DropLeaf: a precision farming smartphone application for measuring pesticide spraying methods

TL;DR

DropLeaf presents a smartphone-based image-analysis pipeline to quantify pesticide spray coverage on water-sensitive papers. By converting images through grayscale, binarization, skeletonization, and marker-based watershed segmentation, it extracts droplets and computes CA, $D_{V0.5}$, and $RS$ to assess spray quality in the field. Experimental validation shows high accuracy against controlled cards and real cards, outperforming some prior tools and approaching microscopy in precision, while also introducing fractal analysis as a potential measure of spray regularity. The tool enables portable, cost-effective pesticide-spray assessment suitable for precision agriculture and UAV sprayer evaluation, with open-access deployment on Android.

Abstract

Pesticide application has been heavily used in the cultivation of major crops, contributing to the increase of crop production over the past decades. However, their appropriate use and calibration of machines rely upon evaluation methodologies that can precisely estimate how well the pesticides' spraying covered the crops. A few strategies have been proposed in former works, yet their elevated costs and low portability do not permit their wide adoption. This work introduces and experimentally assesses a novel tool that functions over a smartphone-based mobile application, named DropLeaf - Spraying Meter. Tests performed using DropLeaf demonstrated that, notwithstanding its versatility, it can estimate the pesticide spraying with high precision. Our methodology is based on image analysis, and the assessment of spraying deposition measures is performed successfully over real and synthetic water-sensitive papers. The proposed tool can be extensively used by farmers and agronomists furnished with regular smartphones, improving the utilization of pesticides with well-being, ecological, and monetary advantages. DropLeaf can be easily used for spray drift assessment of different methods, including emerging UAV (Unmanned Aerial Vehicle) sprayers.

Figures (4)

• Figure 1: The image processing course of DropLeaf. It begins by loading an image of a water-sensitive paper. We then perform a color-space transformation to obtain a grayscale version of the image -- Step 1. Subsequently, the grayscale image is binarized to isolate the drops and to remove noise -- Step 2. Next, we apply the morphological operation of skeletonization -- Step 3, after which we apply a thresholding operation so to emphasize the drops' markers -- Step 4. Finally, we use the markers to find the contours of the drops using the marker-based watershed algorithm -- Step 5, providing the tool with a well-defined set of droplets -- visualized after Step 6.
• Figure 2: Screenshots of our fully-functional app. From left to right: home screen; photo capture of the water-sensitive-card; segmentation process; segmentation result; and computed metrics. Freely available for download on https://play.google.com/store/apps/details?id=upvision.dropleaf
• Figure 3: Control card provided by Hoechst.
• Figure 4: The plot of nine samples of water-sensitive paper. One can observe the correlation among measures of coverage area, volume, and fractal dimension. The x-axis corresponds to the number of the sample; the y-axis corresponds to the normalized output of values of the three measures.