Title :
Robotic platform for real-time tracking of a single fast swimming bacterium
Author :
Tremblay, Charles C. ; Jean, Joscelyn ; Marchand, Laurence ; Turki, Ali ; Chouinard-Gaouette, Philippe ; Brousseau, Mathieu ; Mohammadi, Mahmood ; Martel, Sylvain
Author_Institution :
Dept. of Comput. & Software Eng., Ecole Polytech. de Montreal (EPM), Montréal, QC, Canada
Abstract :
In this paper we present a hardware architecture with software implementation able to track free swimming single 2μm in diameter MC-1 bacterium. The computer vision system operates at up to 77 fps at full speed and up to 24 fps when recording full 512×512 pixels frame from coupled-charge device (CCD) array. Closed-loop control with lock-in tracking is achieved using the Otsu Segmentation Method (OSM) with a cubic spline model-based predictive algorithm. Using the system, speed distribution of MC-1 cells has been recorded showing a m ean speed of 200μm/s. Tracking is demonstrated over a range of a few millimeters during 30 sec.
Keywords :
CCD image sensors; biological techniques; biology computing; closed loop systems; computer vision; image segmentation; microorganisms; optical control; optical microscopy; robots; target tracking; MC-1 bacterium; Otsu segmentation method; charge coupled device array; closed loop control; computer vision system; cubic spline model based predictive algorithm; fast swimming bacterium real time tracking; hardware architecture; lock in tracking; picture size 512 pixel; robotic platform; size 2 mum; software implementation; velocity 200 mum/s; Charge coupled devices; Image segmentation; Magnetic recording; Magnetic resonance imaging; Microorganisms; Microscopy; Software; Cell tracking; Otsu Method; computer vision; cubic spline prediction; real-time tracking;
Conference_Titel :
Optomechatronic Technologies (ISOT), 2010 International Symposium on
Conference_Location :
Toronto, ON
Print_ISBN :
978-1-4244-7684-8
DOI :
10.1109/ISOT.2010.5687357
