Dr. Robert S. Rand Profile

Dr. Robert S. Rand

Project Scientist at R3-Experts Inc

SPIE Involvement:

Author

Publications (28)

SPIE Journal Paper | 5 June 2018 Open Access

Full-range, solar-reflected hyperspectral microscopy to support earth remote sensing research

E. Terrence Slonecker, David Allen, Ronald Resmini, Robert Rand, Emily Paine

JARS, Vol. 12, Issue 02, 026024, (June 2018) https://doi.org/10.1117/12.10.1117/1.JRS.12.026024

KEYWORDS: Microscopy, Reflectivity, Sensors, Microscopes, Remote sensing, Hyperspectral imaging, Feldspar, Spectrometers, Imaging spectroscopy, Minerals

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 14 May 2018 Presentation

Deep learning with convolutional fiber filters for spectral analysis of hyperspectral imagery (Conference Presentation)

Robert Rand

Proceedings Volume 10644, 106440J (2018) https://doi.org/10.1117/12.2305291

KEYWORDS: Optical filters, Image filtering, Hyperspectral imaging, Image analysis, Image classification, Convolutional neural networks, Spatial filters, RGB color model, Convolution, Neural networks

Read Abstract +

SPIE Journal Paper | 11 January 2017 Open Access

Modeling linear and intimate mixtures of materials in hyperspectral imagery with single-scattering albedo and kernel approaches

Robert Rand, Ronald Resmini, David Allen

JARS, Vol. 11, Issue 01, 016005, (January 2017) https://doi.org/10.1117/12.10.1117/1.JRS.11.016005

KEYWORDS: Reflectivity, Hyperspectral imaging, RGB color model, Vegetation, Composites, Data modeling, Sensors, Diagnostics, Glasses, Error analysis

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 19 September 2016 Presentation + Paper

Abundance estimation of solid and liquid mixtures in hyperspectral imagery with albedo-based and kernel-based methods

Robert Rand, Ronald Resmini, David Allen

Proceedings Volume 9976, 99760M (2016) https://doi.org/10.1117/12.2239253

KEYWORDS: Solids, Liquids, Scattering, Reflectivity, Data modeling, Hyperspectral imaging, Sensors, Statistical analysis, RGB color model, Glasses

Read Abstract +

SPIE Journal Paper | 19 July 2016 Open Access

Distributed adaptive framework for multispectral/hyperspectral imagery and three-dimensional point cloud fusion

Robert Rand, Timothy Khuon, Eric Truslow

OE, Vol. 55, Issue 07, 073101, (July 2016) https://doi.org/10.1117/12.10.1117/1.OE.55.7.073101

KEYWORDS: Neural networks, Image segmentation, Sensors, Scanning electron microscopy, LIDAR, Expectation maximization algorithms, Image fusion, Clouds, Image classification, Data fusion

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 1 September 2015 Paper

Characterizing intimate mixtures of materials in hyperspectral imagery with albedo-based and kernel-based approaches

Robert Rand, Ronald Resmini, David Allen

Proceedings Volume 9611, 961112 (2015) https://doi.org/10.1117/12.2190067

KEYWORDS: Reflectivity, RGB color model, Hyperspectral imaging, Scattering, Composites, Data modeling, Glasses, Sensors, Remote sensing, Diagnostics

Read Abstract +

Proceedings Article | 15 September 2014 Paper

Using kernel-based and single-scattering albedo approaches for generalized spectral mixture analysis of hyperspectral imagery

Robert Rand, Ronald Resmini

Proceedings Volume 9222, 92220J (2014) https://doi.org/10.1117/12.2063278

KEYWORDS: Vegetation, RGB color model, Reflectivity, Composites, Scattering, Hyperspectral imaging, Diagnostics, Calibration, Sensors, Statistical modeling

Read Abstract +

Proceedings Article | 20 June 2014 Paper

Invariant-feature-based adaptive automatic target recognition in obscured 3D point clouds

Timothy Khuon, Charles Kershner, Enrico Mattei, Arnel Alverio, Robert Rand

Proceedings Volume 9091, 90911F (2014) https://doi.org/10.1117/12.2064801

KEYWORDS: Clouds, Neural networks, Sensors, Feature extraction, LIDAR, Detection and tracking algorithms, 3D acquisition, Automatic target recognition, Super resolution, Neurons

Read Abstract +

Target recognition and classification in a 3D point cloud is a non-trivial process due to the nature of the data collected from a sensor system. The signal can be corrupted by noise from the environment, electronic system, A/D converter, etc. Therefore, an adaptive system with a desired tolerance is required to perform classification and recognition optimally. The feature-based pattern recognition algorithm architecture as described below is particularly devised for solving a single-sensor classification non-parametrically. Feature set is extracted from an input point cloud, normalized, and classifier a neural network classifier. For instance, automatic target recognition in an urban area would require different feature sets from one in a dense foliage area. The figure above (see manuscript) illustrates the architecture of the feature based adaptive signature extraction of 3D point cloud including LIDAR, RADAR, and electro-optical data. This network takes a 3D cluster and classifies it into a specific class. The algorithm is a supervised and adaptive classifier with two modes: the training mode and the performing mode. For the training mode, a number of novel patterns are selected from actual or artificial data. A particular 3D cluster is input to the network as shown above for the decision class output. The network consists of three sequential functional modules. The first module is for feature extraction that extracts the input cluster into a set of singular value features or feature vector. Then the feature vector is input into the feature normalization module to normalize and balance it before being fed to the neural net classifier for the classification. The neural net can be trained by actual or artificial novel data until each trained output reaches the declared output within the defined tolerance. In case new novel data is added after the neural net has been learned, the training is then resumed until the neural net has incrementally learned with the new novel data. The associative memory capability of the neural net enables the incremental learning. The back propagation algorithm or support vector machine can be utilized for the classification and recognition.

Proceedings Article | 13 June 2014 Paper

An analysis of the nonlinear spectral mixing of didymium and soda-lime glass beads using hyperspectral imagery (HSI) microscopy

Ronald Resmini, Robert Rand, David Allen, Christopher Deloye

Proceedings Volume 9088, 90880Z (2014) https://doi.org/10.1117/12.2051434

KEYWORDS: Reflectivity, Glasses, Hyperspectral imaging, Microscopy, Remote sensing, Soda-lime glass, Spectroscopy, Sensors, Particles, Microscopes

Read Abstract +

Nonlinear spectral mixing occurs when materials are intimately mixed. Intimate mixing is a common characteristic of granular materials such as soils. A linear spectral unmixing inversion applied to a nonlinear mixture will yield subpixel abundance estimates that do not equal the true values of the mixture's components. These aspects of spectral mixture analysis theory are well documented. Several methods to invert (and model) nonlinear spectral mixtures have been proposed. Examples include Hapke theory, the extended endmember matrix method, and kernel-based methods. There is, however, a relative paucity of real spectral image data sets that contain well characterized intimate mixtures. To address this, special materials were custom fabricated, mechanically mixed to form intimate mixtures, and measured with a hyperspectral imaging (HSI) microscope. The results of analyses of visible/near-infrared (VNIR; 400 nm to 900 nm) HSI microscopy image cubes (in reflectance) of intimate mixtures of the two materials are presented. The materials are spherical beads of didymium glass and soda-lime glass both ranging in particle size from 63 m to 125 m. Mixtures are generated by volume and thoroughly mixed mechanically. Three binary mixtures (and the two endmembers) are constructed and emplaced in the wells of a 96-well sample plate: 0%/100%, 25%/75%, 50%/50%, 80%/20%, and 100%/0% didymium/soda-lime. Analysis methods are linear spectral unmixing (LSU), LSU applied to reflectance converted to single-scattering albedo (SSA) using Hapke theory, and two kernel-based methods. The first kernel method uses a generalized kernel with a gamma parameter that gauges non-linearity, applying the well-known kernel trick to the least squares formulation of the constrained linear model. This method attempts to determine if each pixel in a scene is linear or non-linear, and adapts to compute a mixture model at each pixel accordingly. The second method uses 'K-hype' with a polynomial (quadratic) kernel. LSU applied to the reflectance spectra of the mixtures produced poor abundance estimates regardless of the constraints applied in the inversion. The 'K-hype' kernel-based method also produced poor fraction estimates. The best performers are LSU applied to the reflectance spectra converted to SSA using Hapke theory and the gamma parameter kernel-based method.

Proceedings Article | 23 September 2013 Paper

Automated endmember determination and adaptive spectral mixture analysis using kernel methods

Robert Rand, Amit Banerjee, Joshua Broadwater

Proceedings Volume 8870, 88700Q (2013) https://doi.org/10.1117/12.2026728

KEYWORDS: RGB color model, Vegetation, Composites, Neodymium, Reflectivity, Calibration, Radon, Coastal modeling, Mathematical modeling, Sensors

Read Abstract +

Proceedings Article | 15 October 2012 Paper

Background suppression and feature based spectroscopy methods for sub-pixel material identification

Robert Rand, John Grossmann, Roger Clark, Eric Livo, J. Parr

Proceedings Volume 8515, 85150K (2012) https://doi.org/10.1117/12.930469

KEYWORDS: Absorption, Sensors, Single mode fibers, Optical filters, Imaging spectroscopy, Hassium, Spectroscopy, Statistical modeling, Remote sensing, RGB color model

Read Abstract +

Proceedings Article | 10 May 2012 Paper

Spectral and spatial algorithm architecture for classification of hyperspectral and LIDAR

Robert Rand, Timothy Khuon

Proceedings Volume 8407, 840702 (2012) https://doi.org/10.1117/12.918514

KEYWORDS: Neural networks, LIDAR, Sensors, Sensor fusion, Scanning electron microscopy, Expectation maximization algorithms, Data fusion, Image fusion, Image classification, Clouds

Read Abstract +

Proceedings Article | 7 September 2011 Paper

Feature-based and statistical methods for analyzing the Deepwater Horizon oil spill with AVIRIS imagery

Robert Rand, Roger Clark, K. Eric Livo

Proceedings Volume 8158, 81580N (2011) https://doi.org/10.1117/12.894909

KEYWORDS: Absorption, Statistical methods, Statistical analysis, Calibration, Sensors, Imaging spectroscopy, Reflectivity, Optical filters, Spectroscopy, Hyperspectral imaging

Read Abstract +

Proceedings Article | 13 August 2010 Paper

Oscillatory correlation for scene segmentation of hyperspectral imagery for geospatial analysis

Robert Rand

Proceedings Volume 7812, 78120F (2010) https://doi.org/10.1117/12.862048

KEYWORDS: Oscillators, Image segmentation, Hyperspectral imaging, Roads, Buildings, Image analysis, Spectral data processing, Sensors, Dynamical systems, Composites

Read Abstract +

Proceedings Article | 18 August 2009 Paper

A neural network approach for improved detector performance of spectral matched filters in hyperspectral imagery

Robert Rand

Proceedings Volume 7457, 74570T (2009) https://doi.org/10.1117/12.825748

KEYWORDS: Sensors, Single mode fibers, Optical filters, Statistical analysis, Neural networks, Hyperspectral imaging, Sensor performance, Digital filtering, Image filtering, Metals

Read Abstract +

Proceedings Article | 11 April 2008 Paper

How to design synthetic images to validate and evaluate hyperspectral imaging algorithms

Yu-Cherng Channing Chang, Hsuan Ren, Chein-I Chang, Robert Rand

Proceedings Volume 6966, 69661P (2008) https://doi.org/10.1117/12.777717

KEYWORDS: Algorithm development, Minerals, Detection and tracking algorithms, Signal to noise ratio, Calcite, Target detection, Hyperspectral imaging, Interference (communication), Computer simulations, Data modeling

Read Abstract +

Proceedings Article | 24 September 2007 Paper

Exploitation of hyperspectral imagery using adaptive resonance networks

Robert Rand

Proceedings Volume 6696, 66960M (2007) https://doi.org/10.1117/12.734918

KEYWORDS: Neural networks, Fuzzy logic, Hyperspectral imaging, Niobium, Image classification, Sodium, Dimension reduction, Binary data, Distance measurement, Data modeling

Read Abstract +

Proceedings Article | 17 April 2006 Paper

A biologically inspired neural oscillator network for geospatial analysis

Robert Rand, DeLiang Wang

Proceedings Volume 6247, 62470N (2006) https://doi.org/10.1117/12.665040

KEYWORDS: Oscillators, Image segmentation, Data modeling, Neural networks, Biological research, Biological neural networks, Network security, Analytical research, Dynamical systems, Scene simulation

Read Abstract +

Proceedings Article | 16 September 2005 Paper

Separating patterns and finding the independent components of mixed signals based on non-Gaussian distribution properties

Robert Rand, Hao Chen, Pramod Varshney

Proceedings Volume 5909, 59091G (2005) https://doi.org/10.1117/12.615427

KEYWORDS: Independent component analysis, Sensors, Data modeling, Landsat, Target detection, Statistical analysis, Signal processing, Scene classification, Spatial resolution, Earth observing sensors

Read Abstract +

Proceedings Article | 4 November 2004 Paper

Fundamental reformulation of the radiative transport equation

Henry Berger, Robert Rand

Proceedings Volume 5543, (2004) https://doi.org/10.1117/12.559773

KEYWORDS: Differential equations, Partial differential equations, Radiative transfer, Scattering, Diffusion, Neodymium, Infrared sensors, Infrared radiation, Remote sensing, Mass attenuation coefficient

Read Abstract +

Proceedings Article | 2 November 2004 Paper

Wavelet-based feature indices as a data mining tool for hyperspectral imagery exploitation

Edmundo Simental, Edward Bosch, Robert Rand

Proceedings Volume 5558, (2004) https://doi.org/10.1117/12.559510

KEYWORDS: Wavelets, Vegetation, Feature extraction, Roads, Hyperspectral imaging, Buildings, Data mining, Sensors, Composites, Calibration

Read Abstract +

Proceedings Article | 12 August 2004 Paper

The effect of wavelet-based dimension reduction on neural network classification and subpixel targeting algorithms

Robert Rand, Edward Bosch

Proceedings Volume 5425, (2004) https://doi.org/10.1117/12.542696

KEYWORDS: Detection and tracking algorithms, Wavelets, Dimension reduction, Neural networks, Hyperspectral imaging, Principal component analysis, Evolutionary algorithms, Image classification, Algorithms, Digital filtering

Read Abstract +

Proceedings Article | 23 September 2003 Paper

A physically constrained localized linear mixing model for TERCAT applications

Robert Rand

Proceedings Volume 5093, (2003) https://doi.org/10.1117/12.485935

KEYWORDS: Image processing, Shape memory alloys, Hassium, Vegetation, Process modeling, Metals, Bridges, Hyperspectral imaging, Associative arrays, Sensors

Read Abstract +

Proceedings Article | 18 December 2002 Paper

Time domain scattering of traveling wave radiance

Henry Berger, Robert Rand

Proceedings Volume 4818, (2002) https://doi.org/10.1117/12.453705

KEYWORDS: Differential equations, Scattering, Radiative transfer, Mendelevium, Light scattering, Palladium, Partial differential equations, Wave propagation, Infrared sensors, Infrared radiation

Read Abstract +

Proceedings Article | 2 August 2002 Paper

Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method

Robert Rand

Proceedings Volume 4725, (2002) https://doi.org/10.1117/12.478757

KEYWORDS: Hyperspectral imaging, Image classification, Algorithm development, Annealing, Algorithms, Image processing, Visualization, Roads, Spatial resolution, Surface plasmons

Read Abstract +

Proceedings Article | 8 February 2002 Paper

New physical understanding of a type of idealized scattering and the implications of the method of solution used

Henry Berger, Robert Rand

Proceedings Volume 4486, (2002) https://doi.org/10.1117/12.455112

KEYWORDS: Radiative transfer, Differential equations, Scattering, Partial differential equations, Palladium, Wave propagation, Light scattering, Atmospheric optics, Atmospheric sensing, Infrared sensors

Read Abstract +

Proceedings Article | 20 August 2001 Paper

Evaluation of matrix factorization method for data reduction and the unsupervised clustering of hyperspectral data using second-order statistics

Edward Bosch, Robert Rand

Proceedings Volume 4381, (2001) https://doi.org/10.1117/12.437020

KEYWORDS: Databases, Principal component analysis, Dimension reduction, Image processing algorithms and systems, Hyperspectral imaging, Image analysis, Statistical analysis, Matrices, Sensors, Wavelets

Read Abstract +

Proceedings Article | 20 August 2001 Paper

Gibbs-based unsupervised segmentation approach to partitioning hyperspectral imagery for terrain applications

Robert Rand, Daniel Keenan

Proceedings Volume 4381, (2001) https://doi.org/10.1117/12.437018

KEYWORDS: Hyperspectral imaging, Image segmentation, Distance measurement, Algorithm development, Image processing, Vegetation, Shape memory alloys, Calibration, Image resolution, Annealing

Read Abstract +

Showing 5 of 28 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years