论文部分内容阅读
随着城市规模的不断扩大,道路标牌的有效管理是智能交通中的一个关键问题.本文在基于本体有机整合海量、多源、异构语义数据的基础上,研究基于国家路标设置规范的路标牌位置和内容有效性自动审核,是对语义技术在智能交通应用中的有益探索.首先,对地缘信息中的道路、兴趣点及路标建立统一模型,采用本体技术把海量数据在语义层面上关联起来.其次,对国家路标设置规范中的规则进行分类,对每一类规则分别构造规则模板及为其构造带参数的SPARQL查询,从而将路标设置指南进行规范形式化表示,在此基础上实现对路标牌的自动检测.最后,在构建的实验数据集上进行了实验,实验结果证明,提出的方法路牌检测准正确率达到85.1%,召回率达到92.1%.
With the continuous expansion of the city scale, the effective management of road signs is a key issue in intelligent transportation.Based on the ontology organic integration of massive, multi-source and heterogeneous semantic data, this paper studies road signs based on the national road signs setting standards Automatic review of the validity of the location and content is a useful exploration of semantic technology in the application of intelligent transportation.Firstly, a unified model of the roads, points of interest and road signs in geo-information is established, and the ontology is used to correlate the massive data semantically .Secondly, we classify the rules in the national roadmap setting rules, construct the rule templates for each type of rules and construct the SPARQL query with parameters for them respectively, so as to formalize the roadmap setting guidelines, and on this basis, Finally, the experiment was carried out on the constructed experimental dataset. The experimental results show that the proposed method has the accuracy of 85.1% and the recall rate of 92.1%.