期刊文献+

基于贝叶斯网的航拍图像建筑目标提取算法

Automatic building extraction from aerial images based on Bayesian nets
下载PDF
导出
摘要 提出一种基于贝叶斯网的建筑目标提取算法。该算法通过多场景航拍图像进行训练后建立纹元字典,将实际图像中的纹元映射到纹元字典获得图像的场景类信息;然后使用朴素贝叶斯网建模建筑目标与场景类空间上下文的关系约束,将建筑目标提取转换为求解贝叶斯网类别节点的后验概率问题。与同类方法的对比实验表明,提出的算法能有效地提取航拍图像中的建筑目标。 This paper proposed an approach to building extraction from aerial image using Bayesian nets.Firstly,it represented texton dictionary by training aerial image sets.Secondly,acquired classification of a new image by mapping the textons to texton dictionary and obtained the scene categories in the whole image.Finally,it selected naive Bayesian nets to represent spatial constraints between objects and scene classes,and computed the posterior probability of category node to building extraction.The test on the dataset shows that the proposed approach yields substantial improvement over others on building extraction from the aerial image.
出处 《计算机应用研究》 CSCD 北大核心 2012年第4期1550-1552,共3页 Application Research of Computers
基金 国家自然科学基金资助项目(41171341) 国家教育部新世纪优秀人才支持计划资助项目(2009) 河南省科技创新杰出青年计划(114100510006) 航空科学基金光电控制技术国防科技重点实验室资助项目(20095155008) 福建省自然科学基金资助项目(2010J05099 2011J01365) 河南省科技攻关资助项目(112102310082) 河南省高等学校青年骨干教师资助计划 郑州市科技创新培育计划(10PTGG342-1)
关键词 图像分析 目标识别 贝叶斯分类器 航拍图像 纹元 image analysis target recognition Bayesian classifier aerial image textons
  • 相关文献

参考文献9

  • 1PORWAY J,WANG K,ZHU S C.Hierarchical and contextual modelfor aerial image understanding[J].International Journal of Com-puter Vision,2010,88(2):254-283. 被引量:1
  • 2KARANTZALOS K,PARAGIOS N.Recognition-driven two-dimen-sional competing priors toward automatic and accurate building detec-tion[J].IEEE Trans on Geoscience and Remote Sensing,2009,47(1):133-144. 被引量:1
  • 3KATARTZIS A,SAHLI H.A stochastic framework for the identifica-tion of building rooftops using a single remote sensing image[J].IEEE Trans on Geoscience and Remote Sensing,2008,46(1):259-271. 被引量:1
  • 4孙显,王宏琦,张正.基于对象的Boosting方法自动提取高分辨率遥感图像中建筑物目标[J].电子与信息学报,2009,31(1):177-181. 被引量:15
  • 5唐亮,谢维信,黄建军,谢兴灿,刘洁.从航空影像中自动提取高层建筑物[J].计算机学报,2005,28(7):1199-1204. 被引量:12
  • 6LI Fei-fei,IYER A,KOCH C,et al.What do we perceive in a glanceof a real-world scene[J].Journal of Vision,2007,7(1):1-29. 被引量:1
  • 7VARMA M,ZISSERMAN A.A statistical approach to texture classifi-cation from single images[J].International Journal of ComputerVision,2005,62(1-2):61-81. 被引量:1
  • 8SIRMACEK B,NSALAN C.Urban area and building detection usingSIFT keypoints and graph theory[J].IEEE Trans on Geoscienceand Remote Sensing,2009,47(4):1156-1167. 被引量:1
  • 9AGARWAL S,AWAN A,ROTH D.Learning to detect objects in ima-ges via a sparse,part-based representation[J].IEEE Trans on Pat-tern Analysis and Machine Intelligence,2004,26(11):1475-1490. 被引量:1

二级参考文献24

  • 1苏俊英,曹辉,张剑清.高分辨率遥感影像上居民地半自动提取研究[J].武汉大学学报(信息科学版),2004,29(9):791-795. 被引量:26
  • 2周俊,晏非,孙曼.基于区域分割合并的建筑物半自动提取方法[J].海洋测绘,2005,25(1):58-60. 被引量:7
  • 3侯蕾,尹东,尤晓建.一种遥感图像中建筑物的自动提取方法[J].计算机仿真,2006,23(4):184-187. 被引量:23
  • 4Definiens Image GmbH, Munich, Germany. eCognition User Guide[OL], http://www.definiensimaging.com/product .htm, 2002. 被引量:1
  • 5Marceau J. The scale issue in the social and naturalsciences[J]. Canadian Journal of Remote Sensing, 1999, 25(4): 347-356. 被引量:1
  • 6Hay G, Blaschke T, and Marceau D. A comparison of three image-object methods for the multiscale analysis of landscape structure[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2003, 57(5): 327-345. 被引量:1
  • 7Shi Jianbo and Malik J. Normalized cuts and image segmentation[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905. 被引量:1
  • 8Vezhnevets A and Vezhnevets V. Modest AdaBoost -teaching AdaBoost to generalize better[C]. Graphicon2005, Novosibirsk Akademgorodok, Russia, 2005: 79-81. 被引量:1
  • 9He X C and Yung N H C. Curvature scale space corner detector with adaptive threshold and dynamic region of support[C]. Proc 17th International Conference on Pattern Recognition, Cambridge, UK: IEEE Computer Society, 2004: 791-794. 被引量:1
  • 10Mayer H.. Automatic object extraction from aerial imagery--A survey focusing on buildings. Computer Vision and Image Understanding, 1999, 74(2): 138~149 被引量:1

共引文献25

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