Sparse Representation-Based Hyperspectral Image Classification Using Multiscale Superpixels and Guided Filter

Validating Hyperspectral Image Segmentation

“…Year Datasets * Settings Multiscale superpixels [1] 2018 IP, PU Random Watershed + SVM [2] 2010 PU Arbitrary Clustering (SVM) [3] 2011 Washington DC, PU Full image Multiresolution segm. [4] 2018 Three in-house datasets Random Region expansion [5] 2018 PU, Sa, KSC Full image DBN (spatial-spectral) [6] 2014 HU Random DBN (spatial-spectral) [7] 2015 IP, PU Random Deep autoencoder [8] 2014 KSC, PU Monte Carlo CNN [9] 2016 PC, PU, Random CNN [10] 2016 IP, PU, KSC Monte Carlo Active learning + DBN [11] 2017 PC, PU, Bo Random DBN (spectral) [12] 2017 IP, PU Random RNN (spectral) [13] 2017 PU, HU, IP Random CNN [14] 2017 IP, Sa, PU Random CNN [15] 2017 IP, Sa, PU Monte Carlo CNN [16] 2018 IP, Sa, PU Monte Carlo CNN [17] 2018 Sa, PU Random * IP-Indian Pines; PU-Pavia University; Sa-Salinas; KSC-Kennedy Space Center; HU-Houston University; PC-Pavia Centre; Bo-Botswana from an input HSI are selected as training and test pixels at random (without overlaps).…”

“…Such a big amount of reflectance information about the underlying material can help in accurate HSI segmentation (deciding on the boundaries of objects of a given class). Hence, HSI is being actively used in a range of areas, including precision agriculture, military, surveillance, and more [1]. The state-of-the-art HSI segmentation methods include conventional machine-learning algorithms, which can be further divided into unsupervised [2], [3] and supervised [1], [4], [5] techniques, and modern deeplearning (DL) algorithms [6]- [17] that do not require feature engineering.…”

“…Hence, HSI is being actively used in a range of areas, including precision agriculture, military, surveillance, and more [1]. The state-of-the-art HSI segmentation methods include conventional machine-learning algorithms, which can be further divided into unsupervised [2], [3] and supervised [1], [4], [5] techniques, and modern deeplearning (DL) algorithms [6]- [17] that do not require feature engineering. DL techniques allow for extracting spectral features (e.g., using deep belief networks [DBNs] [11], [12] and recurrent neural networks [RNNs] [13]) or both spectral and spatial pixel's information-mainly using convolutional neural networks (CNNs) [9], [10], [14]- [17] and some DBNs [6], [7].…”

Hyperspectral Image Classification using Support Vector Machine with Guided Image Filter

“…Let eigenvector and eigenvalues are arranged in descending order, say,  1 >  2 > 3  4 >….> N , first K rows of matrix in equation 7can be used to calculate the approximation of the original images as mentioned in (8) […”

“…Recently, a guided image filter [18] is used as edgepreserving filter for most of the applications such as enhancing and denoising the images and high dynamic imaging. This guided image filter can be used to enhance the SVM classification accuracy [8] of the hyperspectral images by considering spatial features.…”