Crop and Soil segmentation in precision agriculture applications from remotely sensed data

One of the most challenging problems in precision agriculture is the correct identification and separation of crop and soil. Thresholding techniques based on Normalized Difference Vegetation Index (NDVI) or other such similar metrics have the advantage of being simple, easy to read transformations of the data packed with useful information. Obvious difficulties arise when crop/tree and soil have similar spectral responses as in case of grass filled areas in vineyards. In this case grass and canopy are close in terms of NDVI values and thresholding techniques will generally fail. In this paper we present the FANSCAN algorithm to segment crops and/or tree objects over soil by using high-resolution images starting from Digital Surface Models that are usually available when the data have been acquired by using unmanned platforms. The FANSCAN algorithm uses vector or radial raster scanning across the image to increase the frequency resolution of the scanned data. This approach could be used to segment crops and/or tree objects over soil that is a mandatory task in precision agriculture applications.