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.

Le relazioni