期刊文献+

一种改进的自适应权重立体匹配算法与校正 被引量:4

Improved Adaptive Support-weight Algorithm and Adjustment
下载PDF
导出
摘要 立体匹配是立体视觉中一个重要的环节,针对自适应权重匹配算法中难以兼顾速度和精度的不足,提出了一种基于色彩的局部立体匹配算法。首先,利用区域连通性和颜色相似性改进权重因子,提出基于颜色变化约束的区域生长算法,有效提高了算法的精度和速度;然后基于颜色相似性提出一种视差校正算法,根据颜色相似性的结果对初始视差图进行视差校正,在没有增加额外工作量的前提下进一步提高算法的精度。实验结果表明,此算法能有效提高重复区域、边缘区域、低纹理区域的精度,而且速度较自适应权重算法提高了近20%,与当前主流算法具有可比性。 Stereo matching is one of the important parts in stereo vision. Regarding difficulties of adaptive support-weight algorithm to meet both accu- racy and speed, a novel local stereo matching method based on color is presented in this paper. Firstly, improving weight factor by using region connec- tivity and color similarity, a region growing algorithm based on color constraint is proposed to improve the accuracy and speed of the algorithm effectively. Secondly, a disparity adjustment based on color is presented to further improve algorithm accuracy without adding extra computation cost. Experimental results show this algorithm can effectively improve the accuracy in repeat and depth discontinuities and low-textured regions and get a better stereo matc- hing quality which is comparable with other main stream stereo methods, speeding up nearly twenty percent.
作者 吴方 王沛
出处 《电视技术》 北大核心 2012年第11期19-23,共5页 Video Engineering
基金 上海师范大学项目(SK201127)
关键词 区域连通 颜色相似 自适应权重 立体匹配 region connectivity color similarity adaptive support-weight stereo matching
  • 相关文献

参考文献10

  • 1CHAMBOLLE A,LIONS P L. Image recovery via total variation minimization and related problems[J].Numerische Mathematik,1997,(02):167-188.
  • 2KLAUS A,SORMANN M,KARNER K. Sngment-besed stereo matching using belief propagation and a self-adapting dissimilarity measure[A].IEEE Press,2006.l5-18.
  • 3SALMEN J,SCHLIPSING M,EDELBRUNNER J. Real-time stereo vision:making move out of dynamic programming[A].Beilin:Springer-Verlag,2009.1096-1103.
  • 4WANG L,LIAO M,GONG M. High quality real-time stereo using adaptive cost aggregation and dynamic programming[A].IEEE Press,2006.798-805.
  • 5SCHARSTE1N D,SZELISKI R. A taxonomy and evaluation of dense twoframe stereo correspondence algorithms[J].International Journal on Computer Visiou,2002,(I/2/3):7-42.
  • 6FELZENSZWALB P F,HUTTENLOCHER D P. Efficient belief propagationfor early vision[J].International Journal of Computer Vision,2006,(01):41-54.doi:10.1007/s11263-006-7899-4.
  • 7KANADE T,OKUTOMI M. A stereo matching algorithm with an adaptive window:theory and experiments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,(09):920-932.
  • 8FUSIELLO A,ROBERTO V,TRUCCO E. Efficient Stereo with Multiple Windowing[A].IEEE Press,1997.858-863.
  • 9YOON K J. Adaptive support-weight approach for conrrespondence search[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,(04):650-656.
  • 10陈辰,王沛,韦芳芳.图像多通道边缘信息辅助的快速立体匹配算法[J].电视技术,2011,35(23):17-21. 被引量:2

二级参考文献10

  • 1SCHAMBLOOE A ,LIONS P L. Image recovery via total variation minimi- zation and related problems [ EB/OL ]. [ 2011-02-04]. http ://citese- erx. ist. psu. edu/viewdoc/download? doi = 10. 1. 1. 125. 4407&rep = repl&type = pdf.
  • 2HARTLEY R,ZISSERMAN A. Multiple view geometry in computer vi- sion [ M ]. Cambridge, U K : Cambridge University Press,2000.
  • 3BROWN M Z,BURSCHKA D,HAGER G D. Advances in computational stereo [ J ]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2003,25 ( 8 ) :993-1008.
  • 4LIU Zhi ,LU Yu ,ZHANG Zhaoyang. Real time spatiotemporal segmentation of video objects in the H. 264 compressed domain [ J ]. Visual Communica- tion and Image Representation ,2007(3 ) :275-290.
  • 5HIRSCHMULLER H, SCHARSTEIN D. Evaluation of cost functions for stereo matching[ EB/OL]. [ 2011-02-04 ]. http://citeseerx, ist. psu. edu/viewdoc/download? doi = 10.1.1.71. 5766&rep = repl&type = pdf.
  • 6MCDONNEL M J. Box-filtering techniques [ J ]. Computer Graphics and Image Processing,1981,17( 1 ) :65-70.
  • 7DONATE A,LIU Xiuwen,COLLINS E G. Efiqcient path-based stereo matc- hing with subpixel accuracy[ J ]. IEEE Trans. Systems ,Man,and Cybernet- ics,Part B :Cybernetics ,2011,41 ( 1 ) :183-195.
  • 8Middlebury stereo website [ EB/OL3. [ 2011-02-04 ]. http://vision middlebury edu/stereo.
  • 9SUN Changming. Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques[EB/OL]. [2011--02-04]. http://www. springerlink, com/content/3 v2cgmn89v00w821/.
  • 10高韬,刘正光.基于冗余小波变换的立体图像视差估计[J].电视技术,2008,32(4):23-25. 被引量:2

共引文献1

同被引文献27

  • 1GUPTA R K,CHO S Y. Window-based approach for fast stereo cor- respondence [ J ]. lET Computer Vision, 2013,7 ( 2 ) : 123-134.
  • 2SU X, KHOSHGOFIAAR T M. Arbitrarily-shaped window based stereo matching using the go-light optimization algorithm [ C ]// Proc. IEEE Intemational Conference on Image Processing, 2007 ( ICIP 2007). [ S. 1. ] : IEEE Press,2007:556-559.
  • 3DE-MAEZTU L, VILLANUEVA A, CABEZA R. Stereo matching using gradient similarity and locally adaptive support- weight [ J ]. Pattern Recognition Letters ,2011,32( 13 ) : 1643-1651.
  • 4GU Z,SU X,LIU Y,et al. Local stereo matching with adaptive sup- port-weight, rank transform and disparity calibration [ J]. Pattern Recognition Letters,2008,29 ( 9 ) : 1230-1235.
  • 5MEI X,SUN X,ZHOU M, et al. On building an accurate stereo matc- hing system on graphics hardware [ C]//Prec. IEEE International Conference on Computer Vision Workshops,2011 (ICCV Workshops 2011). [S. 1. ] :IEEE Press,2011 : 467---474.
  • 6DUTI'A A, KAR A, CHA'I'I'ERJI B N. A novel apprnach to comer matching using fuzzy similarity measure[ C ]//Prec. 7th International Conference on Advances in Pattern Recognition ,2009 (ICAPR'09). [S. 1. ] :IEEE Press,2009:57--60.
  • 7GALAR M, FERNANDEZ J, BELIAKOV G, et al. Interval-valued fuzzy sets applied to stereo matching of color images [ J ]. IEEE Trans. Image Processing,2011,20 ( 7 ) : 1949-1961.
  • 8SAFF E B, SNIDER A D. Fundamentals of complex analysis with applications to engineering, science, and mathematics [ M ]. NJ: Prentice Hall,2003.
  • 9SCHARSTEIN D, SZELISK1 R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [ J ]. International Jour- nal of Computer Vision ,2002,47( 1 ) :7--42.
  • 10AMBROSCH K, KUBINGER W. Accurate hardware-based stereo vision [ J ]. Computer Vision and Image Understanding, 2010 ( 11 ) : 1303-1316.

引证文献4

二级引证文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部