UAV Detection of Sinapis arvensis Infestation in Alfalfa Plots Using Simple Vegetation Indices from Conventional Digital Cameras

Luis Fernando Sánchez-Sastre,Luis Manuel Navas-Gracia,Nuno M S Alte Da Veiga,Norlan Miguel Ruiz-Potosme,Mónica Guillén,Mª Auxiliadora Casterad,Pablo Martín-Ramos

doi:10.3390/agriengineering2020012

Abstract

Unmanned Aerial Vehicles (UAVs) offer excellent survey capabilities at low cost to provide farmers with information about the type and distribution of weeds in their fields. In this study, the problem of detecting the infestation of a typical weed (charlock mustard) in an alfalfa crop has been addressed using conventional digital cameras installed on a lightweight UAV to compare RGB-based indices with the widely used Normalized Difference Vegetation Index (NDVI) index. The simple (R−B)/(R+B) and (R−B)/(R+B+G) vegetation indices allowed one to easily discern the yellow weed from the green crop. Moreover, they avoided the potential confusion of weeds with soil observed for the NDVI index. The small overestimation detected in the weed identification when the RGB indices were used could be easily reduced by using them in conjunction with NDVI. The proposed methodology may be used in the generation of weed cover maps for alfalfa, which may then be translated into site-specific herbicide treatment maps.

Highlights

Unmanned Aerial Vehicles (UAVs) are being increasingly used for farming applications as a remote sensing platform
Images were captured on a single date (13 May, when S. arvensis was in the flowering stage) with two conventional digital cameras set on a Mikrokopter UfocamXXL8 V3 octocopter (Figure 1b): an Olympus (Shinjuku, Tokyo, Japan) Pen E-PM1 semireflex digital camera for the RGB pictures and a customized Olympus Pen E-P1 camera for the near infrared (NIR) band
The use of the Normalized Difference Vegetation Index (NDVI) index (Figure 2a) differentiated soil from vegetation and allowed one to discern yellow weeds, but these could be confused with soil, given that both were shown with dark hues

Summary

Introduction

Unmanned Aerial Vehicles (UAVs) are being increasingly used for farming applications as a remote sensing platform. Most systems based on passive remote sensing, as the ones discussed depend on the variability of spectral responses of vegetation in the visible and near infrared (NIR) regions. These responses can be used to calculate indices related to vegetation cover and chlorophyll content, which have found applications in the detection of nitrogen deficiencies [7], in the continuous monitoring of crop status [8], in disease detection [9], as vegetation phenology and ecosystem indicators [10], and in weed detection [11,12], among other areas

Methods

Results

Conclusion