Model-based Segmentation of 3D Point Clouds for Phenotyping Sunflower Plants

William Gélard, Michel Devy, Ariane Herbulot, Philippe Burger

2017 · 37 citations · 20 references

Concepts

Abstract

This article presents a model-based segmentation method applied to 3D data acquired on sunflower plants. Our\nobjective is the quantification of the plant growth using observations made automatically from sensors moved\naround plants. Here, acquisitions are made on isolated plants: a 3D point cloud is computed using Structure\nfrom Motion with RGB images acquired all around a plant. Then the proposed method is applied in order to\nsegment and label the plant leaves, i.e. to split up the point cloud in regions corresponding to plant organs:\nstem, petioles, and leaves. Every leaf is then reconstructed with NURBS and its area is computed from\nthe triangular mesh. Our segmentation method is validated comparing these areas with the ones measured\nmanually using a planimeter: it is shown that differences between automatic and manual measurements are\nless than 10%. The present results open interesting perspectives in direction of high-throughput sunflower\nphenotyping

References

20