Indoor Navigation Based on Computer Vision Utilizing Information from Patterned Surfaces

This paper presents a robust method for estimating the 6 degrees of freedom (DOF) ego-motion of a camera, which is directed at a planar surface and exploits the grid of grout lines associated with the patterned surfaces. The ego-motion estimation is robustly partitioned into a sequence of 2DOF and 4DOF estimations. The 2DOF algorithm uses the sequence of raw camera images to estimate the camera tilt angles and subsequently compensates the images such that the camera image plane is coplanar with the tiled surface. The 4DOF algorithm then takes the sequence of tilt-compensated images as the input and uses Least Squares (LS) and Kalman Filter (KF) processes to estimate the differential translation, azimuthal rotation and change in height between two consecutive image frames. The algorithm has been verified experimentally to provide robust performance while achieving an accuracy of few millimeters in the estimation of the trajectory.