《计算机应用研究》|Application Research of Computers

基于语义和谱聚类的监理视频R树检索方法

Supervision video R-tree retrieval method based on semantic and spectral clustering algorithm

免费全文下载 (已被下载 次)  
获取PDF全文
作者 宋华珠,程贵,巫世峰,钟忺
机构 武汉理工大学 计算机科学与技术学院,武汉 430070
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)06-025-1717-06
DOI 10.19734/j.issn.1001-3695.2018.03.0133
摘要 土木工程监理视频是提高土木工程监理质量的一种有效手段。首先以土木工程监理视频检索为研究对象,建立土木工程监理视频的语义,且对土木工程监理视频数据进行了语义划分,随后结合维基百科相关的部分中文词条和从土木工程监理领域整理的词条进行词向量训练,并使用这些词向量数据对标注数据条目进行训练,为监理视频R树提供含有语义的词向量数据;然后研究基于谱聚类的节点分裂,提出了基于谱聚类的R树节点分裂算法和基于词向量的R树节点检索算法。最后用实际工程的例子说明了所确定的监理视频语义能准确表示监理视频的主要内容,同时实验结果表明该算法优化能有效提高土木工程监理视频的索引速度和检索查全率。
关键词 土木工程监理视频; 语义; 谱聚类; R树; 词向量; 节点分裂
基金项目 国家自然科学基金资助项目(61003130)
国家科技支撑计划子课题(2012BAH33F03)
湖北省自然科学基金资助项目(2015CFB525)
本文URL http://www.arocmag.com/article/01-2019-06-025.html
英文标题 Supervision video R-tree retrieval method based on semantic and spectral clustering algorithm
作者英文名 Song Huazhu, Cheng Gui, Wu Shifeng, Zhong Xian
机构英文名 College of Computer Science & Technology,Wuhan University of Technology,Wuhan 430070,China
英文摘要 The video of civil engineering supervision provides an effective method to improve the quality of civil engineering supervision. This paper first took the video retrieval of civil engineering supervision as the research object, established the semantics of civil engineering supervision video, and regulated the semantic division of civil engineering supervision video. It trained some related Chinese entries in Wikipedia and several civil engineering supervision entries in the domain on word vectors, and used these word vector data to train the labeled data items in order to provide the word vector data with semantic for the R-tree in the video of civil engineering supervision. Then it studied the nodes splitting based on spectral clustering and the proposed the corresponding algorithm, and also proposed the R-tree node retrieval algorithm based on word vector. Finally, the practical experimental results show that the semantic proposed is able to represent the video in the civil engineering supervision, and the proposed algorithms can effectively improve the indexing speed and recall rate of civil engineering supervision video.
英文关键词 civil engineering supervision video; semantic; spectral clustering; R-tree; word vector; node split
参考文献 查看稿件参考文献
 
收稿日期 2018/3/21
修回日期 2018/5/9
页码 1717-1722
中图分类号 TP311.1;U415.13
文献标志码 A