Hyperspectral Images-Based Crop Classification Scheme for Agricultural Remote Sensing

Abstract

Hyperspectral imaging is gaining a significant role in agricultural remote sensing applications. Its data unit is the hyperspectral cube which holds spatial information in two dimensions while spectral band information of each pixel in the third dimension. The classification accuracy of hyperspectral images (HSI) increases significantly by employing both spatial and spectral features. For this work, the data was acquired using an airborne hyperspectral imager system which collected HSI in the visible and near-infrared (VNIR) range of 400 to 1000 nm wavelength within 180 spectral bands. The dataset is collected for nine different crops on agricultural land with a spectral resolution of 3.3 nm wavelength for each pixel. The data was cleaned from geometric distortions and stored with the class labels and annotations of global localization using the inertial navigation system. In this study, a unique pixel-based approach was designed to improve the crops' classification accuracy by using the edge-preserving features (EPF) and principal component analysis (PCA) in conjunction. The preliminary processing generated the high-dimensional EPF stack by applying the edge-preserving filters on acquired HSI. In the second step, this high dimensional stack was treated with the PCA for dimensionality reduction without losing significant spectral information. The resultant feature space (PCA-EPF) demonstrated enhanced class separability for improved crop classification with reduced dimensionality and computational cost. The support vector machines classifier was employed for multiclass classification of target crops using PCA-EPF. The classification performance evaluation was measured in terms of individual class accuracy, overall accuracy, average accuracy, and Cohen kappa factor. The proposed scheme achieved greater than 90 % results for all the performance evaluation metrics. The PCA-EPF proved to be an effective attribute for crop classification using hyperspectral imaging in the VNIR range. The proposed scheme is well-

Driving drowsiness detection using spectral signatures of EEG-based neurophysiology

“…The subspace discriminant (DA learner) and subspace NN ( NN learner) ensemble methods use randomly selected 4D subspace of features in datasets with a large number of predictors. The bagged and boosted trees tend to achieve higher accuracies for datasets with a smaller number of predictors due to fine DT learners performing well in non-linear class separation boundaries and blended data dispersion ( Ali et al, 2023 ).…”

“…Cohen's kappa coefficient (κ) is the statistical test to measure the degree of reliability or agreement between two raters (Akhtar et al, 2021). The kappa score κ ≈ 1 shows that both the performance evaluation raters are in complete agreement about their performance, and their results are reliable, while κ ≈ 0 indicates the disagreement in raters and such results happen by chance (Ali et al, 2023).…”

Novel oil spill indices for sentinel-2 imagery: A case study of natural seepage in Qaruh Island, Kuwait

“…Most developed remote sensing indices are based on the ratio or difference between two bands, like the Normalized Difference Vegetation Index (NDVI) [ 23 , 24 ], but no rule says it has to be this way. A more complex formula involving multiple bands works best.…”

An Ensemble-Based Framework for Sophisticated Crop Classification Exploiting Google Earth Engine

“…With the launch of the Sentinel mission, remote sensing has become more capable of providing higher-quality multispectral data. Hyperspectral and multispectral datasets have been studied extensively in recent decades to monitor crops [6]. Numerous studies have utilized remote-sensing techniques to estimate crop areas based on large agricultural areas and complex measurements [7,8].…”