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...

利用贝叶斯网络进行遥感变化检测

DOI: 10.11834/jig.200506138

Keywords: 有向无环结构,独立性测试,多光谱遥感数据,变化信息检测

Full-Text   Cite this paper   Add to My Lib

Abstract:

多时相遥感信息变化检测及其算法探索是当前国际遥感领域研究的热点,但是贝叶斯网络在遥感数据分类、特别是应用在变化检测方面的文献却很少。本文介绍了利用贝叶斯网络的变量间独立性测试原理,构建了输入两个时相多波段遥感信息的有向无环结构,利用训练后的网络进行两个时相多波段遥感变化信息的检测,取得了较好的效果。对北京六环线以内区域,1994年、2003年5种地类变化信息的遥感数据检测和类型转换进行了统计,其中耕地转换为城镇的占整个区域的26.52%,绿地增加占整个区域4.68%,水体减少占整个区域6.78%,导致裸地增加占整个区域4.80%,这个结果也在1∶5万的航空影像和地面上得到了验证。实验结果表明,贝叶斯网络为遥感数据的直接变化检测提供了一种新的途径。

References

[1]  Friedman D, Geiger N, Goldszmidt M. Bayesian network classifiers [J]. Machine Learning, 1997,29(2) :131 ~ 161.
[2]  HASI Bagan, MA Jian-wen. The Self-Organizing Feature Map Neural Networks Classification of the ASTER Data Based on Wavelet Fusion [J]. China Science[D], 2003, 33 (9): 896~902.
[3]  Heo JOON, Ftzhugh Thomas W. A standardized radiometric normalization method for change detection using remotely sensed imagery[J]. Photogrammetric Engineering & Remote Sensing, 2000,66(2) :173~181.
[4]  Fayyad U M, Irani K B. Multi-interval discretization of continuousvalued attributes for classification learning [ A ]. In: Proceedings of the 13th International Joint Conference on Artificial Intelligence[C] ,San Mateo, CA, 1993:1022 ~ 1027.
[5]  Friedman N, Elidan G. Learning the dimensionality of hidden variables [A]. In: Proceedings of Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI ) [C] , Seattle,Washington, USA, 2001:144~151.
[6]  Cheng J, Bell DA, Liu W. An algorithm for Bayesian belief network construction from data[A]. In: Proceedings of Artificial Intelligence & Statistics[C] , Ft. Lauderdale, Florida, USA, 1997:83~90.
[7]  Cheng J, Greiner R, Kelly J, et al. Learning Bayesian networks from data: an information-theory based approach [J]. The Artificial Intelligence Journal, 2002, 137 ( 1 ) :43~90.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133