Deep Segmentation of Point Clouds of Wheat

Morteza Ghahremani, Kevin Williams, Fiona M K Corke, Bernard Tiddeman, YONGHUAI LIU, John Doonan

Research output: Contribution to journalArticle (journal)peer-review

21 Citations (Scopus)
197 Downloads (Pure)


The 3D analysis of plants has become increasingly effective in modeling the relative structure of organs and other traits of interest. In this paper, we introduce a novel pattern-based deep neural network, Pattern-Net, for segmentation of point clouds of wheat. This study is the first to segment the point clouds of wheat into defined organs and to analyse their traits directly in 3D space.
Point clouds have no regular grid and thus their segmentation is challenging. Pattern-Net creates a dynamic link among neighbours to seek stable patterns from a 3D point set across several levels of abstraction using the K-nearest neighbour algorithm. To this end, different layers are connected to each other to create complex patterns from the simple ones, strengthen dynamic link propagation, alleviate the vanishing-gradient problem, encourage link reuse and substantially reduce the number of parameters. The proposed deep network is capable of analysing and decomposing unstructured complex point clouds into semantically meaningful parts. Experiments on a wheat dataset verify the effectiveness of our approach for segmentation of wheat in 3D space.
Original languageEnglish
Article number608732
JournalFrontiers in Plant Science
Early online date24 Mar 2021
Publication statusPublished - 24 Mar 2021


  • 3D segmentation
  • point cloud
  • convolutional neural network (CNN)
  • stable pattern
  • wheat
  • deep learning
  • 3D analysis
  • convolutional neural network
  • pattern
  • segmentation

Research Centres

  • Data and Complex Systems Research Centre
  • Data Science STEM Research Centre

Research Groups

  • Visual Computing Lab


Dive into the research topics of 'Deep Segmentation of Point Clouds of Wheat'. Together they form a unique fingerprint.

Cite this