BLOB-Based AOMs: A Method for the Extraction of Crop Data from Aerial Images of Cotton

Abstract

The use of aerial imagery in agriculture is increasing. Improvements in unmanned aerial systems (UASs) and the hardware and software used to analyze imagery are presenting new options for agricultural studies. One of the challenges associated with improving crop performance under water deficit conditions is the increased variability in the growth and development inherent in low water settings. The nature of plant growth and development under water deficits makes it difficult to monitor the response to environmental changes. Small field and plot-level experiments are often variable enough that averages of seasonal crop characteristics may be of limited value to the researcher. This variability leads to a desire to resolve fields on finer temporal and spatial scales. While UAS imagery provides an ability to monitor the crop on a useful temporal scale, the spatial scale is still difficult to resolve. In this study, an automated computer software framework was developed to facilitate resolving field and plot-level crop imagery to finer spatial resolutions. The method uses a Binary Large Object (BLOB)-based algorithm to automate the generation of areas of measurement (AOMs) as a tool for crop analysis. The use of the BLOB-based system is demonstrated in the analysis of plots of cotton grown in Lubbock, Texas, during the summer of 2018. The method allowed the creation and analysis of 1133 AOMs from the plots and the extraction of agronomic data that described plant growth and development.

Yield prediction in a peanut breeding program using remote sensing data and machine learning algorithms

“…The orthomosaics were aligned using a series of GCPs in the imagery that anchored them geographically, reducing the marginal error between scenes to ±5 cm. This precision allows for sequential time series-based image extractions using areas of measurement (AOMs) over plot-level image data ( Young et al., 2020 ). These AOMs covered the plot area of the peanuts planted and had some slight border between the plots.…”

“…The flights were conducted under different lighting conditions, and the CLAHE method helped to correct the white balance in the images, particularly if the brightness varied across a single image. The imagery was then analyzed using the binary image masking threshold described by Young et al (2020) and was used to separate the plants from the soil background. The binary image masking method was combined with the HSV (Hue, Saturation, Value) image threshold method to improve peanut plant masking.…”

Continuity Detection Method in Binary Image Signal

“…The analysed continuous area is represented by a group of identical values, respectively in the binary image group of pixels with a true logical value, which is progressively expanded by a local discrete convolution g (x, y) given by (1), where h (m, n) defines the local mask of the size of 3×3 and f (x-m, y-n) is the local area from the original binary image…”

“…The BLOB method is widely used in image processing [1]- [3]. It is used primarily for the analysis of binary matrices, such as part of the Optical Character Recognition (OCR) algorithm [4], as algorithms for error detection, quality control or counting patterns in the image or many other image analysis algorithms [5], [6].…”