English

Graph based Dynamic Segmentation of Generic Objects in 3D

Computer Vision and Pattern Recognition 2019-04-19 v1

Abstract

We propose a novel 3D segmentation method for RBGD stream data to deal with 3D object segmentation task in a generic scenario with frequent object interactions. It mainly contributes in two aspects, while being generic and not requiring initialization: firstly, a novel tree structure representation for the point cloud of the scene is proposed. Then, a dynamic manangement mechanism for connected component splits and merges exploits the tree structure representation.

Keywords

Cite

@article{arxiv.1904.08518,
  title  = {Graph based Dynamic Segmentation of Generic Objects in 3D},
  author = {Xiao Lin and Josep R. Casas and Montse Pardàs},
  journal= {arXiv preprint arXiv:1904.08518},
  year   = {2019}
}

Comments

CVPR 2016 workshops - SUNw: Scene Understanding Workshop 2016 See workshop listing in http://cvpr2016.thecvf.com/program/workshops and paper listing in http://sunw.csail.mit.edu/2016/posters.html)

R2 v1 2026-06-23T08:43:16.841Z