[1]方纯洁,赖小波#,石 磊.基于Census变换的立体匹配算法优化及医学影像应用*[J].郑州大学学报(医学版),2017,(02):146-150.[doi:10.13705/j.issn.1671-6825.2017.02.010]
 FANG Chunjie,LAI Xiaobo,SHI Lei.Research on a fast implementation algorithm based on Census transform stereo matching and its applications in medical imaging[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2017,(02):146-150.[doi:10.13705/j.issn.1671-6825.2017.02.010]
点击复制

基于Census变换的立体匹配算法优化及医学影像应用*()
分享到:

《郑州大学学报(医学版)》[ISSN:1671-6825/CN:41-1340/R]

卷:
期数:
2017年02期
页码:
146-150
栏目:
应用研究
出版日期:
2017-03-15

文章信息/Info

Title:
Research on a fast implementation algorithm based on Census transform stereo matching and its applications in medical imaging
作者:
方纯洁赖小波#石 磊
浙江中医药大学医学技术学院 杭州 310053
Author(s):
FANG Chunjie LAI Xiaobo SHI Lei
College of Medical Technology, Zhejiang Chinese Medical University, Hangzhou 310053
关键词:
立体匹配 Census非参数变换 快速实现 医学影像应用
Keywords:
stereo matching Census transform fast implementation applications in medical imaging
分类号:
TP751.1
DOI:
10.13705/j.issn.1671-6825.2017.02.010
摘要:
目的:建立并优化一种基于Census非参数变换的立体匹配算法。方法:详细分析了基于Census非参数变换的立体匹配,运用移动窗口技术和高速缓存,采用SSE2指令进行数据流的并行处理从而优化算法结构,缩短取指时间,提高计算效率。用Middlebury标准图像对对该算法进行验证,并用于临床阴道镜子宫颈图像对的立体匹配。结果:快速实现了对Middlebury标准图像对以及子宫颈图像对的立体匹配。结论:该算法能够有效提高立体匹配的实时性,可应用于外科手术导航等计算机辅助外科诊疗系统。
Abstract:
Aim: To propose a fast implementation algorithm based on Census transform stereo matching.Methods: Firstly, the Census transform stereo matching was investigated, and its implementation process was analyzed in detail. Secondly, in order to simplify the calculation process and improve the computational efficiency, the moving window technique and cache were employed to optimize the algorithm structure and shorten the fetch time of the instructions. Finally, the SSE2 instructions were adopted to realize the parallel processing for the data stream, and the proposed algorithm was tested with different image pairs.Results: Fast implementation for the stereo matching with the Middlebury standard image pairs and cervical image pair was achieved.Conclusion: The proposed algorithm can effectively improve the real time of the stereo matching based on Census transform, and it can be applied to the computer-aided surgical diagnosis and treatment system such as surgical navigation.

参考文献/References:

[1] CHEN W,ZHANG MJ,XIONG ZH.Fast semi-global stereo matching via extracting disparity candidates from region boundaries[J].IET Computer Vision,2011,5(2):143
[2] PARK H,MITSUMINE H,FUJII M.Fast detection of robust features by reducing the number of box filtering in SURF[J].IEICE Trans Inf Syst,2011,E94D(3):725
[3] TIPPETTS BJ,LEE DJ,ARCHIBALD JK,et al.Dense disparity real-time stereo vision algorithm for resource-limited systems[J].IEEE Transacti Circuits Systems Video Technol,2011,21(10):1547
[4] CHIANG Hsiung,LIN Ting,HOU Lun.Development of a stereo vision measurement system for a 3D three-axial pneumatic parallel mechanism robot arm[J].Sensors(Basel),2011,11(2):2257
[5] OLIVER F, THIERRY V, ERIC T, et al. Real time correlation-based stereo: algorithm, implementations and applications[R].France:INRIA, 1993.
[6] WANG L,LIAO M,GONG M,et al.High-quality real-time stereo using adaptive cost aggregation and dynamic programming:Third International Symposium on 3D Data Processing,Visualization,and Transmission,Proceedings[C].Univ North Carolina,Chapel Hill,NC:IEEE,2006:798
[7] 刘赫伟,汪增福.一种沿区域边界的动态规划立体匹配算法[J].模式识别与人工智能,2010,23(1):38
[8] FELZENSZWALB PF,HUTTENLOCHER DP.Efficient belief propagation for early vision[J].Int J Comput Vis,2006,70(1):41
[9] SUN J,ZHENG NN,SHUM HY.Stereo matching using belief propagation[J].IEEE Trans Pattern Anal Mach Intell,2003,25(7):787
[10]ZABIH R,WOODFILL J. Non-parametric local transforms for computing visual correspondence[C].Stockholm,Swedwn:Proceedings of the Third European Conference on Computer Vision,1994: 151
[11]MÜHLMANN K,MAIER D,HESSER J,et al.Calculating dense disparity maps from color stereo images, an efficient implementation[J].Int J Comput Vis,2002,47(1/3):79
[12]IBARRA-MANZANO MA,ALMANZA-OJEDA DL,DEVY M,et al.Stereo vision algorithm implementation in FPGA using census transform for effective resource optimization:Proceedings of The 2009 12th Euromicro Conference on Digital System Design,Architectures,Methods and Tools[C].Patras,Greece:IEEE,2009:799
[13]SCHARSTEIN D,SZELISKI R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].Int J Comput Vis,2002,47(1/3):7
[14]SEBOT J,DRACH-TEMAM N. Memory bandwidth: the true bottleneck of SIMD multimedia performance on a superscalar processor[Z].LNCS,2001,2150:439

备注/Memo

备注/Memo:
*国家自然科学基金资助项目 61602419; 浙江省自然科学基金资助项目 LY16F010008,LQ16F020003; 浙江省教育厅科研项目Y201431354; 浙江中医药大学校级课题 2012ZY18
#通信作者,男,1981年6月生,博士,副教授,研究方向:医学图像处理,E-mail:shopo@zcmu.edu.cn
更新日期/Last Update: 2017-03-20