A Comparative Study on Linear Regression-Based Noise Estimation for Hyperspectral Imagery

Gao, Lianru; Du, Qian; Zhang, Bing; Yang, Wei; Wu, Yuanfeng

doi:10.1109/jstars.2012.2227245

Cited by 91 publications

(53 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we can incorporate the high correlations between bands for noise estimation, such as SSDC, which is a useful method for hyperspectral image noise estimation. In SSDC, the spatial and spectral correlations are removed through a multiple linear regression model, and the remaining residuals are the estimates of noise [49,50,58]. Recent works show that SSDC can offer reliable results for noise estimation when there are different land cover types in the hyperspectral images [50].…”

Section: Proposed Okmnf Methodsmentioning

confidence: 99%

Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification

et al. 2017

Self Cite

View full text Add to dashboard Cite

This paper presents an optimized kernel minimum noise fraction transformation (OKMNF) for feature extraction of hyperspectral imagery. The proposed approach is based on the kernel minimum noise fraction (KMNF) transformation, which is a nonlinear dimensionality reduction method. KMNF can map the original data into a higher dimensional feature space and provide a small number of quality features for classification and some other post processing. Noise estimation is an important component in KMNF. It is often estimated based on a strong relationship between adjacent pixels. However, hyperspectral images have limited spatial resolution and usually have a large number of mixed pixels, which make the spatial information less reliable for noise estimation. It is the main reason that KMNF generally shows unstable performance in feature extraction for classification. To overcome this problem, this paper exploits the use of a more accurate noise estimation method to improve KMNF. We propose two new noise estimation methods accurately. Moreover, we also propose a framework to improve noise estimation, where both spectral and spatial de-correlation are exploited. Experimental results, conducted using a variety of hyperspectral images, indicate that the proposed OKMNF is superior to some other related dimensionality reduction methods in most cases. Compared to the conventional KMNF, the proposed OKMNF benefits significant improvements in overall classification accuracy.

show abstract

Section: Proposed Okmnf Methodsmentioning

confidence: 99%

Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…As can be clearly seen from Figure 1, the noise level of the five representative bands is different, and the noise levels of bands 1 and 220 are obviously higher than those of the other three bands. Besides, the previous works correlated with noise estimation of HSI [52][53][54] have demonstrated that the hyperspectral imaging spectrometers adopt very narrow band, which makes the energy acquired in each band not enough to obtain high signal-to-noise ratio (SNR), and the HSI is usually corrupted by wavelength-dependent and sensor-specific noise, which not only degrades the visual quality of the HSI but also limits the precision of the subsequent image interpretation and analysis. That is to say, the noise of HSI is wavelength-dependent, thus the noise levels of different bands are different.…”

Section: The Proposed Su-nlementioning

confidence: 99%

“…To overcome the above mentioned problem, according to the Figure 1 and the previous works correlated with noise estimation of HSI [52][53][54], it is natural to assume that the noise levels at different bands are different. We adopt a simple and efficient noise estimation method based on the multiple regression theory, developed by Bioucas and Nascimento [52], to estimate the noise in each band of HSI.…”

Section: The Proposed Su-nlementioning

confidence: 99%

Sparse Unmixing of Hyperspectral Data with Noise Level Estimation

Mei

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:Recently, sparse unmixing has received particular attention in the analysis of hyperspectral images (HSIs). However, traditional sparse unmixing ignores the different noise levels in different bands of HSIs, making such methods sensitive to different noise levels. To overcome this problem, the noise levels at different bands are assumed to be different in this paper, and a general sparse unmixing method based on noise level estimation (SU-NLE) under the sparse regression framework is proposed. First, the noise in each band is estimated on the basis of the multiple regression theory in hyperspectral applications, given that neighboring spectral bands are usually highly correlated. Second, the noise weighting matrix can be obtained from the estimated noise. Third, the noise weighting matrix is integrated into the sparse regression unmixing framework, which can alleviate the impact of different noise levels at different bands. Finally, the proposed SU-NLE is solved by the alternative direction method of multipliers. Experiments on synthetic datasets show that the signal-to-reconstruction error of the proposed SU-NLE is considerably higher than those of the corresponding traditional sparse regression unmixing methods without noise level estimation, which demonstrates the efficiency of integrating noise level estimation into the sparse regression unmixing framework. The proposed SU-NLE also shows promising results in real HSIs.Keywords: alternative direction method of multipliers (ADMM); hyperspectral image (HSI); sparse unmixing method based on noise level estimation (SU-NLE)

show abstract

“…Although those selected bands with sparsity have strength to the small-sample-size problem, the random noise due to the very narrow bandwidth of the hyperspectral sensor negatively affects to the prediction model. One simple noise estimation algorithm uses the mean of standard deviations of several visually homogeneous regions as noise estimate (Gao et al, 2013). However, the homogeneous areas within an image need to be manually selected in this method.…”

Section: Fused Lasso Regression For Noise and Peak Shiftmentioning

confidence: 99%

“…Therefore, the prediction models often result in the poor generalization capability (Pappu, 2014). Considering sensor mechanism and practical measurement, energy acquired in each band is not enough to generate high signal-to-noise ratio (S/N) due to the very narrow band interval of typical hyperspectral imaging spectrometers (Gao et al, 2013). The noise in the hyperspectral data can be categorized in two types: periodic noise and random noise.…”

Section: Introductionmentioning

confidence: 99%

Optimal Wavelength Selection on Hyperspectral Data With Fused Lasso for Biomass Estimation of Tropical Rain Forest

Takayama¹,

Iwasaki²

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Commission VIII, WG VIII/7KEY WORDS: Biomass, Hyperspectral, Forest Management, Fused Lasso, GLCM ABSTRACT:Above-ground biomass prediction of tropical rain forest using remote sensing data is of paramount importance to continuous largearea forest monitoring. Hyperspectral data can provide rich spectral information for the biomass prediction; however, the prediction accuracy is affected by a small-sample-size problem, which widely exists as overfitting in using high dimensional data where the number of training samples is smaller than the dimensionality of the samples due to limitation of require time, cost, and human resources for field surveys. A common approach to addressing this problem is reducing the dimensionality of dataset. Also, acquired hyperspectral data usually have low signal-to-noise ratio due to a narrow bandwidth and local or global shifts of peaks due to instrumental instability or small differences in considering practical measurement conditions. In this work, we propose a methodology based on fused lasso regression that select optimal bands for the biomass prediction model with encouraging sparsity and grouping, which solves the small-sample-size problem by the dimensionality reduction from the sparsity and the noise and peak shift problem by the grouping. The prediction model provided higher accuracy with root-mean-square error (RMSE) of 66.16 t/ha in the crossvalidation than other methods; multiple linear analysis, partial least squares regression, and lasso regression. Furthermore, fusion of spectral and spatial information derived from texture index increased the prediction accuracy with RMSE of 62.62 t/ha. This analysis proves efficiency of fused lasso and image texture in biomass estimation of tropical forests.

show abstract

A Comparative Study on Linear Regression-Based Noise Estimation for Hyperspectral Imagery

Cited by 91 publications

References 29 publications

Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification

Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification

Sparse Unmixing of Hyperspectral Data with Noise Level Estimation

Optimal Wavelength Selection on Hyperspectral Data With Fused Lasso for Biomass Estimation of Tropical Rain Forest

Contact Info

Product

Resources

About