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...
电子学报  2014 

多高斯模型特征空间覆盖学习的海洋航摄图像分割

DOI: 10.3969/j.issn.0372-2112.2014.10.039, PP. 2117-2122

Keywords: 航拍海洋图像,多高斯模型,特征空间,覆盖学习,图像分割

Full-Text   Cite this paper   Add to My Lib

Abstract:

本文提出了一种新的基于多高斯特征空间覆盖学习的航摄海洋图像分割方法.通过分析,发现在RGB三维色空间中,海水背景像素点的分布尽管在不同成像条件下具有不同的分布特性,但其具有的共同特性是具有集聚性,可以被一个或多个椭球所覆盖.因此,本文在色空间中基于贝叶斯最大后验概率和3δ准则对海水背景进行多高斯分布模型覆盖建模,自学习得到其高斯分布个数并建立相对应的多高斯分布模型.最后,根据上述学习结果,从航拍海洋的图像中分离出海水背景,实现航拍海洋图像中背景和目标的分割.实验证明,该方法具有良好的背景学习性能,能够准确有效地得到海水背景多高斯分布覆盖模型.基于该背景学习模型的海洋图像分割,具有较高的正确率和较低的误差,且算法花费的时间较少,具有较好的稳定性和实时性.

References

[1]  刘田田.可见光海面航拍图像的分析与辨别[D].深圳:深圳大学,2011.
[2]  刘颖.航拍海洋图像的分析与分割[D].深圳:深圳大学,2012.
[3]  刘颖,裴继红,谢维信,王荔霞.基于背景学习的海洋图像分割方法[A].第四届中国信息融合大会[C].武汉,2012.692-698. Liu Ying,Pei Ji-hong,Xie Wei-xin,Wang Li-xia.Ocean image segmentation method based on background learning[A].The Fourth Chinese Information Fusion Conference[C].Wuhan,2012.692-698.(in Chinese)
[4]  熊彪,江万寿,李乐林.基于高斯混合模型的遥感影像半监督分类[J].武汉大学学报·信息科学版,2011,36(1):108-112. Xiong Biao,Jiang Wan-shou,Li Le-lin.Gauss mixture model based semi-supervised classification for remote sensing image[J].Geometrics and Information Science of Wuhan University,2011,36(1):108-112.(in Chinese)
[5]  刘松涛,陆斌,王慧丽,殷福亮.基于粗精交互融合和迭代图像割的舰船可见光图像分割方法[J].光电子·激光,2012,23(8):1609-1615. Liu Song-tao,Lu Bin,Wang Hui-li,Yin Fu-liang.Ship visible image segmentation method based on combining coarse and precise interaction and iterative graph cut[J].Journal of Optoelectronics·Laser,2012,23(8):1609-1615.(in Chinese)
[6]  朱峰,张晓娜,陈健美,刘哲.基于多阶抽样的高斯混合模型彩色图像分割[J].中国图象图形学报,2011,16(4):566-571. Zhu Feng,Zhang Xiao-na,Chen Jian-mei,Liu Zhe.Color image segmentation based on Gaussian mixture model with multi-sampling[J].Journal of Image and Graphics,2011,16(4):566-571.(in Chinese)
[7]  Figueiredo M A T,Jain A K.Unsupervised learning of finite mixture models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(3):381-396.
[8]  Yang A Y,Wright J,Ma Y,Sastry S S.Unsupervised segmentation of natural images via lossy data compression[J].Computer Vision and Image Understanding,2008,110(2):212-225.
[9]  兰志刚,靳卫卫,朱明亮,等.基于高斯混合模型的海冰图像非监督聚类分割研究[J].海洋科学,2011,35(11):97-100. Lan Zhi-gang,Jin Wei-wei,Zhu Ming-liang,et al.Sea ice image segmentation with unsupervised clustering based on the Gaussian mixture model[J].Marine Science,2011,35(11):97-100.(in Chinese)
[10]  Hanan Al-Jubouri,Hongbo Du,Harin Sellahewa.Applying Guassianmixture model on discrete Cosine features for image segmentation and classification[A].2012 4th Computer Science and Electronic Engineering Conference (CEEC)[C].University of Essex,UK,2012.194-199.
[11]  Wei Li,Saurabh Prasad,James E Fowler.Classification and reconstruction from random projections for hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(2):833-843.
[12]  P Wayne Power,Johann A Schoonees.Understandingbackground mixture models for foreground segmentation[A].Proceedings of Image and Vision Computing[C].New Zealand,2002.266-271.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133