Real-time Kernel-based Multiple Target Tracking for Robotic Beating Heart Surgery

Performing surgery on the beating heart has significant advantages for the patient compared to traditional heart surgery on the stopped heart. A remote-controlled robot can be used to automatically cancel out the movement of the beating heart. This necessitates precise tracking of the heart surface. For this purpose, we track 24 identical artificial markers placed on the heart. This creates a data association problem, because it is not known which measurement was obtained from which marker. To solve this problem, we apply a multiple target tracking method based on a symmetric kernel transformation. This method allows efficient handling of the data association problem even for a reasonably large number of targets. We demonstrate how to implement this method efficiently. The proposed approach is evaluated on in-vivo data of a real beating heart surgery performed on a porcine beating heart.