期刊文献+

基于迭代传播的小基高比立体匹配方法 被引量:5

Iterative diffusion based stereo matching method for small baseline
下载PDF
导出
摘要 提出一种基于迭代传播的方法求解小基高比立体匹配中的相关基本等式以解决立体匹配中存在的黏合现象。该方法首先根据启发式信息估计实际立体匹配系统中整数级视差的误差水平;其次,根据Morozov原理设计一个迭代正则参数选择方法对相关基本等式进行正则化处理并建立目标泛函;再次,利用延迟扩散定点迭代方法获得目标泛函的迭代传播等式;最后,通过共轭梯度法对该等式进行迭代求解。实验结果表明:该方法减少了小基高比立体匹配中的黏合现象,其视差图的准确率可达95%以上,且像元匹配差异精度优于1/10个像元。 A method based on iterative diffusion was proposed to solve the central equation of correlation in small baseline stereovision for Adhesion phenomenon.This method firstly estimated the error level of integer disparity in the practical stereo matching system with heuristic information;secondly,an iterative method for the choice of regulation parameter was designed according to Morazov principle to be regulation of the objective function;thirdly,the iterative diffusion equation was obtained by lagged diffusivity fixed point iteration;finally,the equation was solved iteratively by conjugate gradient method.The experimental results show that this method reduces the "adhesion phenomenon" in the small baseline stereovision and the accuracy of its resulting disparity map is more than 95% and it has sub-pixel accuracy better than 1/10.
出处 《中南大学学报(自然科学版)》 EI CAS CSCD 北大核心 2012年第4期1362-1370,共9页 Journal of Central South University:Science and Technology
基金 国家自然科学基金资助项目(60873138) 中央高校基本科研业务费专项资金资助项目(HEUCF100607)
关键词 立体匹配 小基高比 迭代传播 共轭梯度法 黏合现象 stereo matching small baseline iterative diffusion conjugate gradient method adhesion phenomenon
  • 相关文献

参考文献16

  • 1罗三定,陈海波.基于区域增长的自适应窗口立体匹配算法[J].中南大学学报(自然科学版),2005,36(6):1042-1047. 被引量:10
  • 2Delon J.Fine comparison of images and other problems[D].Paris:ENS Cachan.Mathematics Department,2004:89-108.
  • 3Facciolo G.Variational adhesion correction with image based regularization for digital elevation models[D].Montevicleo:University of the Republic.Engineering College,2005:37-49.
  • 4Delon J,Rouge B.Small baseline stereovision[J].Journal of Mathematical Imaging and Vision,2007,28(3):209-223.
  • 5Igual L,Preciozzi J,Garrido L,et al.Automatic low baseline stereo in urban areas[J].Inverse Problems and Imaging,2007,1(2):319-348.
  • 6Morgan G L K,LIU Jian-guo,YAN Hong-shi.Sub-pixel stereo matching for DEM generation from narrow baseline stereo imagery[C]//Proceedings of International Geoscience and Remote Sensing Symposium.Boston:IEEE,2008:1284-1287.
  • 7Sabater N,Blanchet G,Moisan L,et al.Review of low-baseline stereo algorithms and benchmarks[C]//Proceedings of Image and Signal Processing for Remote Sensing XVI.Toulouse:IEEE,2010:1-12.
  • 8Morgan G L K,LIU Jian-guo,YAN Hong-shi.Precise subpixel disparity measurement from very narrow baseline stereo[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(9):3424-3433.
  • 9Aujol J F.Some first-order algorithms for total variation based image restoration[J].Mathematical Imaging and Vision,2009,34(3):307-327.
  • 10Beck A,Teboulle M.Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems[J].IEEE Transactions on Image Processing,2009,18(11):2419-2434.

二级参考文献13

  • 1Anandan P.A computational framework and an algorithm for the measurement of visual motion[J].International Journal of Computer Vision,1989,2(3):283-310.
  • 2Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and experiment[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1994,16(9):920-932.
  • 3Fusiello A,Roberto V.Efficient stereo with multiple windowing[A].IEEE Conference on Computer Vision and Pattern Recognition[C].San Juan,1997:858-863.
  • 4Shimizu M,Okutomi M.Precise sub-pixel estimation on area-based matching[A].8th International Conference on Computer Vision[C].Vancouver,2001:90-97.
  • 5Veksler O.Fast variable window for stereo correspondence using integral images[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Madison,2003:556-561.
  • 6Intille S,Bobick A.Disparity-space images and large occlusion stereo[A].European Conference on ComputerVision[C].Stockholm,1994:179-186.
  • 7Belhumeur P N.A bayesian-approach to binocular stereopsis[J].Computer Vision,1996,19(3):237-260.
  • 8Intille S,Bobick A.Incorporating intensity edges in the recovery of occlusion regions[A].International Conference on Pattern Recognition[C].Jerusalem,1994:674-677.
  • 9Fua P.A parallel stereo algorithm that produces dense depth maps and preserves image features[J].Machine Vision and Applications,1993,69(1):35-49.
  • 10SUN Chang-ming.Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques[J].International Journal of Computer Vision,2002,47(3):99-117.

共引文献9

同被引文献34

  • 1罗三定,陈海波.基于区域增长的自适应窗口立体匹配算法[J].中南大学学报(自然科学版),2005,36(6):1042-1047. 被引量:10
  • 2Dutta A, Kar A, Chatterji B N. A new approach to comer matching from image sequence using fuzzy similarity index[J]. Pattern Recognition Letters, 2011, 32(5): 712-720.
  • 3Green A. Development and status of image matching in photogrammetry[J]. Photogrammetric Record, 2012, 26(137): 36-57.
  • 4Li H, Ma Y, Liang K. Rapid matching algorithm for hyperspeetral image based norm sifting[J]. Chinese Optics Letters, 2012, 10(1): 72-80.
  • 5Bastanlar Y, Temizel A, Yardimci Y. Improved SIFT matching for image pairs with scale difference[J]. Electronics Letters, 2010, 46(5): 346-354.
  • 6Chiou Y C, Liang Y T. An effective comer detection method using subpixel edge detector and gaussian filter[J]. Sensor Review, 2010, 30(1): 93-101.
  • 7Forstner W, Gtilch E. A fast operator for detection and precise location of distinct points, corners and centers of circular features[C]//ISPRS Conference on Fast Processing of Photogrammetric Data. Interlaken, Switzerland, 1987: 281-305.
  • 8Harris C, Stephens M J. A combined comer and edge detector[C]//Proceedings of the 4th Alvey Vision Conference. Manchester, Britain, 1998: 147-151.
  • 9Sadek R, Constantinopoulos C, Meinhardt E, et al. On affine invariant descriptors related to SIFT[J]. Slam Journal on Imaging Sciences, 2012, 5(2): 652-687.
  • 10Matas J, Chum O, Urban M, et al. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image Vision Computing, 2004, 22(10): 761-767.

引证文献5

二级引证文献16

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