Automatic tracking of region of interest in neurosurgical video

In this paper, we present a new method to automatically detect a region of interest (ROI) within video frames for remote monitoring of neurosurgery. This method is based on an object tracking technique combined with an automatic shape analysis. By defining the ROI, this method produces a smooth and convex emphasis region within which surgical procedures are performed. A large bandwidth budget is assigned within the ROI to archive high-fidelity Internet transmission. Outside the ROI, a small bandwidth budget is allocated to efficiently utilize the bandwidth resource in Internet connection.