• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3295-3311
• /
• 2020

With the wide application of hyperspectral images, it becomes more and more important to compress hyperspectral images. Conventional recursive least squares (CRLS) algorithm has great potentiality in lossless compression for hyperspectral images. The prediction accuracy of CRLS is closely related to the correlations between the reference bands and the current band, and the similarity between pixels in prediction context. According to this characteristic, we present an improved CRLS with adaptive band selection and adaptive predictor selection (CRLS-ABS-APS). Firstly, a spectral vector correlation coefficient-based k-means clustering algorithm is employed to generate clustering map. Afterwards, an adaptive band selection strategy based on inter-spectral correlation coefficient is adopted to select the reference bands for each band. Then, an adaptive predictor selection strategy based on clustering map is adopted to select the optimal CRLS predictor for each pixel. In addition, a double snake scan mode is used to further improve the similarity of prediction context, and a recursive average estimation method is used to accelerate the local average calculation. Finally, the prediction residuals are entropy encoded by arithmetic encoder. Experiments on the Airborne Visible Infrared Imaging Spectrometer (AVIRIS) 2006 data set show that the CRLS-ABS-APS achieves average bit rates of 3.28 bpp, 5.55 bpp and 2.39 bpp on the three subsets, respectively. The results indicate that the CRLS-ABS-APS effectively improves the compression effect with lower computation complexity, and outperforms to the current state-of-the-art methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• Aerospace Engineering and Technology
• /
• v.2 no.1
• /
• pp.190-196
• /
• 2003

The top-of-atmosphere(TOA) radiance and its seasonal variation for various surface types have been analyzed using the MODIS direct broadcasting data acquired from the KARI ground station for the period between July 2002 and November 2003. The selected study areas considering the MODIS spatial resolution and the characteristics of the Korean peninsular are as follows: agricultural land, forest land, inland water, sea water, urban land, wetland, and atmosphere(cloud). The results showed that TOA radiances depend on the surface characteristics for the selected sample areas. Furthermore, the MODIS observations appear to well depict the general features of earth radiation properties. The authors hope that this study may provide the basic information on the analysis of hyperspectral data.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.103-109
• /
• 2023

This research developed a measurement technique that can measure the oxygen temperature inside a high temperature furnace. Instead of measuring only changes in frequency components within a small range used in the existing variable laser absorption spectroscopy, laser spectroscopy technology was used to spread out wavelength of the light source passing through the gas Based on a total of 20,000 image data, research was conducted to predict the temperature of a high-temperature furnace using CNN with black and white images in the form of spectral bands by temperature of 25 to 800 degrees. The optimal model was found through Hyper parameter optimization, R2 score is 0.89, and the accuracy of the test data is 88.73%. Based on this research, it is expected that concentration measurement and air-fuel ratio control technology can be applied.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.11
• /
• pp.51-62
• /
• 2019

In this study, a simple method to estimate the soil water content variation in a wide area was proposed using hyperspectral near-infrared images. The reflectance data of a sand, granite soils, and a kaolinite were measured by reflecting the soil samples with different wavelengths in the visible and near-infrared (VNIR) regions using hyperspectral cameras. The measured reflectances and parameters were used to build a water content prediction model using the Partial Least Square Regression (PLSR) analysis. In the water content prediction model, the Area of Reflectance (Near-infrared, NIR) parameter was the most suitable parameter to determine the water content. The parameter was applicable regardless of the soil type, as the coefficient of determination (R²) exceeded 0.9 for each soil sample. Additionally, the mean absolute percentage error (MAPE) was less than 15% when compared with the actual water content of the soil. Therefore, the predictability of water content variation for soils with water content lower than 50% was confirmed. Accordingly through this study, the predictability of water content variation in several soil types using the hyperspectral near-infrared images was confirmed. For further development, a model that incorporates soil classification would be required to improve the accuracy of the model and to predict higher range of water contents.

• Journal of the Optical Society of Korea
• /
• v.12 no.4
• /
• pp.262-268
• /
• 2008

A compact imaging spectrometer (COMIS) for use in the STSAT3 microsatellite is currently under development. It is scheduled to be launched into a low Sun-synchronous Earth orbit (${\sim}700km$) by the end of 2010. COMIS was inspired by the success of CHRIS, which is a small hyperspectral imager developed for the ESA microsatellite PROBA. COMIS is designed to achieve nearly equivalent imaging capabilities of CHRIS in a smaller (65 mm diameter and 4.3 kg mass) and mechanically superior (in terms of alignment and robustness) package. Its main operational goal will be the imaging of Earth's surface and atmosphere with ground sampling distances of ${\sim}30m$ at the $18{\sim}62$ spectral bands ($4.0{\sim}1.05{\mu}m$). This imaging will be used for environmental monitoring, such as the in-land water quality monitoring of Paldang Lake, which is located next to Seoul, South Korea. The optics of COMIS consists of two parts: imaging telescope and dispersing relay optics. The imaging telescope, which operates at an f-ratio of 4.6, forms an image (of Earth's surface or atmosphere) onto an intermediate image plane. The dispersion relay optics disperses the image and relay it onto a CCD plane. All COMIS lenses and mirrors are spherical and are made from used silica exclusively. In addition, the optics is designed such that the optical axis of the dispersed image is parallel to the optical axis of the telescope. Previous efforts focused on manufacturing ease, alignment, assembly, testing, and improved robustness in space environments.

• Food Engineering Progress
• /
• v.15 no.4
• /
• pp.324-331
• /
• 2011

Hyperspectral reflectance imaging technology was used to predict internal quality of cherry tomatoes with the spectral range of 400-1000 nm. Partial least square (PLS) regression method was used to predict firmness, sugar content, and acid content. The PLS models were developed with several preprocessing methods, such as normalization, standard normal variate (SNV), multiplicative scatter correction (MSC), and derivative of Savitzky Golay. The performance of the prediction models were investigated to find the best combination of the preprocessing and PLS models. The coefficients of determination ($R^{2}_{p}$) and standard errors of prediction (SEP) for the prediction of firmness, sugar content, and acid content of cherry tomatoes from green to red ripening stages were 0.876 and 1.875kgf with mean of normalization, 0.823 and $0.388^{\circ}Bx$ with maximum of normalization, and 0.620 and 0.208% with maximum of normalization, respectively.

• Ecology and Resilient Infrastructure
• /
• v.6 no.4
• /
• pp.243-249
• /
• 2019

The purpose of this study is to analyze the reflectance of bed materials according to changes in the water level using a drone-based hyperspectral sensor. For this purpose, we took hyperspectral images of bed materials such as soil, gravel, cobble, reed, and vegetation to compare and analyze the spectral data of each material. To adjust the water level, we constructed an experimental channel to control the discharge and installed the bed materials within the channel. In this study, we configured 3 cases according to the water level (0.0 m, 0.3 m, 0.6 m). After the imaging process, we used the mean value of 10 points for each bed material as analytical data. According to the analysis, each material showed a similar reflectance by wavelength and the intrinsic reflectance characteristics of each material were shown in the visible and near-infrared region. Also, the deeper the water level, the lower the peak reflectance in the visible and near-infrared region, and the rate of decrease differed depending on the bed material. We expect the intrinsic properties of these bed materials to be used as basic research data to evaluate river environments in the future.

• Korean Journal of Optics and Photonics
• /
• v.22 no.4
• /
• pp.184-190
• /
• 2011

A compact imaging spectrometer (COMIS) was developed for a microsatellite STSAT-3. The satellite is now rescheduled to be launched into a low sun-synchronous Earth orbit (~700 km) by the end of 2012. Its main operational goal is the imaging of the Earth's surface and atmosphere with ground sampling distance of 27 m and 2 - 15 nm spectral resolution over visible and near infrared spectrum (0.4 - 1.05 ${\mu}m$). A flight model of COMIS was developed following an engineering model that had successfully demonstrated hyperspectral imaging capability and structural rigidity. In this paper we report the environmental test results of the flight model. The mechanical stiffness of the model was confirmed by a small shift of the natural frequency i.e., < 1% over 10 gRMS random vibration test. Electrical functions of the model were also tested without showing any anomalies during and after vacuum thermal cycling test with < $10^{-5}$ torr and $-30^{\circ}C\;-\;35^{\circ}C$. The imaging capability of the model, represented by a modulation transfer function (MTF) value at the Nyquist frequency, was also kept unvaried after all those environmental tests.

• Nuclear Engineering and Technology
• /
• v.55 no.7
• /
• pp.2380-2387
• /
• 2023

Hyperspectral data and its ability to explore the minerals and their associated rocks have a remarkable application in mineral exploration and lithological characterization. The present study aims to explore the radiation shielding aspects of the iron ore in Kerala with the aid of the Hyperion hyperspectral dataset. The reflectance-spectra obtained from the laboratory conditions as well as from the image show various absorptions. The results from the spectra are validated with geochemical data and GPS points. The Monte Carlo simulation employed to evaluate the radiation shielding ability. Raising the oxygen ions caused a noteworthy decrease in the µ values of the studied rocks which is accompanied by an increase in Δ_0.5 and Δ_eq values. The Δ_0.5 and Δ_eq values increased by factors of approximately 77 % with raising the oxygen ions between 44.32 and 47.57 wt.%. The µ values varies with the oxygen concentrations, where the µ values decreased from 2.531 to 0.925 cm^-1 (at 0.059 MeV), from 0.381to 0.215 cm^-1 (at 0.662 MeV), and from 0.279 to 0.158 cm^-1 (at 1.25 MeV) with raising the oxygen ions from 44.32 to 47.43 wt.%.