Determining shape of strawberry crops with spherical harmonics

Abstract

Shape descriptor and shape reconstruction are two challenges found in computer vision and graphics as well as in perception for robotics, especially for some fields such as agri- robotics (robotics for agriculture). Being able to offer a reliable description of shape that can also translate directly into an high fidelity model of the shape, would be of high importance for a lot of applications such as phenotyping or agronomy. In this paper we report on our work on using spherical harmonics to offer efficient representation of strawberry shapes and we validate them by reconstructing the fruits. The reconstruction achieve extremely close results to the original shape (less than 1% deviation) and the representation reduce the complexity and improve compactness by a large factor (minimum 100).