现有的超声宽视野图像配准算法和PC平台的特点,通过匹配模板筛选、局部运动矢量评价、加权最小二乘等步骤,进一步改进和优化了配准的过程,提高了超声图像配准的鲁棒性和实时性。

关键词: 宽视野成像, 图像配准, 局部运动矢量评价, 加权最小二乘

Abstract: The technology of image registration is the core of UltraSound Extended-Field-of-View(US-EFOV) imaging technology.The characteristics of existing US-EFOV imaging algorithm and PC platform are combined in this paper.By the processes of template selection,local motion vector estimation,and weighted least-squares,the process of image registration is improved and optimized,and both the robustness and real-time of ultrasound image registration are enhanced.

Key words: Extended-Field-Of-View(EFOV), image registration, local motion vector estimation, weighted least-squares