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...

基于多层马尔科夫随机场模型的变化检测

Keywords: 变化检测,图像分割,马尔科夫随机场,特征提取

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出了一种基于多层马尔科夫随机场模型的变化检测方法.首先输入的多个特征通过模拟退火方法得到对应每个特征的初步检测结果,然后利用多层马尔科夫随机场将初步检测结果进行融合.最后对图像进行目标级分割并与像素级变化检测结果相结合,根据各个目标的变化率给出了最终的变化检测.文章提出的方法运用多层马尔科夫随机场融合方法充分考虑了相邻像素间的相关性和各层之间的联系,并从目标角度进行了变化率的分析,使得融合结果更细致和精确.

References

[1]  Radke R J,Andra S,A-iKo F,et al.Image change detection algorithms:a system atic survey[J].IEEE Trans on Image Processing,2005,14(3):294-307.
[2]  Dai X L,Khorram S.The effects of image misregistration on the accuracy of remotely sensed change detection[J].IEEE Trans on Geoscience and Remote Sensing,1998,36(5):1 566-1 577.
[3]  Huo C L,Cheng J,Lu H Q,et al.Object-level change detection based on multiscale fusion[J].Acta Automatica Sinica,2008,34(3):251-257.
[4]  Su J,Lin X G,Liu D Z.Change detection algorithm for remote sensing images based on object matching[J].Journal of Tsinghua University:Natural Science Edition,2007,47(10):1 610-1 613.
[5]  Benedek C S,Szir’anyi T,Kato Z,et al.A multi-layer MRF model for object-motion detection in unregistered airborne image-pairs[C]//IEEE International Conference on Image Processing(ICIP).San Antonio,Texas,USA,2007:141-144.
[6]  Li X C,Zhu S A.A survey of the Markov random field method for image segmentation[J].Journal of Image and Graphics,2007,12(5):789-798.
[7]  Chen Y,Cao Z.An improved MRF-based change detection approach for multitemporal remote sensing imagery[J].Signal Processing,2013,93(1):163-175.
[8]  Guo W,Zhu M M,Yang H B.A study on RCS recognition method of radar targets based on hidden Markov[J].Modern Radar,2013,35(3):37-40.
[9]  Celik T.Change detection in satellite images using a genetic algorithm approach[J].IEEE Geoscience and Remote Sensing Letters,2010,7(2):386-390.
[10]  Mao G G,Yu C,Qiao D W.A neighborhood based ratio approach for change detection in SAR images[J].IEEE Geosci Remote Sens Lett,2012,2(9):308-311.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133