全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种基于多层次MRF的多源图象融合算法

DOI: 10.11834/jig.20030263

Keywords: 计算机图象处理(520?6040),多源图象融合,多层次模型,序贯最大后验概率,图象分割

Full-Text   Cite this paper   Add to My Lib

Abstract:

图象融合技术的主要目的是将多种图象传感器数据中的互补信息组合起来,使形成的新图象更适合于计算机处理(如分割、特征提取和目标识别)等.在多层次MRF模型的基础上,提出了一种应用于多源图象分类的图象融合算法.该融合算法将定义在多层次图结构上的非线性因果Markov模型与贝叶斯SMAP(sequentialmaxi-mumaposteriori)最优化准则结合起来,克服了MAP(maximumaposteriori)准则在多层次图结构上计算不合理的缺陷.该算法可应用于多源遥感图象中的信息融合,使像素分类更精确,并解决多源海量数据的富集表示.另外还利用合成图象与自然图象分别针对多层次MRF模型的改进及算法中可最优化准则的不同进行了对比实验,结果表明,该算法具有许多优越性

References

[1]  [2]Solberg A, Taxt T, Jain A. A markov random fields model for classification of multisource satellite imagery[J]. IEEE Trans.Geoscience and Remote Sensing,1996,34(1):100~112.
[2]  [4]Laferté J M, Pérez P, Heitz F. Discrete markov modeling and inference on the quad-tree [J]. IEEE Transactions on Image Processing, 2000, 9(3) :390~404.
[3]  [5]Laferte J M, Heitz F, Perez P et al. Hierarchical statistical models for the fusion of multiresolution image data[A]. In:Proc. Int. Conf. Computer Vision[C], Cambridge, MA, USA,June 1995:908~913.
[4]  [7]Chardin A, Perez P. Semi-iterative inference with hierarchical Energy-based Models for Image Analysis [A]. In: Int.Workshop on Energy Minimzation Methods in Computer Vision and Pattern Recognition [C], Univercity of York, England:Springer Verlag, July 1999,1654 : 83~98.
[5]  [1]Charles A. Bouman and michael shapiro. A multiscale random field model for bayesian image segmentation [J]. IEEE. Trans.Image Processing, 1994,3 (2): 162~177.
[6]  [3]Pérez P, Chardin A, Laferté J M. Noniterative manipulation of discrete energy-based models for image analysis [J]. Pattern Recognition, 2000, 33(4) :573~586.
[7]  [6]Chardin A, Perez P. Semi-iterative inference with hierarchical model [A]. In: Int. Conf. on image processing [C], Chicago,Illinois, USA. October 1998 : 630~634.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133