Portable 3D visual sensor based indoor localization on mobile device

Smart mobile device and consumer level 3D visual sensor are becoming very cheap and widely accessible in people's daily lives. Visual information based indoor localization is getting more and more attention in the computer vision research community to achieve real time and precise localization result. In this paper, we present a 6-degree-of-freedom (6-DoF) pose estimation using a portable 3D visual sensor mounted on a mobile device. A detailed 3D model and a WiFi received signal strength model of the indoor environment are constructed in the offline training phase. During the online localization, we first use WiFi signals to locate the device in a 3D sub model. The initial pose is calculated through feature matching between the online captured 2D image and the key frame images used to build the 3D model. Then we employ iterative closest point (ICP) algorithm to estimate the rigid transform between online captured 3D point cloud and local 3D point cloud. The 6-DOF pose estimation is further refined by random sample consensus (RANSAC) algorithm. We implement the system on iOS platform and the experiments carried out in an indoor environment shows promising result of our approach. To the best of our knowledge, this is the first portable 3D visual sensor based indoor localization system on mobile device.