Automatic 3D plant reconstruction from photographies, segmentation and classification of leaves and internodes using clustering

  • Thiago Teixeira Santos Embrapa Agricultural Informatics
  • Julio Akira Ueda Embrapa Agricultural Informatics
Keywords: 3d plant models, image-based reconstruction, multiple view stereo, structure segmentation


A stereo approach for 3D plant modelling is presented. Using only a set of photographies, the method produces a dense 3D point cloud sampling the plant surface. Clustering automatically segments the plant structure in meaningful parts, which are classified in elements of interest as leaves and internodes. Measurements can be computed for each element, as area or surface normals.

1B Reconstructing and observing plant structure