Noise Removal Based on Tensor Modelling for Hyperspectral Image Classification

Abstract

With the current state-of-the-art computer aided manufacturing tools, the spatial resolution of hyperspectral sensors is becoming increasingly higher thus making it easy to obtain much more detailed information of the scene captured. However, the improvement of the spatial resolution also brings new challenging problems to address with signal dependent photon noise being one of them. Unlike the signal independent thermal noise, the variance of photon noise is dependent on the signal, therefore many denoising methods developed for the stationary noise cannot be applied directly to the photon noise. To make things worse, both photon and thermal noise coexist in the captured hyperspectral image (HSI), thus making it more difficult to whiten noise. In this paper, we propose a new denoising framework to cope with signal dependent nonwhite noise (SDNW), Pre-estimate—Whitening—Post-estimate (PWP) loop, to reduce both photon and thermal noise in HSI. Previously, we proposed a method based on multidimensional wavelet packet transform and multi-way Wiener filter which performs both white noise and spectral dimensionality reduction, referred to as MWPT-MWF, which was restricted to white noise. We get inspired from this MWPT-MWF to develop a new iterative method for reducing photon and thermal noise. Firstly, the hyperspectral noise parameters estimation (HYNPE) algorithm is used to estimate the noise parameters, the SD noise is converted to an additive white Gaussian noise by pre-whitening procedure and then the whitened HSI is denoised by the proposed method SDNW-MWPT-MWF. As comparative experiments, the Multiple Linear Regression (MLR) based denoising method and tensor-based Multiway Wiener Filter (MWF) are also used in the denoising framework. An HSI captured by Reflective Optics System Imaging Spectrometer (ROSIS) is used in the experiments and the denoising performances are assessed from various aspects: the noise whitening performance, the Signal-to-Noise Ratio (SNR), and the classification performance. The results on the real-world airborne hyperspectral image HYDICE (Hyperspectral Digital Imagery Collection Experiment) are also presented and analyzed. These experiments show that it is worth taking into account noise signal-dependency hypothesis for processing HYDICE and ROSIS HSIs.

An Improved New Convolutional Neural Network Method for Inverting the Pore Pressure in Oil Reservoir by Surface Vertical Deformation

“…However, past research mainly focused on changes of formation pore pressure to calculate surface deformation. At present, the method of predicting the underground parameters by the surface deformation has been applied [15][16][17]. This is the first time of calculating pore pressure of underground oil reservoirs by surface deformation.…”

Hyperspectral and LiDAR Data Fusion Classification Using Superpixel Segmentation-Based Local Pixel Neighborhood Preserving Embedding

“…Currently, various algorithms are only designed for HSI or LiDAR. Several algorithms for classification, feature extraction, and segmentation are proposed for HSI [2][3][4][5][6][7][8][9][10], while many feature extraction and detection algorithms are only designed for LiDAR [11][12][13][14][15][16]. However, it is evident that no single type of sensors can always be adequate for reliable image interpretation.…”

A Novel Algorithm for Hyperspectral Image Denoising in Medical Application

“…For sensors utilized in hyperspectral imagination, there are two fundamental classifications over the random noise that are signal independent (TN) noise and signal dependent (PN) noise. [1,2]. The charged coupled device (CCD) digicam resolution has been increased considerably, among order so much the photon noise has turn out to be as much dominant because the signal-independent digital noise of HSI statistics accumulated by using new-generation hyperspectral sensors [1][2][3][4][5][6].…”

“…[1,2]. The charged coupled device (CCD) digicam resolution has been increased considerably, among order so much the photon noise has turn out to be as much dominant because the signal-independent digital noise of HSI statistics accumulated by using new-generation hyperspectral sensors [1][2][3][4][5][6]. The commonly used signal dependent and signal independent noise model have been conjointly proposed recently, anywhere the hyper-spectral noise parameter estimation algorithmic rule used to be projected.…”

“…Based on scatter plot estimation of signal dependent photon noise parameters was proposed by Aiazzi et al in [13,14]. Regardless, the signal dependent noise is not appropriate in hyperspectral image which is discussed by B. Aiazzi et al Argenti et al was presented most precise common signal dependent noise model for digital image [15,16] and also measured the noise value in wavelet domain using Linear Minimum Mean Square Error (LMMSE) [1] (www.mdpi. com/2072-4292/10/9/1330/htm).…”