Data races are egregious concurrency bugs that are especially problematic in performance-oriented GPU codes where large thread counts and multiple shared memory regions tend to exacerbate them. In this work, we present a new dynamic data-race checker called HiRace, whose key novelty is an innovative state machine designed to capitalize on the bulk-synchronous hierarchical GPU programming model. This state machine condenses an arbitrarily long access history into a constant-size state. We evaluate HiRace on a large, calibrated data-race benchmark suite. In over 3,500 studied executions of 580 CUDA kernels, 346 of which contain data races, we found HiRace to detect races missed by other tools without raising false alarms and to be more than 10 times faster on average than the current state of the art with half the memory overhead.

There are a multitude of civilian and military applications for the detection of anomalous changes in hyperspectral images. Anomalous changes occur when the material within a pixel is replaced. Environmental factors that change over time, such as illumination, will affect the radiance of all the pixels in a scene, despite the materials within remaining constant. The goal of an anomalous change detection algorithm is to suppress changes caused by the environment, and detect pixels where the materials within have changed. Anomalous change detection is a two step process. Two co-registered images of a scene are first transformed to maximize the overall correlation between the images, then an anomalous change detector (ACD) is applied to the transformed images. The transforms maximize the correlation between the two images to attenuate the environmental differences that distract from the anomalous changes of importance. Several categories of transforms with different optimization parameters are discussed and compared. One of two types of ACDs are then applied to the transformed images. The first ACD uses the difference of the two transformed images. The second concatenates the spectra of two images and uses an aggregated ACD. A comparison of the two ACD methods and their effectiveness with the different transforms is done for the first time.

Most detection algorithms for hyperspectral imaging applications assume a target with a perfectly known spectral signature. In practice, the target signature is either imperfectly measured (target mismatch) and/or it exhibits spectral variability. The objective of this paper is to introduce a robust matched filter that takes the uncertainty and/or variability of target signatures into account. It is shown that, if we describe this uncertainty with an ellipsoid in the spectral space, we can design a matched filter that provides a response of the same magnitude for all spectra within this ellipsoid. Thus, by changing the size of this ellipsoid, we can control the "spectral selectivity" of the matched filter. The ability of the robust matched filter to deal effectively with target mismatch and spectral variability is demonstrated with hyperspectral imaging data from the HYDICE sensor.

The objective of this paper is to introduce a robust matched filter that takes the uncertainty or variability of target signatures into account. It is shown that, if we describe this uncertainty with an ellipsoid in the spectral space, we can design a matched filter that provides a response of the same magnitude for all spectra within this ellipsoid. Thus, by changing the size of this ellipsoid, we can control the "spectral selectivity" of the matched filter. Finally, we demonstrate the operation of the robust matched filter with real hyperspectral imaging data.

The objective of this paper is the statistical characterization of natural hyperspectral backgrounds using multivariate probability distribution models. We consider models based on elliptically contoured t-distributions and threshold models based on extreme value theory. Both models provide a level of accuracy for the "heavy-tails" of hyperspectral backgrounds, which is necessary for the implementation of constant false alarm rate detectors and their performance evaluation. The performance of these models is illustrated using data from the AVIRIS sensor.