GFkuts: a novel multispectral image segmentation method applied to precision agriculture

Image segmentation enables the precise extraction of several crop traits from multispectral aerial imagery. This paper presents a novel segmentation technique called GFKuts. The method integrates a graph-based optimization algorithm with a k-means Monte Carlo approach. Here, we evaluate the performance of the proposed method against other approaches for image segmentation found in the specialized literature. Results report an improvement on the F1-score accuracy in terms of crop canopy segmentation. These findings are promising for the precise calculation of vegetative indices and other crop trait features.