Sensor-Aware Recognition and Tracking for Wide-Area Augmented Reality on Mobile Phones

Sensors

Jing Chen²  Ruochen Cao¹  Yongtian Wang²  Fabrizio Lamberti³  Andrea Sanna³ 

[1] School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China;;School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China

关键词: mobile augmented reality;    sensor-aware scene recognition;    VLAD;    sensor fusion;   

DOI  :  10.3390/s151229847

来源: mdpi

【 摘 要 】

Wide-area registration in outdoor environments on mobile phones is a challenging task in mobile augmented reality fields. We present a sensor-aware large-scale outdoor augmented reality system for recognition and tracking on mobile phones. GPS and gravity information is used to improve the VLAD performance for recognition. A kind of sensor-aware VLAD algorithm, which is self-adaptive to different scale scenes, is utilized to recognize complex scenes. Considering vision-based registration algorithms are too fragile and tend to drift, data coming from inertial sensors and vision are fused together by an extended Kalman filter (EKF) to achieve considerable improvements in tracking stability and robustness. Experimental results show that our method greatly enhances the recognition rate and eliminates the tracking jitters.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.