Textural analysis of soil images to quantify and characterize the spatial variation of soil properties using a real-time soil sensor

Abstract

The primary aim of this work was to predict soil moisture content and soil organic matter using soil image texture statistics. Co-occurrence method texture statistics were used to characterize Andisol soils to extend the possibility of using RGB color space in representing composite soil color. Four co-occurrence method textural features; angular second moment (ASM), contrast (CON), correlation (COR) and inverse difference moment (IDM) calculated from generalized matrix for image texture representation were used to describe soil moisture content variation under laboratory conditions. It was found that CON and COR had negative responses to moisture content (MC) and ASM had positive response to MC. The same were also observed in direct captured field soil images in terms of textural indices against MC and soil organic matter (SOM). The correlations were significant for ASM and COR in fertilizer and combined (fertilizer-manure) plots and insignificant in manure plots. To relate sub-surface image textural indices and soil properties for individual years, stepwise multiple linear regression (SMLR) and supervised feed-forward neural networks (NN) were investigated in an attempt to provide minimal prediction errors. The improvements achieved by NN with minimal prediction errors were better than SMLR in different years. It was assumed that several years of data sets with a much larger number of observations could be used to differentiate fundamental soil properties.

Microscope-based computer vision to characterize soil texture and soil organic matter

“…However, almost the highest resolution satellite can provide a minimum resolution of 10 m/square pixel (http://carpe.umd.edu/geospatial/ satellite_imagery_resources.php) and is not a feasible resolution to comprehend about the soil particle sizes. In contrast, Roy, Shibusawa, and Okayama (2006) used the GLCM method for texture estimation from images collected using Toshiba IK-UM42 camera that captured image with a resolution of 7.2 pixels/mm or about 142.8 um/square pixel, not enough resolution to comprehend soil particle sizes.…”

Estimating soil organic carbon from soil reflectance: a review

“…Thus, uniform treatment of the soil will result in zones within a field that are either over-or under-treated (Roy et al 2006). The quantification of soil heterogeneity is an obstacle to the widespread adoption of precision agriculture (Franzen et al 2000).…”

“…Recent research has suggested that reflectances in certain spectral bands have been correlated with soil properties and could provide inexpensive predictions of soil physical, chemical and biological properties (Ben-Dor and Banin 1995; Reeves et al 2000;Dunn et al 2002;Daniel et al 2004;Roy et al 2006;Stamatiadis et al 2005;Francis and Schepers 1997;Pocknee et al 1996;Ehsani et al 1999). As SOC increases, the soil appears darker, and vice versa (Fig.…”

Characterization of Water Infiltration and Redistribution for Two‐Dimensional Soil Profiles by Moment Analyses

“…Persson (2005) showed that a soil's surface water content could be detected by photographing the soil and analyzing it with visible wavelengths using characteristics such as hue and color brightness. Roy et al (2006) determined water‐content values from images taken in the field and analyzed them by image statistics methods; following this, they built a neural network for the prediction of soil water and organic matter content from these image characteristics. Another practical use of image analysis in soil science is the comparison of water distribution in wettable versus water‐repellant soils based on gray‐scale images produced by a monochromatic camera (Wallach and Jortzick, 2008).…”