Weed detection using machine learning: A systematic literature review

Abubakar, Bashir Salisu

doi:10.54480/slrm.v2i2.21

Cited by 4 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NNs are an excellent alternative to classic mathematical algorithms and are promising alternatives to these classic mathematic models [116]. Deep NNs are increasingly studied because of their performance and automatic feature extraction [117]. Numerous studies have discussed the advantage of using NNs in crop parameter estimation [7,41,116,118].…”

Section: Methodsmentioning

confidence: 99%

A Meta-Analysis of Remote Sensing Technologies and Methodologies for Crop Characterization

et al. 2022

View full text Add to dashboard Cite

Climate change and population growth risk the world’s food supply. Annual crop yield production is one of the most crucial components of the global food supply. Moreover, the COVID-19 pandemic has stressed global food security, production, and supply chains. Using biomass estimation as a reliable yield indicator, space-based monitoring of crops can assist in mitigating these stresses by providing reliable product information. Research has been conducted to estimate crop biophysical parameters by destructive and non-destructive approaches. In particular, researchers have investigated the potential of various analytical methods to determine a range of crop parameters using remote sensing data and methods. To this end, they have investigated diverse sources of Earth observations, including radar and optical images with various spatial, spectral, and temporal resolutions. This paper reviews and analyzes publications from the past 30 years to identify trends in crop monitoring research using remote sensing data and tools. This analysis is accomplished through a systematic review of 277 papers and documents the methods, challenges, and opportunities frequently cited in the scientific literature. The results revealed that research in this field had increased dramatically over this study period. In addition, the analyses confirmed that the normalized difference vegetation index (NDVI) had been the most studied vegetation index to estimate crop parameters. Moreover, this analysis showed that wheat and corn were the most studied crops, globally.

show abstract

Section: Methodsmentioning

confidence: 99%

A Meta-Analysis of Remote Sensing Technologies and Methodologies for Crop Characterization

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In contrast to deep learning methods, these algorithms require task-specific feature extraction as a data preprocessing step. Task-specific shapes, textures, and spectral or color features were commonly computed in weed detection [4,16]. Nowadays, most weed detection approaches rely on deep learning models [4].…”

Section: Related Workmentioning

confidence: 99%

Weakly Supervised Perennial Weed Detection in a Barley Field

2023

View full text Add to dashboard Cite

In the field of precision agriculture, weed detection models combined with selective spraying by ground or aerial robotics are seen as promising approaches for increasing yield harvests while simultaneously minimizing herbicide use. The available labeled training data are a major bottleneck for developing and applying supervised deep learning models, and more automated methods for labeled data generation are therefore needed. Our research aims to address this need by introducing a rule-based method for label data generation for perennial weeds. For this research, a dataset of a barley field was collected using an unmanned aerial vehicle (UAV) with a flight altitude of 10 m. A multispectral and a thermal camera were used for the data collection. The preprocessed dataset consists of multispectral and thermal orthomosaic images along with a canopy height model. The methodological part of this article introduces a proposed rule-based method for labeled data generation for perennial weeds based on the Normalized Difference Vegetation Index (NDVI), and this approach is further used to generate labels for the measured data. The preprocessed data combined with the generated labels was used to train U-net models. Three data combinations are used for the training and testing: multispectral, multispectral–thermal and multispectral–thermal–canopy–height–model. This approach was used to evaluate whether additional data improve model performance. To evaluate the models on ground truth labels, they are tested on a manually annotated test dataset, which consists of 10% of the whole dataset. The tested models achieved an F1 score of 0.82–0.83 on the test dataset. This finding demonstrates that the rule-based labeling method generates valid labels for the perennial weed detection task. Furthermore, our study shows that data fusion improved the model slightly. The data combination of multispectral–thermal–canopy–height–model as input resulted in the best-performing model, with an F1 score of 0.835.

show abstract