Green-gradient based canopy segmentation: A multipurpose image mining model with potential use in crop phenotyping and canopy studies

Abstract

Vegetation canopies may be characterized based on how they interact with light. Efficient quantification of the sophisticated shading patterns inside the 3D vegetation canopies may improve our understanding of canopy functions and status, which is possible now more than ever, thanks to the high-throughput phenotyping (HTP) platforms. In order to evaluate the option of developing an image mining technique based on relative variations in RGB triplets (green-gradient based canopy segmentation method, or GSM) for HTP purposes and canopy assessments, an archive of ground-based nadir images of heterogeneous wheat canopies (cultivar mixtures) were analyzed. The images were taken from experimental plots of a twoyear field experiment conducted during 2014-15 and 2015-16 growing seasons at the School of Agriculture, Shiraz University, Iran. In GSM, the vegetation pixels were categorized into the maximum possible number of 255 groups based on their green levels. Subsequently, mean red and mean blue levels of each group were calculated and plotted against the green levels. It was observed that the two sets of red and blue mean values yielded two smooth upward exponential shaped curves, with the blue one having a higher degree of curvature. It is suggested that such graph (i.e. GSM graph) could be readily utilized for identifying and characterizing canopies, e.g. in the form of one or two image-derived equation(s). Moreover,