Discriminating crops/weeds in an upland rice field from UAV images with the SLIC-RF algorithm

Abstract

In this study, we propose a method for discriminating crops/weeds in upland rice fields using a commercial unmanned aerial vehicles (UAVs) and red-green-blue (RGB) cameras with the simple linear iterative clustering (SLIC) algorithm and random forest (RF) classifier. In the SLIC-RF algorithm, we evaluated different combinations of input features: three color spaces (RGB, hue-saturation-brightness [HSV], CIE-L*a*b), canopy height model (CHM), spatial texture (Texture) and four vegetation indices (VIs) (excess green [ExG], excess red [ExR], green-red vegetation index [GRVI] and color index of vegetation extraction [CIVE]). Among the color spaces, the HSV-based SLIC-RF model showed the best performance with the highest out-of-bag (OOB) accuracy (0.904). The classification accuracy was improved by the combination of HSV with CHM, Texture, ExG, or CIVE. The highest OOB accuracy (0.915) was obtained from the HSV+Texture combination. The greatest errors from the confusion matrix occurred in the classification between crops and weeds, while soil could be classified with a very high accuracy. These results suggest that with the SLIC-RF algorithm developed in this study, rice and weeds can be discriminated by consumer-grade UAV images with acceptable accuracy to meet the needs of site-specific weed management (SSWM) even in the early growth stages of small rice plants..

OpenWeedLocator (OWL): An open-source, low-cost device for fallow weed detection.

“…The low variability in precision of ExHSV, coupled with the ability to refine sensitivity in two colour spaces suggests it is a better option for large-scale weed detection in environments where weeds are large and green. Similarly, Kawamura et al, (2021) found combining HSV and ExG features improved performance of a machine learning model over other models trained on HSV alone. Using ExG instead of NExG in the composite ExHSV algorithm may be advantageous based on the results presented here, however, Woebbecke et al, (1995a) found non-normalized RGB chromatic coordinates to be highly variable, resulting in poorer performance.…”

How Can Unmanned Aerial Vehicles Be Used for Detecting Weeds in Agricultural Fields?

“…Another study [94] used classification algorithms based on the RF for weed extraction and unsupervised classification with the K-means algorithm to estimate weeds in non-weed areas. The simple linear iterative clustering algorithm and RF classifier had discriminated rice and weeds with better performance using hue-saturation-brightness than RGB and CIE-L*a*b consumer-grade UAV images, as shown by Kawamura et al [95]. The images from Canon S110 NIR (green, red, near-infrared) on UAV were also classified by Reis et al [42] by combining RF and maximum likelihood algorithms.…”

Weed Detection in Rice Fields Using Remote Sensing Technique: A Review

“…These are typical steps to acquire RGB images captured by UAV remote sensing: (1) pre-flight planning, (2) flight and image acquisition and (3) post-processing and indices or dataset extrapolation [44]. However, when preparing the images for machine learning algorithms, the processing steps are different depending on the research's objective [45][46][47]. The advantage of using this sensor is that radiometric and atmospheric calibration are not required, unlike multispectral and hyperspectral images [41].…”