Segmentation of tree seedling point clouds into elementary units

Franck Hétroy-Wheeler (1) , Eric Casella (2) , Dobrina Boltcheva (3)

1 MORPHEO - Capture and Analysis of Shapes in Motion
2 Centre for Sustainable Forestry and Climate Change
3 ALICE - Geometry and Lighting

This paper describes a new semi-automatic method to cluster TLS data into meaningful sets of points to extract plant components. The approach is designed for small plants with distinguishable branches and leaves, such as tree seedlings. It first creates a graph by connecting each point to its most relevant neighbours, then embeds the graph into a spectral space, and finally segments the embedding into clusters of points. The process can then be iterated on each cluster separately. The main idea underlying the approach is that the spectral embedding of the graph aligns the points along the shape's principal directions. A quantitative evaluation of the segmentation accuracy, as well as of leaf area estimates, is provided on a poplar seedling mock-up. It shows that the segmentation is robust with false positive and false negative rates around 1%. Qualitative results on four contrasting plant species with three different scan resolution levels each are also shown.

Mots clés: 3D point cloud; tLiDAR; terrestrial laser scanning; tree seedling; spectral clustering; segmentation

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Sciences de l'environnement

Franck Hétroy-Wheeler, Eric Casella, Dobrina Boltcheva. Segmentation of tree seedling point clouds into elementary units. International Journal of Remote Sensing, 2016, 37 (13), pp.2881-2907. ⟨10.1080/01431161.2016.1190988⟩. ⟨hal-01285419⟩