PROJECT TITLE :

6-DOF Pose Estimation of a Robotic Navigation Aid by Tracking Visual and Geometric Features

ABSTRACT:

This paper presents a half-dozen-DOF create estimation (PE) method for a robotic navigation aid (RNA) for the visually impaired. The RNA uses one 3D camera for PE and object detection. The proposed technique processes the camera's intensity and range data to estimates the camera's egomotion that is then used by an extended Kalman filter (EKF) as the motion model to track a set of visual options for PE. A RANSAC process is used within the EKF to identify inliers from the visual feature correspondences between 2 image frames. Solely the inliers are used to update the EKF's state. The EKF integrates the egomotion into the camera's pose in the planet coordinate system. To retain the EKF's consistency, the space between the camera and the ground plane (extracted from the vary data) is employed by the EKF as the observation of the camera's z coordinate. Experimental results demonstrate that the proposed technique ends up in accurate cause estimates for positioning the RNA in indoor environments. Primarily based on the PE methodology, a wayfinding system is developed for localization of the RNA in a very home environment. The system uses the estimated cause and the floorplan to locate the RNA user in the home environment and announces the points of interest and navigational commands to the user through a speech interface.