In microscope applications, many of the imaging and vision techniques that are generally applied in industrial macro-environments are not suitable because of several constraints imposed by the micro-environment. For example, limited depth of field and short focal length of optical microscopes do not allow the use of stereo-optics and disparity estimators for building depth maps.
In a previous research project, we have used depth information concealed in acquired microscope images to achieve real-time object recognition and tracking. By using focus stacks as models, it was possible to provide real-time object recognition of multiple micro-objects in up to 4 degrees-of-freedom. The micro-objects were not required to stay at a fixed distance to the camera anymore. Novel automated procedures in biology and micro-technology are thus conceivable.