Adaptive Model-Based Visual Stabilization of Image Sequences Using Feedback

Visual stabilization proposed in this paper compensates changes of the scene caused by motion and deformation of an observed object. This is of high importance in computer-assisted beating heart surgery, where the views of the beating heart should be stabilized. The proposed model-based method defines visual stabilization as a transformation of the current image sequence to a stabilized image sequence. This transformation incorporates physical model of the observed object and model of the measurement process. In contrast to standard approaches, the quality of the visual stabilization is continuously evaluated and improved in two aspects. On the one hand, discretization errors are reduced. On the other hand, the parameters of the underlying models are adjusted. The performance of the proposed method is evaluated in an experiment with a pressure-regulated artificial heart. Compared with standard methods, the model-based method provides higher accuracy, which is additionally improved by a feedback mechanism.