计算机应用 ›› 2016, Vol. 36 ›› Issue (2): 574-579.DOI: 10.11772/j.issn.1001-9081.2016.02.0574

• 人工智能 • 上一篇    下一篇

融合纹理结构的潜在狄利克雷分布铁路扣件检测模型

罗建桥, 刘甲甲, 李柏林, 狄仕磊   

  1. 西南交通大学 机械工程学院, 成都 610031
  • 收稿日期:2015-07-14 修回日期:2015-09-01 出版日期:2016-02-10 发布日期:2016-02-03
  • 通讯作者: 李柏林(1962-),男,广西桂林人,教授,博士生导师,博士,主要研究方向:图像处理、优化技术。
  • 作者简介:罗建桥(1991-),男,湖南湘潭人,硕士研究生,主要研究方向:图像语义分析、机器学习;刘甲甲(1983-),男,安徽淮北人,博士研究生,CCF会员,主要研究方向:图像信息融合、模式识别;狄仕磊(1992-),男,甘肃武威人,硕士研究生,主要研究方向:图像分割、目标检测。
  • 基金资助:
    四川省科技支撑计划项目(2013GZ0032,2014GZ0005);2014年西南交通大学博士创新基金资助项目。

Latent Dirichlet allocation model integrated with texture structure for railway fastener detection

LUO Jianqiao, LIU Jiajia, LI Bailin, DI Shilei   

  1. School of Mechanical Engineering, Southwest Jiaotong University, Chengdu Sichuan 610031, China
  • Received:2015-07-14 Revised:2015-09-01 Online:2016-02-10 Published:2016-02-03

摘要: 针对潜在狄利克雷分布(LDA)模型忽略图像结构的问题,提出一种融合图像纹理结构信息的LDA扣件检测模型TS_LDA。首先,设计一种单通道局部二值模式(LBP)方法获得图像纹理结构,将单词的纹理信息作为标注,用单词和标注的联合分布反映了图像的结构特点;然后,将标注信息嵌入LDA,由单词和标注共同推导图像主题,改进之后的主题分布考虑了图像结构;最后,以该主题分布训练分类器,检测扣件状态。相比LDA方法,正常扣件与失效扣件在TS_LDA主题空间中的区分度增加了5%~35%,平均漏检率降低了1.8%~2.4%。实验结果表明,TS_LDA能够提高扣件图像建模精度,从而更加准确地检测扣件状态。

关键词: 纹理结构, 视觉单词, 单词标注, 潜在狄利克雷分布模型, 铁路扣件检测

Abstract: Focusing on the ignorance of the image structure in Latent Dirichlet Allocation (LDA) model, a LDA fastener detection model integrated with image texture information, namely TS_LDA, was proposed. Firstly, a single-channel Local Binary Pattern (LBP) method was designed to acquire the image texture structure, and the texture information was treated as a label of visual word. The joint distribution of words and labels reflected the characteristics of an image structure. Secondly, those labels were embedded into LDA, and image topics were derived from words and labels. The improved distribution of topics considered the image structure. Finally, the classifier was trained and fastener states were identified on the basis of topic distribution. Compared with the LDA method, the differences between normal and disabled fasteners increased by 5%-35%, the average misdetection rate decreased by 1.8%-2.4% in the topic space of TS_LDA. The experimental results show that TL_LDA is able to enhance the accuracy of fastener image modeling, thus inspects fastener states more precisely.

Key words: texture structure, visual word, label of word, Latent Dirichlet Allocation(LDA)model, railway fastener detection

中图分类号: