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

基于视觉注意力模型的高速铁路轨道病害检测 被引量：2

High-speed Railway Track Damage Detection Based on the Model of Visual Attention
原文传递
导出
摘要 提出了基于视觉注意力模型的高速铁路轨道病害检测方法.采用基于稀疏采样和核密度估计的视觉注意力模型,得到高速铁路车载视频的显著图,进而提取视频中包含病害的区域;为了解决病害图像分类中的小样本问题,结合已标记样本和未标记样本,提出了基于生成模型的半监督分类方法,并用于高速铁路轨道病害识别分类.对3种典型的轨道病害进行了检查与识别实验,实验结果表明,该方法具有很高的检测率和识别率. Based on the model of visual attention, a track damage detection method for high-speed railways is proposed. The visual attention model based on sparse sampling and kernel density estimation is adopted to extract the damaged regions from the salient maps of a high-speed railway video. A semi-supervised classification based on a generative model is proposed to solve the problem of having a small sample in the damaged image classification. Then, it is used in the damaged images＇ recognition and classification, which makes use of both labeled and unlabeled samples. Three types of typical track damages are examined in the experiment and the results show that the proposed method has a high detection and recognition rate.
作者 夏利民 刘涛 肖永良
机构地区 中南大学信息科学与工程学院 湖南财政经济学院信息管理系
出处 《信息与控制》 CSCD 北大核心 2015年第3期353-358,共6页 Information and Control
基金 国家自然科学基金资助项目(50808025) 湖南省科技计划资助项目(S2013G2013) 中南大学博士后基金资助项目(2014)
关键词 高速铁路轨道 视觉注意力模型 显著图 生成模型 半监督分类 high-speed railway track visual attention model saliency map generative model semi-supervised classification
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献16

  • 1Jack R, Jackson P. Imaging attributes of railway track formation and ballast using ground probing radar[ J]. NDT & E International, 1999, 32 (8) : 457 - 462.
  • 2Hugensehmidt J. Railway track inspection using GPR[ J l. Journal of Applied Geophysics, 2000, 43 (2) : 147 -155.
  • 3Wei S B, Li Y, Zhao Y F, et al. Design and development of GJ-6 track detection system[J]. Railway Engineering, 2012(2) : 97 -100.
  • 4Robert I F, Yushchenko L. Visual attention model for computer vision[ J]. Biologically Inspired Cognitive Architectures, 2014, 7( 1 ) : 26 - 38.
  • 5Toet A. Computational versus psyehophysieal l~ottom-up image saliency: A comparative evaluation study[J]. Pattern Analysis and Machine In- telligence, 2011, 33(11): 2131 -2146.
  • 6David F, Odelia S, Juan F. A saliency-based bottom-up visual attention model for dynamic scenes analysis [ J ]. Biological Cybernetics, 2013, 107(2) : 141 -160.
  • 7Guo M W, Zhao Y Z, Zhang C B, et al. Fast object detection based on selective visual attention[J]. Neurocomputing, 2014, 9( 1 ) : 1 - 14.
  • 8Naveed E, Irfan M, Sung W B. Feature aggregation based visual attention model for video summarization[ J]. Computers and Electrical Engi- neering, 2014, 40(3): 993- 1005.
  • 9Araken S, Anne C. Applying semi-supervised leaming in hierarchical multi-label classification[ J ]. Expert Systems with Applications, 2014, 41 (14) : 6075 - 6085.
  • 10朱韶平,夏利民,彭东亮.基于图像和GM-PLSA模型的物品推荐方法[J].系统工程,2013,31(12):109-115. 被引量：2

二级参考文献20

  • 1Hofmann T, Puzicha J. Latent class models for collaborative filtering [C] // IJCAI. Stockholm, 1999:688-693.
  • 2Hofman T. Collaborative filtering via Gaussian probabilistie latent semantic analysis [C] // Pro- ceedings of international conference on SIGIR'03. Toronto, 2003 : 259- 266.
  • 3Guo Z F. Research on recommendation list diversity of recommender systems [C] // International conference on management of e-commerce and e-government. Nanchang, 2008 : 72 - 76.
  • 4Tao P, Dong W W, Yang G X. A graph indexing approach for content-based recommendation system [C] // 2010 Second International Conference on MultiMedia and Information Technology, 2010 : 93- 97.
  • 5Wen W Y, Hui W S, Natalia S. Enhancing content- based recommendation with the task model of classification. Knowledge Engineering and Management by the Masses, 2010,6317 : 431-440.
  • 6Li Y, Lu L, Feng L X. A hybrid collaborative filtering method for multiple-interests and multiple- content recommendation in e-commerce [J]. Expert Systems with Applications, 2005,28 : 67- 77.
  • 7Luis M, Juan M, Juan F. Combining content-based and collaborative recommendations: A hybrid approach based on Bayesian networks [ J ]. International Journal of Approximate Reasoning, 2010,51 (7) : 785- 799.
  • 8Adomavicius G, Kwon Y. Improving aggregate recommendation diversity using ranking-based Techniques [C] // Proceedings of the IEEE Transactions on Knowledge and Data Engineering. Piscataway,NJ,USA :IEEE, 2011 : 1- 15.
  • 9Fleder D, Hosanagar K. Blockbuster culture' s next rise or fall: The impact of recommender systems on sales diversity [J]. Management Science, 2009, 55(5) :697-712.
  • 10Anderson C. The long tail-Der lange Schwanz[M]. New York : Hyperion, 2006 : 1 - 15.

共引文献1

同被引文献22

  • 1] Ashraf A B, Lucey S, Cohn J, et aI. The painful face II-pain expression recognition using active appearance models [J ]. Image Vision Computing, 2009, 27 (12): 1788-1796.
  • 2Lucey P, Cohn J, Lucey S, et al. Painful monitoring: Auto- matic pain monitoring using the UNBC-McMaster shoulder pain expression archive database [J]. Image and Vision Computing, 2012, 30 (3): 197-205.
  • 3Lucey P, Cohn J, Lucey S, et al. Automa-tically detecting pain using facial actions [C] //3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, 2009 : 1-8.
  • 4Lucey P, Cohn J F, Matthews I, et al. Automatically detec- ting pain in video through facial action units [J]. IEEE Tran- sactions on Systems, Man, and Cybernetics, Part B: Cyber- netics, 2011, 41 (3): 664-674.
  • 5Nanni L, Brahnam S, Lumini A. A local approach based on a local binary patterns variant texture descriptor for classifying pain states [J]. Expert Systems with Applications, 2010, 37 (12) : 7888-7894.
  • 6Sikka K, Dhall A, Bartlett MS. Classification and weakly, super- vised pain localization using multiple segment representation [-J]. Image and Vision Computing, 2014, 32 (10): 659-670.
  • 7Zhu S P. Pain expression recognition based on pLSA model [-J/ OL]. The Scientific World Journal, 2014. http: //dx. doi. org/ 10. 1155/2014/736106.
  • 8Bengio Y, Delalleau O. On the expressive power of deep archi- tectures [C] //Proc of 14th International Conference on Dis-covery Science. Berlin: Springer-Verlag, 2011: 18-36.
  • 9Itamar A, Derek C R, Thomas P K. Deep machine leaming-a new frontier [J]. Artificial Intelligence Research IEEE Compu- tational Intelligence Magazine, 2010, 5 (4): 13-18.
  • 10Bengio Y. Learning deep architectures for AI [J]. Founda- tions and Trends in Machine Learning, 2009, 2 (1): 1-127.

引证文献2

二级引证文献9

信息与控制
2015年 第3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