Simultaneous Image Segmentation and 3D Plane Fitting for RGB-D Sensors - An Iterative Framework

Abstract

In this paper, we segment RGB-D sensor (e.g. Microsoft Kinect camera) images into 3D planar surfaces. We initialize a set of plane equations based solely from the depth (point cloud) information. We then iteratively refine the pixel-to-plane assignment and plane equations. During this process, the number of planes are also reduced by merging adjacent local planes with similar orientations. For the pixel-to-plane assignment, we treat the image as a Markov Random Field (MRF), and solve the association problem using graph-based global energy minimization. We design the energy terms to encapsulate both appearance cues from the RGB (color) channels and shape cues from the D (depth) channel. Experiments show that the use of both appearance and geometry information significantly improves the segmentation quality, especially so at genuine plane edges and plane intersections. As a byproduct, the framework also automatically fills in missing depth information.

Cite

Text

Guan et al. "Simultaneous Image Segmentation and 3D Plane Fitting for RGB-D Sensors - An Iterative Framework." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6238914

Markdown

[Guan et al. "Simultaneous Image Segmentation and 3D Plane Fitting for RGB-D Sensors - An Iterative Framework." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/guan2012cvprw-simultaneous/) doi:10.1109/CVPRW.2012.6238914

BibTeX

@inproceedings{guan2012cvprw-simultaneous,
  title     = {{Simultaneous Image Segmentation and 3D Plane Fitting for RGB-D Sensors - An Iterative Framework}},
  author    = {Guan, Li and Yu, Ting and Tu, Peter H. and Lim, Ser-Nam},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2012},
  pages     = {49-56},
  doi       = {10.1109/CVPRW.2012.6238914},
  url       = {https://mlanthology.org/cvprw/2012/guan2012cvprw-simultaneous/}
}