Point Cloud Segmentation to Approximately Convex Surfaces for Fruit Recognition

Abstract

A fruit recognition approach based on segmenting the point cloud acquired by a 3D camera into approximately convex surfaces is considered. A segmentation approach which transforms a depth image into a triangular mesh and then segments this mesh into approximately convex segments is applied to depth images of fruits on trees. An analysis of the results obtained by this approach is performed with the intention to determine how successful the studied method is in detecting fruit as separate objects in a point cloud. The reported analysis gives a valuable insight into the potential applicability of the tested methodology in the preprocessing stage of a fruit recognition system as well as its drawbacks.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2014.0015

https://doi.org/10.20532/ccvw.2014.0015

BibTeX

@InProceedings{10.20532/ccvw.2014.0015,
  author =       {Robert Cupec and Damir Filko and Ivan Vidovi{\' c}
                  and Nyarko, Emmanuel Karlo and {\v Z}eljko Hocenski},
  title =        {Point Cloud Segmentation to Approximatelly Convex
                  Surfaces for Fruit Recognition},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 2},
  pages =        {56-61},
  year =         2014,
  editor =       {Lon{\v c}ari{\' c}, Sven and Suba{\v s}i{\' c},
                  Marko},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {A fruit recognition approach based on segmenting the
                  point cloud acquired by a 3D camera into
                  approximately convex surfaces is considered. A
                  segmentation approach which transforms a depth image
                  into a triangular mesh and then segments this mesh
                  into approximately convex segments is applied to
                  depth images of fruits on trees. An analysis of the
                  results obtained by this approach is performed with
                  the intention to determine how successful the
                  studied method is in detecting fruit as separate
                  objects in a point cloud. The reported analysis
                  gives a valuable insight into the potential
                  applicability of the tested methodology in the
                  preprocessing stage of a fruit recognition system as
                  well as its drawbacks.},
  doi =          {10.20532/ccvw.2014.0015},
  url =          {https://doi.org/10.20532/ccvw.2014.0015}
}