2019/12/15 by Michael R. Walker, Walker, Michael R.
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #FOS: Computer and information sciences #Image and Object Detection Techniques #Robotics (cs.RO) #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.1912.06981
openalex publication_date 2019/12/15 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Acquiring an anatomical map from position data is important for medical\napplications where catheters interact with soft tissues. To improve autonomous\nnavigation in these settings, we require information beyond nonparametric maps\ntypically available. We present an algorithm for local surface approximation\nfrom position data with automatic surface order selection. The traditional\nsurface fitting objective function is derived from a Bayesian perspective.\nPosterior probabilities from the occupancy map are incorporated as weights on\npoints selected for surface fitting. Our novel iterative algorithm incorporates\nsurface order selection using the Bayesian information criterion. Simulations\ndemonstrate the ability to automatically select surface order consistent with\nthe latent surface in the presence of noise. Results on human procedure data\nare also presented.\n