Combining Radar and Optical Sensor Data to Measure Player Value in Baseball.

Evaluating a player's talent level based on batted balls is one of the most important and difficult tasks facing baseball analysts. An array of sensors has been installed in Major League Baseball stadiums that capture seven terabytes of data during each game. These data increase interest among spectators, but also can be used to quantify the performances of players on the field. The weighted on base average cube model has been used to generate reliable estimates of batter performance using measured batted-ball parameters, but research has shown that running speed is also a determinant of batted-ball performance. In this work, we used machine learning methods to combine a three-dimensional batted-ball vector measured by Doppler radar with running speed measurements generated by stereoscopic optical sensors. We show that this process leads to an improved model for the batted-ball performances of players.

Investigation of Key Variables Impacting ICM Sensing Using Computer Simulations.

The insertable cardiac monitors (ICMs) used for diagnosing and managing abnormal heart activities can falsely detect heart rhythms due to respiration, device rotation/orientation, device position, device flipping, and body mass that alter the amplitudes and morphologies. The objective of this paper is to investigate the effects of these key variables on ICM sensing by using computer simulations and virtual human family. We observed in these simulations that sensing amplitudes can vary greatly depending on device flipping, orientation/rotation, and migration; change significantly due to respiration effect; and are most sensitive to it when body mass is large. Those findings support identification of the key variables impacting clinical false detections.

Reflectance recovery for airborne sensor images of 3D scenes.

An airborne sensor measures the radiance spectrum, which is dependent on the spectral reflectance of the ground material, the orientation of the material surface, and the atmospheric and illumination conditions. We present an algorithm to estimate the surface spectral reflectance, given the sensor radiance spectrum corresponding to a single pixel. The algorithm uses a nonlinear physics-based image formation model. A low-dimensional linear subspace model is used for the reflectance spectra. The solar radiance, sky radiance, and path-scattered radiance are dependent on the environmental conditions and viewing geometry, and this interdependence is considered by using a coupled-subspace model for these spectra. The algorithm uses the Levenberg-Marquardt method to estimate the subspace model parameters. We have applied the algorithm to a large set of synthetic and real data.

Estimating visible through near-infrared spectral reflectance from a sensor radiance spectrum.

We show that surface spectral reflectance can be separated from illumination effects in visible through near-infrared (350 nm-1740 nm) hyperspectral data by using only the information in a single radiance spectrum. The separation method exploits the fact that reflectance and illumination spectra typically lie in distinct subspaces. We present a comparison of a linear and a nonlinear algorithm for the separation. These algorithms compute an estimate of the spectral reflectance up to a scaling factor. In addition, we present an iterative method that is used to determine the starting point for the nonlinear algorithm. We also develop a method for selecting the dimension of the reflectance and illumination subspaces that is appropriate for material identification applications. The accuracy of the separation methods is quantified by application to noisy visible through near-infrared spectral data with a database of 107 materials and 3000 illumination spectra. The utility of the separation method for material identification is demonstrated with the same database. The results show that accurate reflectance recovery and material identification is possible by use of visible through near-infrared spectral data over the outdoor environmental conditions represented in this data set.

Using independent component analysis for material estimation in hyperspectral images.

We develop a method for automated material estimation in hyperspectral images. The method models a hyperspectral pixel as a linear mixture of unknown materials. The method is particularly useful for applications in which material regions in a scene are smaller than one pixel. In contrast to many material estimation methods, the new method uses the statistics of large numbers of pixels rather than attempting to identify a small number of the purest pixels. The method is based on maximizing the independence of material abundances at each pixel. We show how independent component analysis algorithms can be adapted for use with this problem. We demonstrate properties of the method by application to airborne hyperspectral data.

Global spectral irradiance variability and material discrimination at Boulder, Colorado.

We analyze 7,258 global spectral irradiance functions over 0.4-2.2 microm that were acquired over a wide range of conditions at Boulder, Colorado, during the summer of 1997. We show that low-dimensional linear models can be used to capture the variability in these spectra over both the visible and the 0.4-2.2 microm spectral ranges. Using a linear model, we compare the Boulder data with the previous study of Judd et al. [J. Opt. Soc. Am. 54, 1031 (1964)] over the visible wavelengths. We also examine the agreement of the Boulder data with a spectral database generated by using the MODTRAN 4.0 radiative transfer code. We use a database of 223 minerals to consider the effect of the spectral variability in the global spectral irradiance functions on hyperspectral material identification. We show that the 223 minerals can be discriminated accurately over the variability in the Boulder data with subspace projection techniques.

Using reflectance models for color scanner calibration.

We examine the use of linear spectral reflectance models for calibrating a color scanner to generate device-independent CIE XYZ values from scanner vectors. Polynomial regression approaches to color scanner calibration use parameterized functions to approximate the calibration mapping over a set of training colors. These approaches can perform poorly if the parameterized functions do not accurately model the structure of the desired calibration mapping. Several studies have shown that linear reflectance models accurately characterize a wide range of materials. By viewing color scanner calibration as reflectance estimation, we can incorporate linear reflectance models into the calibration process. We show that in most cases linear models do not constrain the calibration problem sufficiently to allow exact recovery of X, Y, Z from a scanner vector obtained with three filters. By examining a series of methods that exploit information about reflectance functions, however, we show that reflectance information can be used to improve the accuracy of calibration over that of standard methods applied to the same set of inputs.

Invariant identification of material mixtures in airborne spectrometer data.

We present an algorithm for identifying linear mixtures of a specified set of materials in 0.4-2.5 microm airborne imaging spectrometer data. The algorithm is invariant to the illumination and atmospheric conditions and the relative amounts of the specified materials within a pixel. Only the spectral reflectance functions for the specified materials are required by the algorithm. Invariance over illumination and atmospheric conditions is achieved by incorporating a physical model for scene variability in the constrained optimization formulation. The algorithm also computes estimates of the amounts of the specified materials in identified mixtures. We demonstrate the effectiveness of the algorithm by using real and synthetic Hyperspectral Digital Imaging Collection Experiment imagery acquired over a range of conditions and altitudes.