Title :
A vision system for 2D real-time vector motion estimation of a random-sized moving pattern
Author :
Nicola, M. De ; Bertaso, A. ; Massari, N. ; Gottardi, M.
Author_Institution :
Div. of Microsyst., Fondazione B. Kessler, Trento
Abstract :
A 2D motion detection and estimation vision system is here presented. It performs real-time template matching on edges extracted from successive frames, acquired with an addressable CMOS camera. The x-y motion vector components are estimated counting the number of matched edges moving over less than one pixel within two subsequent frames. The algorithm has been implemented on an FPGA and uses a 20 times 20 pixel binary- image. The system computes up to 350 motion-vector-estimation/s on a random-sized pattern. The computation rate is mainly limited by the frame rate of the camera. The system was linked to a PC through an USB interface.
Keywords :
CMOS image sensors; computer vision; edge detection; field programmable gate arrays; image matching; motion estimation; 2D motion detection; 2D real-time vector motion estimation; addressable CMOS camera; edge extraction; field programmable gate arrays; random-sized moving pattern estimation; real-time template matching; vision system; CMOS image sensors; Cameras; Field programmable gate arrays; Image edge detection; Machine vision; Motion detection; Motion estimation; Pixel; Real time systems; Universal Serial Bus; CMOS image sensors; Motion vector estimation; image processing;
Conference_Titel :
Advanced Motion Control, 2008. AMC '08. 10th IEEE International Workshop on
Conference_Location :
Trento
Print_ISBN :
978-1-4244-1702-5
Electronic_ISBN :
978-1-4244-1703-2
DOI :
10.1109/AMC.2008.4516059
