Indoor navigation with smartphone-based visual SLAM and Bluetooth-connected wheel-robot

A smartphone-based positioning system suitable for indoor robot application is developed in this research by integrating image and other sensors on a smartphone with wheel odometer feedback from a Bluetooth-connected robot vehicle. WiFi signal, inertial sensors, and CMOS sensor in the smartphone were considered to provide measurements for positioning calculations. The real-time performances of SIFT, SURF, and ORB image feature detection and tracking algorithms are compared in the smartphone and ORB was chosen for implementation. Experimental result of Visual SLAM positioning is presented together with state convergence analysis.

[1]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[3]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[4]  Javier Civera,et al.  Inverse Depth Parametrization for Monocular SLAM , 2008, IEEE Transactions on Robotics.

[5]  Chadly Marouane,et al.  Indoor positioning using smartphone camera , 2011, 2011 International Conference on Indoor Positioning and Indoor Navigation.

[6]  Andreas Möller,et al.  Scale-preserving long-term visual odometry for indoor navigation , 2012, 2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[7]  Karol Matusiak,et al.  Comparison of Key Point Detectors in SIFT Implementation for Mobile Devices , 2012, ICCVG.

[8]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.