Cell detection and tracking for micromanipulation vision system of cell-operation robot

Abstract

The paper discusses cell detection and tracking in a microscope scene for a cell-operation robot. An approach integrating a morphological operator and Bayesian estimation technique is used for cell detection and tracking. One of the problems in the implementation is difficulty in obtaining accurate information of cells. We introduce classification criteria which rely on both shape and texture information of the cell to get fine results, and we present geometric constraints incorporating a nonlinear diffusion process to reduce the drift of points during the tracking procedure. A preliminary test is conducted on the system. Experimental results show the effectiveness of the proposed methods.