Fast Generalized Chan-Vese Model for plant/soil segmentation to estimate percentage of ground cover in agricultural images

摘要

* color space, then a level set method, capable of dealing with topology changes, is used to segment the whole image. Finally, a functional is optimized via a “sweeping” algorithm for fast convergence. Percentage of Ground Cover (PGC) is then easily estimated from the segmented image. Several experiments have been conducted to validate the proposed algorithm.