期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

整合局部特征和滤波器特征的空间金字塔匹配模型 被引量：9

Unifying Local Features and Filterbank Features in the Spatial Pyramid Matching Model
在线阅读 下载PDF
导出
摘要 本文提出一种场景分类方法,通过整合局部特征和滤波器特征获得丰富的表征信息,并利用空间金字塔匹配模型提取空间上下文信息.该方法有如下四个特点:(1)通过转换将滤波器很好地嵌入空间金字塔匹配模型中;(2)在滤波器特征转换的过程中,采用降采样和平均操作,在空间密度和空间范围两者之间取得了很好的折衷;(3)将滤波器特征和局部特征组合起来,获得了更强的描述能力;(4)捕获了像素域和调制域的互补信息.同时,在三个数据库上的实验证明了该方法的有效性. This paper presents an approach to scene classification,which unifies local features and filterbank features to capture rich representation information,and extracts spatial context information using the spatial pyramid matching（SPM） model.The proposed method has four characteristics.First,filterbank features are successfully embedded into the SPM model by a transformation method.Second,in the transform process,downsampling and average pooling are used to achieve good balance between spatial density and spatial extent.Third,filterbank features and local features are combined to represent images for more discriminative power.Fourth,the complementary information is extracted in pixel and modulation domains.Promising experimental results on three datasets demonstrate the effectiveness of the proposed method.
作者 高常鑫 桑农
机构地区 华中科技大学图像识别与人工智能研究所多谱信息处理技术国家级实验室
出处 《电子学报》 EI CAS CSCD 北大核心 2011年第9期2034-2038,共5页 Acta Electronica Sinica
基金 国家自然科学基金重点资助项目(No.60736010) 中国博士后科学基金资助项目(No.20100480902) 中央高校基本科研业务资助(No.HUST:2010ZD034)
关键词 基于上下文的表征 空间金字塔匹配 像素域 调制域 场景分类 context-based representation spatial pyramid matching pixel domain modulation domain scence classification
分类号 TP391.41 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献22

  • 1Torralba A,Murphy K P,et al.Context-based vision system for place and object recognition[A].Proceedings of the IEEE International Conference on Computer Vision[C].Nice,France:IEEE Press,2003.273-280.
  • 2Siagian C,Itti L.Rapid biologically-inspired scene classification using features shared with visual attention[J].International Journal of Computer Vision,2007,29(2):300-312.
  • 3谢昭,高隽.基于高斯统计模型的场景分类及约束机制新方法[J].电子学报,2009,37(4):733-738. 被引量：11
  • 4Abe Y,Shikano M,et al.Vision based navigation system for autonomous mobile robot with global matching[A].Proceedings of IEEE International Conference on Robotics and Automation[C].Detroit,Michigan:IEEE Press,1999.1299-1304.
  • 5Thrun S.Finding landmarks for mobile robot navigation[A].Proceedings of IEEE International Conference on Robotics and Automation[C].Leuven,Belgium:IEEE Press,1998.958-963.
  • 6于林森,张田文.基于视觉与标注相关信息的图像聚类算法[J].电子学报,2006,34(7):1265-1269. 被引量：6
  • 7Oliva A,Torralba A.Modeling the shape of the scene:a holistic representation of the spatial envelope[J].International Journal of Computer Vision,2001,42:145-175.
  • 8Biederman I,Mezzanotte R J,et al.Scene perception:detecting and judging objects undergoing relational violations[J].Cognitive Psychology,1982,14(2):143-177.
  • 9Oliva A,Schyns P G.Diagnostic colors mediate scene recognition[J].Cognition Psychology,2000,41(2):176-210.
  • 10Potter M C.Meaning in visual search[J].Science,1975,187(4180):965-966.

二级参考文献39

  • 1A Oliva, A Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope [ J]. International Journal of Computer Vision,2001,42(3) :145- 175.
  • 2A Oliva, A Torralba. Building the gist of a scene: the role of global image features in recognition[ J] .Progress in Brain Research,2006, 155:23 - 36.
  • 3T Serre, A Oliva, T A Poggio. A feedforward architecture accounts for rapid categorization[ A ]. In Proceedings of the National Academy of Science [ C ]. New York: PNAS, 2007. 6424 - 6429.
  • 4A Vailaya, M Figueiredo, A Jain, H Zhang. Image classification for content-based indexing [ J ].IEEE. Transactions on Image Processing, 2001,10(1) : 117 - 130.
  • 5E B Sudderth,A Torralba,W T Freeman,A S Willsky. Learning hierarchical models of scenes,objects and parts[A] .In Proceedings of Tenth IEEE International Conference on Vision[C]. USA: IEEE., 2005.1331 - 1338.
  • 6L F Fei, P Perona. A bayesian hierarchical model for learning natural scene categodes[ A]. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[ C]. USA: IEEE., 2001,2.524 - 531.
  • 7T Serre, L Wolf, T Poggio. Object recognition with features inspired by visual cortex [ A ]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[ C]. USA: IEEE, 2005,2.994 - 1000.
  • 8Y W Teh. Bethe free energy and contrastive divergence approximations for undirected graphical models[ D]. Toronto, Canada: University of Toronto, 2003,7.
  • 9Y W Teh,M Welling. The unified propagation and scaling algorithm[ J]. Advances in Neural Information Processing Systems,2001,14(2) :953 - 960.
  • 10D Lowe. Local feature view clustering for 3D object recognition[ A ]. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition[ C]. USA: IEEE., 2001.682 - 688.

共引文献52

同被引文献117

  • 1王国新,平西建,许漫坤,张涛,包锡锐.一种基于短重码间距统计的隐写分析方法[J].中国科学（F辑:信息科学）,2009,39(4):416-421. 被引量：2
  • 2杨绪兵,陈松灿.基于原型超平面的多类最接近支持向量机[J].计算机研究与发展,2006,43(10):1700-1705. 被引量：17
  • 3杨绪兵,陈松灿,杨益民.局部化的广义特征值最接近支持向量机[J].计算机学报,2007,30(8):1227-1234. 被引量：10
  • 4Xin Huang,Liangpei Zhang.An SVM Ensemble Approach Coming Spectral,Structural,and Semantic Features for the Classification of High-Resolution Remotely Sensed Ima-gery[J] .IEEE Trans.On Geoscience and Remoting Sensing,2013,51(1):257-272.
  • 5Nello Cristianini,John Shawe-Taylor.An introduction to Support Vector Machines and Other Kernel-based Learning Methods[M] .Cambridge University Press?New York,NY,USA,2000.
  • 6http://www.esat.kuleuven.be/sista/lssvmlab/.
  • 7Qi x j, Han Y T. Incorporating Multiple SVMs for Automatic Image Annotation. Pattern Recognition, 2007, 40(2) : 728-741.
  • 8Gabriella C, Dance C R, Fan L X, et al. Visual Categorization with Bags of Keypoints/! Proc of the Workshop on Statistical Learning in Computer Vision. Prague, Czech Republic, 2004 : 1-22.
  • 9Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories/! Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006, I!: 2169-2178.
  • 10Harzallah H, Jurie F, Schmid C. Combining Efficient Object Loca- lization and Image Classification // Proc of the 12th IEEE Inter- national Conference on Computer Vision. Kyoto, Japan, 2009:237-244.

引证文献9

二级引证文献46

电子学报
2011年 第9期

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