标題：A Mobile Outdoor Augmented Reality Method Combining Deep Learning Object Detection and Spatial Relationships for Geovisualization

作者：Rao, Jinmeng;Qiao, Yanjun;Ren, Fu; Wang, Junxing; Du, Qingyun

來源出版物：SENSORS卷：17 文獻編号:1951 DOI：10.3390/s17091951 出版年：2017

摘要：The purpose of this study was to develop a robust, fast and markerless mobileaugmented reality method for registration, geovisualization and interaction in uncontrolled outdoorenvironments. We propose a lightweight deep-learning-based object detection approach for mobileor embedded devices; the vision-based detection results of this approach are combined with spatialrelationships by means of the host device’s built-in Global Positioning System receiver, InertialMeasurement Unit and magnetometer. Virtual objects generated based on geospatial informationare precisely registered in the real world, and an interaction method based on touch gestures isimplemented. The entire method is independent of the network to ensure robustness to poor signalconditions. A prototype system was developed and tested on the Wuhan University campus toevaluate the method and validate its results. The findings demonstrate that our method achieves ahigh detection accuracy, stable geovisualization results and interaction.

文獻類型：Article

語種：English

作者關鍵詞： geovisualization; outdoor augmented reality; deep learning; object detection; Inertial Measurement Unit

通訊作者地址：Du, Qingyun; School of Resources and Environmental Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, China

電子郵件地址：qydu@whu.edu.cn

地址：

[Rao, Jinmeng;Qiao, Yanjun;Ren, Fu; Wang, Junxing; Du, Qingyun]School of Resources and Environmental Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, China

[Ren, Fu;Du, Qingyun]Key Laboratory of GIS, Ministry of Education,Wuhan University, 129 Luoyu Road,Wuhan 430079, China

[Ren, Fu;Du, Qingyun]Key Laboratory of Digital Mapping and Land information Application Engineering,National Administration of Surveying, Mapping and Geoinformation, Wuhan University, 129 Luoyu Road,Wuhan 430079, China

[Du, Qingyun]Collaborative Innovation Center of Geospatial Technology, Wuhan University, 129 Luoyu Road,Wuhan 430079, China

ISSN：1424-8220

影響因子：2.677