期刊文献+

基于局部特征和隐条件随机场的场景分类方法 被引量:4

Scene Classification Based on Local Feature and Hidden Conditional Random Fields
在线阅读 下载PDF
导出
摘要 针对复杂场景图像分类的难题,提出一种基于局部特征和隐条件随机场的场景分类方法.该方法将图像划分为一系列超像素区域,提取每个区域的局部特征组成观察图像的输入特征向量,并建立基于隐条件随机场的场景分类模型推断图像的场景类别标记,其中每个局部特征对应一个隐变量.训练采用随机梯度上升法估计模型参数.在标准的图像库上进行实验,结果表明,与同类方法相比,场景分类方法取得了更好的分类结果. To solve the problem of complex scene classification,an approach based on local feature and hide conditional random fields(HCRF) is proposed.Firstly,the image is segmented into sets of super-pixels,and then the local features extracted from those regions are used as the characteristic vectors of input image observations.Secondly,the HCRF model is established to infer the scene category of the image,where every local feature has the corresponding latent variable.The parameters of the model could be estimated using random gradient ascent algorithm.On the public image dataset,the test results demonstrate that the proposed approach has better classification results than the previous methods.
出处 《北京理工大学学报》 EI CAS CSCD 北大核心 2012年第7期720-724,共5页 Transactions of Beijing Institute of Technology
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(NCET-09-0126) 河南省科技创新人才杰出青年计划(114100510006) 国家教育部高等学校博士学科点专项科研基金资助课题(20110121110020) 国防科工局资助项目(B1420110155) 航空科学基金资助项目(20095155008) 福建省自然科学基金资助项目(2011J01365) 河南省高等学校青年骨干教师资助计划项目 郑州市科技创新人才培育计划项目(10PTGG342-1)
关键词 图像分析 特征提取 隐条件随机场 场景分类 image analysis feature extraction hide conditional random fields scene classification
  • 相关文献

参考文献13

  • 1高琳,唐鹏,盛鹏,左航,游志胜.复杂场景下基于条件随机场的视觉目标跟踪[J].光学学报,2010,30(6):1721-1728. 被引量:15
  • 2He X, Zemel R S, Carreira-Perpin-a'n M A'. Multiscale conditional random fields for image labeling [C] // Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE Computer Society, 2004:695- 702.
  • 3Quattoni A, Wang S B, Morency L P, et al. Hidden conditional random fields [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(10) : 1848 - 1852.
  • 4褚一平,张引,叶修梓,张三元.基于隐条件随机场的自适应视频分割算法[J].自动化学报,2007,33(12):1252-1258. 被引量:11
  • 5Wang Y, Mori G. Hidden part models for human action recognition., probabilistic versus max-margin[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(7) : 1310 - 1323.
  • 6Vogel J, Schiele B. Semantic modeling of natural scenes for content-based image retrieval [J]. International Journal of Computer Vision, 2007,72(2) ..133 - 157.
  • 7Bosch A, Zisserman A. Scene classification using a hybrid generative/discriminative approach [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(4) : 712 - 727.
  • 8Bosch A, Zisserman A, Munoz X. Scene classification via pLSA[C] // Proceedings of European Conference on Computer Vision. Graz, Austria: Springer, 2006: 517 - 530.
  • 9Jin T, Li L, Li P, et al. Hidden conditional random fields for category and scene classification[J].Journal of Computational Information Systems, 2012, 8 ( 2 ):877 -885.
  • 10刘靖,李翠华,杨敦旭.一种基于超像素的户外建筑图像布局标定方法[J].厦门大学学报(自然科学版),2010,49(2):175-180. 被引量:3

二级参考文献47

共引文献26

同被引文献32

  • 1ZHAO L Y, WANG X, SUKTHANKAR G, et al. Motif discovery and feature selection for CRF-bascd activity recognition[ C]//20th International Conference on Pattern Recognition. Piscataway, N J: IEEE Press, 2010:3826-3829.
  • 2WANG S B, QUATYONI A. Hidden conditional random fields for gesture recognition [ C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2006:1521 - 1527.
  • 3MORENCY L P, QUATI'ONI A, DARRELL T. Latent - dynamic discriminative models for continuous gesture recognition[ C]//2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2007: 1- 8.
  • 4ZHANG J G , GONG S G . Action categorization with modified hidden conditional random field[ J]. Pattern Recognition, 2010, 43 (1): 197-203.
  • 5FUJ]I Y, YAMANOTO K, NAKAGAWA S. Hidden conditional neural fields for continuous phone speech recognition[ J]. IEICE Transactions on Information and Systems, 2012, E95-D(8) : 2094 -2104.
  • 6SUTTON C , ROHANIMANESH K , MeCALLUM A . Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence" data [ C ]// Twenty-First International Conference on Machine Learning. New York: ACM Press, 2004:783-790.
  • 7BLANK M , GORELICK L , SHECHTMAN E , et al. Actions as space-time shapes[ C]// 10th IEEE International Conference on Computer Vision. Piseataway, NJ: IEEE Press, 2005: 1395- 1402.
  • 8WrlTENLH,FRANKE.数据挖掘实用机器学习技术[M].董琳,邱泉,于晓峰,译.北京:机械工业出版社,2006:254-238.
  • 9刘瑞清.基于条件随机场模型的超光谱图像分类[D].西安:西安电子科技大学,2012.
  • 10Sutton C,Mccallum A.An introduction to conditional random fields[J].Machine Learning,2011,4(4):267-373.

引证文献4

二级引证文献15

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