scholarly journals Mixed Noise Estimation Model for Optimized Kernel Minimum Noise Fraction Transformation in Hyperspectral Image Dimensionality Reduction

2021 ◽  
Vol 13 (13) ◽  
pp. 2607
Author(s):  
Tianru Xue ◽  
Yueming Wang ◽  
Yuwei Chen ◽  
Jianxin Jia ◽  
Maoxing Wen ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Spatial Resolution ◽  
Hyperspectral Image ◽  
Noise Estimation ◽  
Processing Unit ◽  
Estimation Model ◽  
Minimum Noise Fraction ◽  
Mixed Noise ◽  
Noise Fraction ◽  
Minimum Noise

Dimensionality reduction (DR) is of great significance for simplifying and optimizing hyperspectral image (HSI) features. As a widely used DR method, kernel minimum noise fraction (KMNF) transformation preserves the high-order structures of the original data perfectly. However, the conventional KMNF noise estimation (KMNF-NE) uses the local regression residual of neighbourhood pixels, which depends heavily on spatial information. Due to the limited spatial resolution, there are many mixed pixels in HSI, making KMNF-NE unreliable for noise estimation and leading to poor performance in KMNF for classification on HSIs with low spatial resolution. In order to overcome this problem, a mixed noise estimation model (MNEM) is proposed in this paper for optimized KMNF (OP-KMNF). The MNEM adopts the sequential and linear combination of the Gaussian prior denoising model, median filter, and Sobel operator to estimate noise. It retains more details and edge features, making it more suitable for noise estimation in KMNF. Experiments using several HSI datasets with different spatial and spectral resolutions are conducted. The results show that, compared with some other DR methods, the improvement of OP-KMNF in average classification accuracy is up to 4%. To improve the efficiency, the OP-KMNF was implemented on graphics processing units (GPU) and sped up by about 60× compared to the central processing unit (CPU) implementation. The outcome demonstrates the significant performance of OP-KMNF in terms of classification ability and execution efficiency.

scholarly journals Target detection algorithm for airborne thermal hyperspectral data

2014 ◽  
Vol XL-8 ◽  
pp. 827-832 ◽  
Author(s):  
R. Marwaha ◽  
A. Kumar ◽  
P. L. N. Raju ◽  
Y. V. N. Krishna Murthy
Keyword(s):  
Spectral Resolution ◽  
Hyperspectral Image ◽  
Imaging System ◽  
Hyperspectral Data ◽  
High Spectral Resolution ◽  
Infrared Range ◽  
Digital Photograph ◽  
Minimum Noise Fraction ◽  
Noise Fraction ◽  
Minimum Noise

Airborne hyperspectral imaging is constantly being used for classification purpose. But airborne thermal hyperspectral image usually is a challenge for conventional classification approaches. The Telops Hyper-Cam sensor is an interferometer-based imaging system that helps in the spatial and spectral analysis of targets utilizing a single sensor. It is based on the technology of Fourier-transform which yields high spectral resolution and enables high accuracy radiometric calibration. The Hypercam instrument has 84 spectral bands in the 868 cm<sup>&minus;1</sup> to 1280 cm<sup>&minus;1</sup> region (7.8 μm to 11.5 μm), at a spectral resolution of 6 cm<sup>&minus;1</sup> (full-width-half-maximum) for LWIR (long wave infrared) range. Due to the Hughes effect, only a few classifiers are able to handle high dimensional classification task. MNF (Minimum Noise Fraction) rotation is a data dimensionality reducing approach to segregate noise in the data. In this, the component selection of minimum noise fraction (MNF) rotation transformation was analyzed in terms of classification accuracy using constrained energy minimization (CEM) algorithm as a classifier for Airborne thermal hyperspectral image and for the combination of airborne LWIR hyperspectral image and color digital photograph. On comparing the accuracy of all the classified images for airborne LWIR hyperspectral image and combination of Airborne LWIR hyperspectral image with colored digital photograph, it was found that accuracy was highest for MNF component equal to twenty. The accuracy increased by using the combination of airborne LWIR hyperspectral image with colored digital photograph instead of using LWIR data alone.

scholarly journals Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification

2017 ◽  
Vol 9 (6) ◽  
pp. 548 ◽  
Author(s):  
Lianru Gao ◽  
Bin Zhao ◽  
Xiuping Jia ◽  
Wenzhi Liao ◽  
Bing Zhang
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Hyperspectral Image Classification ◽  
Minimum Noise Fraction ◽  
Noise Fraction ◽  
Minimum Noise

scholarly journals THE EFFECT OF MINIMUM NOISE FRACTION ON MULTISPECTRAL IMAGERY DATA FOR VEGETATION CANOPY DENSITY MODELLING

2018 ◽  
Vol 5 (2) ◽  
pp. 253
Author(s):  
Akbar Muammar Syarif ◽  
Ignatius Salivian Wisnu Kumara
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Hyperspectral Image ◽  
Vegetation Density ◽  
Model Accuracy ◽  
Multispectral Data ◽  
Minimum Noise Fraction ◽  
Noise Fraction ◽  
Minimum Noise ◽  
Density Modeling

Minimum Noise Fraction (MNF) is known as one of the method to minimize noise on hyperspectral imagery. In addition, there are not many studies have tried to show the effect of MNF transform on multispectral data. This study purposes to determine the effect of MNF transform on the accuracy level of vegetation density modeling using 10 meters Sentinel-2A spatial resolution (multispectral data) and to know the cause. The study area is located in parts of Sapporo City, Hokkaido, Japan. Vegetation density is modelled through vegetation index approach, Normalized Difference Vegetation Index (NDVI). The results show that the coefficient correlation of vegetation density data and vegetation index regression after MNF transformation (0.801623) has higher value than the same regression without the MNF (0.794481). However, better correlation does not represent the better accuracy on vegetation density modeling. Accuracy calculation through standard error of estimate shows the use of MNF in multispectral data for vegetation density modeling causes the decrease of model accuracy value. The accuracy of vegetation density model without involving MNF transformation reached 91.40 %, while the model accuracy through MNF transformation before vegetation density modeling reached 90.89 %. The insignificant increased accuracy is occurred due to the limited number of multispectral image information compared to hyperspectral image data.

scholarly journals The Effect of Minimum Noise Fraction on Multispectral Imagery Data for Vegetation Canopy Density Modelling

2018 ◽  
Vol 5 (2) ◽  
pp. 251
Author(s):  
Akbar Muammar Syarif ◽  
Ignatius Salivian Wisnu Kumara
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Hyperspectral Image ◽  
Vegetation Density ◽  
Model Accuracy ◽  
Multispectral Data ◽  
Minimum Noise Fraction ◽  
Noise Fraction ◽  
Minimum Noise ◽  
Density Modeling

Minimum Noise Fraction (MNF) is known as one of the method to minimize noise on hyperspectral imagery. In addition, there are not many studies have tried to show the effect of MNF transform on multispectral data. This study purposes to determine the effect of MNF transform on the accuracy level of vegetation density modeling using 10 meters Sentinel-2A spatial resolution (multispectral data) and to know the cause. The study area is located in parts of Sapporo City, Hokkaido, Japan. Vegetation density is modelled through vegetation index approach, Normalized Difference Vegetation Index (NDVI). The results show that the coefficient correlation of vegetation density data and vegetation index regression after MNF transformation (0.801623) has higher value than the same regression without the MNF (0.794481). However, better correlation does not represent the better accuracy on vegetation density modeling. Accuracy calculation through standard error of estimate shows the use of MNF in multispectral data for vegetation density modeling causes the decrease of model accuracy value. The accuracy of vegetation density model without involving MNF transformation reached 91.402 %, while the model accuracy through MNF transformation before vegetation density modeling reached 90.889 %. The insignificant increased accuracy is occurred due to the limited number of multispectral image information compared to hyperspectral image data. 

Sign in / Sign up

Export Citation Format

Share Document