Vision based micromanipulation using features: a multiple view approach

In this paper, we describe a multiple view visual servo system using a perspective view camera and a microscope that controls a 3DOF stage so that the interested area can be positioned precisely as desired under the microscope. First, we extend the existing visual servo techniques in micromanipulation to the case of eye-to-hand multiple view vision sensors (one conventional CCD camera forms the perspective view, one microscope forms the microview) working in complimentary. Second, the image processing and homography estimation based partitioned image based visual servo approach is proposed to derive the control law of the stage based on planar features acquired from the scene.