Title :
Simple algorithm for robot localization by using mathematical correlation of image pixels with physical data
Author :
Khan, Talha Masood ; Choudhry, M.A.
Author_Institution :
Univ. of Eng. & Technol., Taxila
Abstract :
The Robot localization is an important problem in the field of machine vision. In this paper, we present an algorithm to find out the moving robot pose and its orientation in a work-shop indoor environment. The algorithm is tested and verified for a mobile robot with various shapes and sizes of objects in the work environment. Camera calibration and Image geometric transformation were performed prior to the application of the algorithm. A simple mathematical correlation was used to locate a robot on the work-shop floor. Image Pixel indexes were used in conjunction with physical data to successfully locates the robot on the ground plane.
Keywords :
SLAM (robots); correlation methods; image matching; mobile robots; robot vision; camera calibration; image geometric transformation; image pixels; machine vision; mathematical correlation; mobile robot; moving robot pose; physical data; robot localization; template matching; work-shop indoor environment; Calibration; Cameras; Indoor environments; Machine vision; Mobile robots; Pixel; Robot localization; Robot vision systems; Shape; Testing; Robot localization; camera calibration; geometric transformations; template matching;
Conference_Titel :
Control, Automation and Systems, 2007. ICCAS '07. International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-89-950038-6-2
Electronic_ISBN :
978-89-950038-6-2
DOI :
10.1109/ICCAS.2007.4406630