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

Nahina Islam, Md Mamunur Rashid, Santoso Wibowo, Cheng-Yuan Xu, Ahsan Morshed, Saleh A. Wasimi, Steven Moore and Sk Mostafizur Rahman
Additional contact information
Nahina Islam: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Md Mamunur Rashid: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Santoso Wibowo: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Cheng-Yuan Xu: Institute for Future Farming Systems, Central Queensland University, Bundaberg, QLD 4670, Australia
Ahsan Morshed: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Saleh A. Wasimi: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Steven Moore: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia
Sk Mostafizur Rahman: School of Engineering and Technology, Central Queensland University, Rockhampton, QLD 4700, Australia

Agriculture, 2021, vol. 11, issue 5, 1-13

Abstract: 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.

Keywords: weed detection; smart farming; machine learning; remote sensing; image processing (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (11)

Downloads: (external link)
https://www.mdpi.com/2077-0472/11/5/387/pdf (application/pdf)
https://www.mdpi.com/2077-0472/11/5/387/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:11:y:2021:i:5:p:387-:d:543131

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().