Indoor Localization for the Visually Impaired Using a 3D Sensor

An indoor localization system offers a significant assistance to the visually impaired in their daily lives by helping them localize themselves and further navigate an indoor environment. RGB-D sensor (e.g. Google Tango Tablet) is able to provide three-dimensional information of the environment around the sensor, which can be used for localization and navigation. In this paper, we propose a system that uses the Tango Tablet to first pre-build an 3D model of an indoor environment, and then utilize the newly captured RGB-D information and an Iterative Closest Point (ICP) algorithm to calculate the device’s (i.e., user’s) location and orientation corresponding to each RGB-D image. Voice feedback is provided to the users via text-to-speech. The system has three components: an environmental modeling and optimization module, a pose estimation module, and a GUI module. Experiments have been carried out in real indoor environments to test the performance of the system in terms of both time and accuracy.

[1]  Manolis I. A. Lourakis,et al.  SBA: A software package for generic sparse bundle adjustment , 2009, TOMS.

[2]  Jan-Michael Frahm,et al.  From structure-from-motion point clouds to fast location recognition , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jizhong Xiao,et al.  Multi-volume occupancy grids: An efficient probabilistic 3D mapping model for micro aerial vehicles , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Tao Chen,et al.  Landmark recognition with compact BoW histogram and ensemble ELM , 2015, Multimedia Tools and Applications.

[5]  Roberto Manduchi,et al.  Mobile Vision as Assistive Technology for the Blind: An Experimental Study , 2012, ICCHP.

[6]  Giovanni Maria Farinella,et al.  Representing scenes for real-time context classification on mobile devices , 2015, Pattern Recognit..

[7]  Niko Sünderhauf,et al.  On the performance of ConvNet features for place recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Torsten Sattler,et al.  Camera Pose Voting for Large-Scale Image-Based Localization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).