Joint segmentation of color and depth data based on splitting and merging driven by surface fitting
作者：
Highlights：
• We introduce a RGBD segmentation scheme based on splitting and merging.
• The scene is recursively split in two parts with normalized cuts spectral clustering.
• Then a recursive merging stage recombines segments belonging to the same object.
• A NURBS model is fitted on the computed segments at each step.
• The fitting accuracy is used to understand if a segment represents a single object.
摘要
•We introduce a RGBD segmentation scheme based on splitting and merging.•The scene is recursively split in two parts with normalized cuts spectral clustering.•Then a recursive merging stage recombines segments belonging to the same object.•A NURBS model is fitted on the computed segments at each step.•The fitting accuracy is used to understand if a segment represents a single object.
论文关键词：Segmentation,Depth,Spectral clustering,Kinect,NURBS
论文评审过程：Received 10 June 2016, Revised 19 June 2017, Accepted 8 December 2017, Available online 14 December 2017, Version of Record 29 December 2017.
论文官网地址：https://doi.org/10.1016/j.imavis.2017.12.004
