Landmark Finding Algorithms for Indoor Autonomous Mobile Robot Localization

Abstract

This contribution is oriented to ways of computer vision algorithms for mobile robot localization in internal and external agricultural environment.The main aim of this work was to design, create, verify and evaluate speed and functionality of computer vision localization algorithm.An input colour camera data and depth data were captured by MS® Kinect sensor that was mounted on 6-wheel-drive mobile robot chassis.The design of the localization algorithm was focused to the most significant blobs and points (landmarks) on the colour picture.Actual coordinates of autonomous mobile robot were calculated out from measured distances (depth sensor) and calculated angles (RGB camera) with respect to landmark points.Time measurement script was used to compare the speed of landmark finding algorithm for localization in case of one and more landmarks on picture.The main source code was written in MS Visual studio C# programming language with Microsoft.Kinect.1.7.dll on Windows based PC.Algorithms described in this article were created for a future development of an autonomous agronomical mobile robot localization and control.