Simultaneous pose estimation and patient-specific model reconstruction from single image using maximum penalized likelihood estimation (MPLE)
作者：
Highlights：
• Formulate the simultaneous pose estimation and surface model reconstruction as a MPLE.
• Solve the MPLE problem effectively by embedding the ECM in the PSO.
• Simultaneously optimize the pose and deformation rather than sequentially.
• Model oriented object contour as a mixture of von Mises–Fisher Gaussian distributions.
• Use probabilities instead of paired correspondences on contours with no delineation.
摘要
Highlights•Formulate the simultaneous pose estimation and surface model reconstruction as a MPLE.•Solve the MPLE problem effectively by embedding the ECM in the PSO.•Simultaneously optimize the pose and deformation rather than sequentially.•Model oriented object contour as a mixture of von Mises–Fisher Gaussian distributions.•Use probabilities instead of paired correspondences on contours with no delineation.
论文关键词：Pose estimation,3D–2D deformable registration,Surface reconstruction,Maximum penalized likelihood estimation (MPLE),Patient-specific model,Image-guided intervention
论文评审过程：Received 5 October 2015, Revised 2 February 2016, Accepted 19 March 2016, Available online 2 April 2016, Version of Record 6 May 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.03.025
