登录 | 注册 | 充值 | 退出 | 公司首页 | 繁体中文 | 满意度调查
综合馆
基于移动增强现实的智慧城市导览
  • 摘要

    提出一种采用移动增强现实技术实现智慧城市导览的方法,满足用户个性化、多尺度、按需推送的智能导览需求,呈现用户虚实融合的周边环境.移动终端计算性能以及资源存储能力有限,但集成多种传感器,方便携带,易于显示.利用服务器实现基于词汇树的海量场景识别定位系统.依据地理位置信息动态划分分区缩减了场景检索范围,基于二进制鲁棒尺度不变特征(binary robust invariant scalablekeypoints,BRISK)进行层级式聚类提高了识别算法的实时性.移动终端利用服务器返回的识别结果进行BRISK特征与光流算法结合的混合特征跟踪注册方法,并通过点集映射消除特征点漂移,利用前后帧信息以及关键帧信息减少跟踪抖动.UKbench标准图像库以及真实环境下的实验结果表明,虚实融合的智能导览效果良好.该原型系统已成功应用于上海电信体验馆等展馆智能导览系统.

  • 作者

    张运超  陈靖  王涌天  刘越  Zhang Yunchao  Chen Jing  Wang Yongtian  Liu Yue 

  • 作者单位

    北京理工大学计算机学院 北京 100081

  • 刊期

    2014年2期 ISTIC EI PKU

  • 关键词

    智慧城市导览  移动增强现实  动态区域划分  层级式聚类  混合特征跟踪  smart city guide  mobile augmented reality  dynamic partition  hierarchical clustering  hybrid feature tracking 

参考文献
  • [1] 范志强,赵沁平. 一种基于数据聚类的鲁棒SIFT特征匹配方法. 计算机研究与发展, 2012,5
  • [2] 秦磊,高文. 基于内容相关性的场景图像分类方法. 计算机研究与发展, 2009,7
  • [3] 钟志鹏,王涌天,陈靖,刘越. 一个基于移动视觉搜索技术的博物馆导览系统. 计算机辅助设计与图形学学报, 2012,4
  • [4] Taehee L;Hollerer T. Hybrid feature tracking and user interaction for markerless augmented reality. Piscataway,NJ:IEEE, 2008
  • [5] 陈靖;王涌天;郭俊伟. 基于特征识别的增强现实跟踪定位算法. 中国科学:信息科学, 2010,11
  • [6] Chum O;Matas J. Matching with PROSAC-progressive sample consensus. Piscataway,NJ:IEEE, 2005
  • [7] Tsai S;Chen D;Takacs G. Fast geometric re-ranking for image-based retrieval. Piscataway,NJ:IEEE, 2010
  • [8] Kurz D;Himane B. Inertial sensor-aligned visual feature descriptors. Piscataway,NJ:IEEE, 2011
  • [9] Jegou H;Douze M;Schmid C. Improving bag of-feature for large scale image search. {H}International Journal of Computer Vision, 2010,3
  • [10] Lee T;Hoellerer T. Multithreaded hybrid feature tracking for markerless augmented reality. {H}IEEE Transactions on Visualization and Computer Graphics, 2009,3
  • [11] Wagner D;Schmalstieg D;Bischof H. Multiple target detection and tracking with guaranteed framerates on mobile phones. Piscataway,NJ:IEEE, 2009
  • [12] Davison J;Reid D;Molton D. MonoSLAM:Real-time single camera SLAM. {H}IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,6
  • [13] Klein G;Murray D. Parallel tracking and mapping for small AR workspaces. Piscataway,N J:IEEE, 2007
  • [14] Trzcinski T;Lepetit V;Fua P. Thick boundaries in binary space and their influence on nearest-neighbor search. {H}Pattern Recognition Letters, 2012,16
  • [15] Bay H;Ess A;Tuytelaars T. SURF:Speeded up robust features. {H}COMPUTER VISION AND IMAGE UNDERSTANDING, 2008,3
  • [16] Leutenegger S;Chli M;Siegwart R. BRISK:Binary robust invariant scalable keypoints. Piscataway,NJ:IEEE, 2011
  • [17] Schindler G;Brown M;Szeliski R. City-scale location recognition. Piscataway,NJ:IEEE, 2007
  • [18] Lowe D. Distinctive image features from scale invariant keypoints. {H}International Journal of Computer Vision, 2004,2
  • [19] Vlahakis V;Ioannidis M;KarigiannisJ. Archeoguide:An augmented reality guide for archaeological sites. Computer Graphics and Applications, 2002,5
  • [20] Berg A;Zhang H;Maire M. SVM-KNN:Discriminative nearest neighbor classification for visual category recognition. Piscataway,NJ:IEEE, 2006
  • [21] Calonder M;Ozuysal M;Lepetit V. Fast keypoint recognition using random ferns. {H}IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,3
  • [22] Nister D;Stewenius H. Scalable recognition with a vocabulary tree. Piscataway,NJ:IEEE, 2006
  • [23] He Junfeng;Feng Jinyuan;Liu Xianglong. Mobile product search with bag of hash bits. New York:ACM, 2011
查看更多︾
相似文献 查看更多>>
54.198.246.164