M. Vigneshkumar

Bio: M. Vigneshkumar is an academic researcher. The author has contributed to research in topics: Hyperspectral imaging. The author has an hindex of 2, co-authored 3 publications receiving 6 citations.

Comparative classification approach in hyperion imagery

Abstract: The traditional approaches to estimate the Iron ore involves large manpower, cost and time. Iron ore identification is necessary due to the rapid increase in construction work, industries and population. Hyperspectral Imagery analysis used to estimate the Iron ore precisely depends on the spectral signature. The spectral signature of Iron ore shows huge absorption in 865 nm due to the presence of Iron content in the sample spectra. Hyperspectral imagery contains a large number of spectral bands and involves various processing steps such as identification of the calibration bands, absolute reflectance generation, data dimensional minimization, Iron ore endmembers extraction and classification. The radiance imagery absolute reflectance bands are carried out using FLAASH atmospheric correction module. The noiseless pure pixels are obtained using data dimensionality reduction techniques as spectral data reduction and spatial data reduction. The comparative analysis is performed between sub-pixel (LSU) and per-pixel (SAM) classification. The results showed that the sub-pixelbased classification produces a better distribution of Iron ore than the per pixel-based classification.

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology.

Abstract: Hyperspectral imaging is a nondestructive testing technology that integrates spectroscopy and iconology technologies, which enables us to quickly obtain both internal and external information of objects and identify crop seed varieties. First, the hyperspectral images of ten soybean seed varieties were collected and the reflectance was obtained. Savitzky-Golay smoothing (SG), first derivative (FD), standard normal variate (SNV), fast Fourier transform (FFT), Hilbert transform (HT), and multiplicative scatter correction (MSC) spectral reflectance pretreatment methods were used. Then, the feature wavelengths and feature information of the pretreated spectral reflectance data were extracted using competitive adaptive reweighted sampling (CARS), the successive projections algorithm (SPA), and principal component analysis (PCA). Finally, 5 classifiers, Bayes, support vector machine (SVM), k-nearest neighbor (KNN), ensemble learning (EL), and artificial neural network (ANN), were used to identify seed varieties. The results showed that MSC-CARS-EL had the highest accuracy among the 90 combinations, with training set, test set, and 5-fold cross-validation accuracies of 100%, 100%, and 99.8%, respectively. Moreover, the contribution of spectral pretreatment to discrimination accuracy was higher than those of feature extraction and classifier selection. Pretreatment methods determined the range of the identification accuracy, feature-selective methods and classifiers only changed within this range. The experimental results provide a good reference for the identification of other crop seed varieties.

Alteration mineral mapping using ETM+ and hyperion remote sensing data at Bau gold field, Sarawak, Malaysia

Abstract: The area under investigation is the Bau gold mining district in the State of Sarawak, East Malaysia, on the island of Borneo. It has tropical climate with limited bedrock exposures. Bau is a gold field similar to Carlin style gold deposits. Geological analyses coupled with remote sensing data were used to detect hydrothermally altered rocks associated with gold mineralization. The Landsat Enhanced Thematic Mapper+ (ETM+) and Hyperion data were used to carry out mineral mapping of mineralized zones in the study area and surrounding terrain. Directed Principal Components Analysis (DPCA) transformation of four appropriate ETM+ band ratios were applied to produce DPC images, allowing the removal of the effects of vegetation from ETM+ data and the detection of separate mineral images at a regional scale. Linear Spectral Unmixing (LSU) was used to produce image maps of hydroxyl-bearing minerals using Hyperion data at a district scale. Results derived from the visible and near infrared and shortwave infrared bands of Hyperion represented iron oxide/hydroxide and clay minerals rich zones associated with the known gold prospects in the Bau district. The results show that the known gold prospects and potentially interesting areas are recognizable by the methods used, despite limited bedrock exposure in this region and the constraints imposed by the tropical environment. The approach used in this study can be more broadly applicable to provide an opportunity for detecting potentially interesting areas of gold mineralization using the ETM+ and Hyperion data in the tropical/sub-tropical regions.

Evaluation of Sentinel 1–derived and open-access digital elevation model products in mountainous areas of Western Ghats, India

Abstract: Digital elevation model, acquired and generated using manual field survey, stereo pairs, interferometric synthetic aperture radar (InSAR) and light detection and ranging techniques to characterize terrain topography, plays a dynamic role in geological and hydrological applications. Digital elevation models (DEMs) are subjected to comprise ineradicable faults owing to acquirement techniques and pre-processing methodologies. Experiencing non-uniform variation in accuracy, it is mandatory to assess the accuracy of DEMs before employing it for numerous purposes. Considering the fact, assessment of vertical and horizontal accuracies of open-access DEMs and InSAR-derived DEM is performed with Survey of India (SOI) toposheets as reference. Results concluded that Cartosat DEM and SRTM DEM of 30 m resolution with NRMSE as 10.5% and 10%, respectively, and PBIAS as − 0.3% and − 0.5% respectively highly correlated with the toposheet elevation when compared with other DEMs. Horizontal assessment of pixel offset concluded that Cartosat and SRTM DEM experience an offset of 0.1% along X-axis and 0.33% along Y-axis. Assessment of vertical accuracy and pixel offset concluded that CartoDEM and SRTM DEM are highly recommended for research purposes over Kodagu District, Karnataka, India. InSAR-derived DEM experiences massive variation and are not suggested over hilly terrains.

Enhancement of limestone mineral identification using Hyperion imagery: a case study from Tirunelveli District, Tamil Nadu, South India

Abstract: Hyperspectral remote sensing consolidates imaging and spectroscopy in a solitary system which frequently comprises big datasets and necessitates the novel processing methods. In the present study, Cheranmadevi Block of Tirunelveli District in Tamil Nadu is selected to extract the abundant limestone mineral. Hyperion is one of the freely available hyperspectral imagery containing 242 spectral bands with 10-nm intervals in the wavelength between 400 and 2500 nm. The main objectives of the present research work are to enhance the imagery visualization, end member extraction, and classification, and estimate the abundant limestone quantity by removing the striping error in Hyperion imagery. The scanning electron microscope with energy-dispersive X-ray spectroscopy analysis is performed to identify the chemical composition of limestone mineral. The spectral reflectance of limestone is characterized using analytical spectral devices like a field spectroradiometer. Limestone has deep absorption in the short-wave infrared region (1900–2500 nm) around 2320–2340 nm due to their calcite composition (CaCO3). The feature extraction in Hyperion data is performed using various preprocessing steps like bad bands removal, vertical strip removal, and radiance and reflectance creation. To improve the classification accuracy, vertical strip removal process is performed using a local destriping algorithm. The absolute reflectance is achieved by the atmospheric correction module using Fast Line-of-sight Atmospheric Analysis of Hypercubes. The acquired reflectance image spectra are compared with the spectral libraries of USGS, JPL, and field spectra. Destriping enhances qualities of Hyperion data interims of the spectral profile, radiance, reflectance, and data reduction methods. The present research work focused on the local destriping algorithm to increase the quality and quantity of limestone deposit extraction.