Spatial-Spectral Feature for Extraction Technique for Hyperspectral Crop Classification

Abstract

Objectives:To present an extraction technique for the classification of the hyperspectral crop using the spatial-spectral feature. Methods: This paper presents a spatial-spectral feature extraction method employing the Image fusion technique and intrinsic feature extraction and a model for Improved Decision Boundary (IDB) using Support Vector Machine (SVM). Findings:The experiments have been conducted by using the Indian pines dataset which was extracted using the AVIRIS sensor. The dataset comprises of 16 distinctive classes such as corn, wheat, oats etc, which have used for evaluation of our model. Before the evaluation of the dataset the model has been trained using different training datasets in order to increase the accuracy and reduce misclassification. Moreover, the Spatial-Spectral Feature (SSF) model aided in distinguishing between crop intrinsic features and shadow element under dynamic environment condition. Our model attained 99.54%, 99.4%, 99.25% and 9.8 sec for OA accuracy, AA accuracy, Kappa and Time respectively. Furthermore, the overall accuracy of the model for the Support Vector Machine-3-dimensional discrete wavelet transform (SVM-3DDWT), Convolutional Neural Network and Spatial-Spectral Feature Extraction Technique showed result of 94.28%, 96.12% and 99.4% respectively. Other existing models showed a low accuracy for the same dataset. Further, for addressing class imbalance issues this work modelled an improved decision boundary model for SVM by considering soft-margin rather than hard margin. The SSF-IDBSVM model achieves much better accuracies with less misclassification in comparison with recent deep learning-based HSI classification model. Novelty: Recently, several feature extraction and deep learning-based crop classification model have been modelled. However, existing crop classification fails to distinguish crop intrinsic feature concerning shadow feature; further, consider hard decision boundary; as a result, high misclassification is induced for smaller class size. Hence, this study provides an extraction feature which provides the classification of the crop in less time with higher classification and less misclassification.

Hyperspectral object classification using hybrid spectral-spatial fusion and noise tolerant soft-margin technique

“…The averaging-based image fusion is done at each group and the corresponding fusion data 𝑄 is given using (3).…”

“…It works especially effectively in the domains of precision agriculture and plant phenotyping identification [1], [2]. One such indicator is the normalized-difference vegetation index (NDVI) [3], from which the NDVI distributed mapping is typically derived using standard methods, which typically use the initial unmanned aerial vehicle (UAV) multi-spectral (MS) image. Inaccuracy in the NDVI distributed mapping could be caused by the original MS pictures' low spatial resolution.…”

A hybrid spectral-spatial fusion technique for hyperspectral object classification

“…According to figure, there are an overall of 16 crops (or labels) that make up the ground-truth information. In a manner comparable to [2], [3], the waterabsorption spectrum bands are removed, and the total number of the bands that comprise the spectral spectrum is decreased to 200.…”

“…Particularly, it is put to good use in the fields of precision agricultural as well as in identification of phenotypes of plants [1], [2]. The normalized-difference vegetation-index (NDVI) [3] is one such indicator, and conventional approaches often employ the initial UAV multi-spectral (MS) image to derive the NDVI distributed mapping. Inaccuracy within the NDVI distributed mapping may result from the poor spatial resolution of the source MS images.…”

Application of deep learning methods for automated analysis of retinal structures in ophthalmology

“…In modern ophthalmology, advanced deep learning technologies are being actively implemented [1], [2] for automated analysis of retinal structures. Some of the key methods that have attracted the attention of researchers and clinicians are EfficientNet [3], [4] and DenseNet [5], [6]. These methods provide powerful tools for image processing [7], [8] with a high degree of efficiency.…”