Early Weed Detection Using Image Processing and Machine Learning Techniques in an Australian Chilli Farm

This paper explores the potential of machine learning algorithms for weed and crop classification from UAV images. The identification of weeds in crops is a challenging task that has been addressed through orthomosaicing of images, feature extraction and labelling of images to train machine learning algorithms. In this paper, the performances of several machine learning algorithms, random forest (RF), support vector machine (SVM) and k-nearest neighbours (KNN), are analysed to detect weeds using UAV images collected from a chilli crop field located in Australia. The evaluation metrics used in the comparison of performance were accuracy, precision, recall, false positive rate and kappa coefficient. MATLAB is used for simulating the machine learning algorithms; and the achieved weed detection accuracies are 96% using RF, 94% using SVM and 63% using KNN. Based on this study, RF and SVM algorithms are efficient and practical to use, and can be implemented easily for detecting weed from UAV images.

[1]  Yong He,et al.  Recognising weeds in a maize crop using a random forest machine-learning algorithm and near-infrared snapshot mosaic hyperspectral imagery , 2018, Biosystems Engineering.

[2]  James Brinkhoff,et al.  Land Cover Classification of Nine Perennial Crops Using Sentinel-1 and -2 Data , 2019, Remote. Sens..

[3]  Dimitrios Moshou,et al.  Incorporating Surface Elevation Information in UAV Multispectral Images for Mapping Weed Patches , 2018, J. Imaging.

[4]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[5]  Zhe Xu,et al.  Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV , 2014, Remote. Sens..

[6]  Shlomi Aharon,et al.  Image-Based High-Throughput Phenotyping of Cereals Early Vigor and Weed-Competitiveness Traits , 2020, Remote. Sens..

[7]  Arnon Karnieli,et al.  Assessment of maize yield and phenology by drone-mounted superspectral camera , 2019, Precision Agriculture.

[8]  N. Mueller,et al.  Climate Change and Global Food Systems: Potential Impacts on Food Security and Undernutrition. , 2017, Annual review of public health.

[9]  María Pérez-Ortiz,et al.  Selecting patterns and features for between- and within- crop-row weed mapping using UAV-imagery , 2016, Expert Syst. Appl..

[10]  Jorge Torres-Sánchez,et al.  An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery , 2018, Remote. Sens..

[11]  Dharmendra Saraswat,et al.  Machine learning approaches to automate weed detection by UAV based sensors , 2019, Defense + Commercial Sensing.

[12]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[13]  Hans Jørgen Andersen,et al.  Detecting creeping thistle in sugar beet fields using vegetation indices , 2015, Comput. Electron. Agric..

[14]  Dan G. Blumberg,et al.  Hyperspectral Reflectance and Indices for Characterizing the Dynamics of Crop-Weed Competition for Water , 2021, Remote. Sens..

[15]  S. Kinast,et al.  Ground-level hyperspectral imagery for detecting weeds in wheat fields , 2013, Precision Agriculture.

[16]  Faisal Ahmed,et al.  Classification of crops and weeds from digital images: A support vector machine approach , 2012 .

[17]  S. Balamurali,et al.  Performance Analysis of Classifier Models to Predict Diabetes Mellitus , 2015 .

[18]  Wen Zhang,et al.  A review on weed detection using ground-based machine vision and image processing techniques , 2019, Comput. Electron. Agric..

[19]  Nahina Islam,et al.  A Review of Applications and Communication Technologies for Internet of Things (IoT) and Unmanned Aerial Vehicle (UAV) Based Sustainable Smart Farming , 2021, Sustainability.

[20]  Juan Ignacio Arribas,et al.  Weed Classification for Site-Specific Weed Management Using an Automated Stereo Computer-Vision Machine-Learning System in Rice Fields , 2020, Plants.

[21]  Martin Weis,et al.  An Ultrasonic System for Weed Detection in Cereal Crops , 2012, Sensors.

[22]  Ashutosh Kumar Singh,et al.  Machine Learning for High-Throughput Stress Phenotyping in Plants. , 2016, Trends in plant science.

[23]  Yadong Liu,et al.  Computer vision technology in agricultural automation —A review , 2020 .

[24]  Satyendra Prasad Singh,et al.  Performance Analysis of Classification Tree Learning Algorithms , 2012 .

[25]  Dominique Chabot,et al.  An Object-Based Image Analysis Workflow for Monitoring Shallow-Water Aquatic Vegetation in Multispectral Drone Imagery , 2018, ISPRS Int. J. Geo Inf..

[26]  Stuart R. Phinn,et al.  Measuring Canopy Structure and Condition Using Multi-Spectral UAS Imagery in a Horticultural Environment , 2018, Remote. Sens..

[27]  Jing Guo,et al.  Combing K-means Clustering and Local Weighted Maximum Discriminant Projections for Weed Species Recognition , 2019, Front. Comput. Sci..

[28]  Abdolabbas Jafari,et al.  Evaluation of support vector machine and artificial neural networks in weed detection using shape features , 2018, Comput. Electron. Agric..

[29]  R. Gerhards,et al.  Precision farming for weed management: techniques , 2008, Gesunde Pflanzen.