Hyperspectral imagery leverages the use of spectral measurements to detect objects of interest in a scene that may not be discernable from their spatial patterns alone. This paper describes a project to make available to the community a set of hyperspectral airborne images on which anyone can run a target detection algorithm to find selected objects of interest in an image. The image and target spectral signatures are publicly available but the pixel location of targets within the image is withheld to allow for independent algorithm evaluation and scoring. To distribute these data, a website has been created which allows users to download the hyperspectral data and upload their target detection results which are then automatically scored. The Target Detection Blind Test website is located at

Abstract-Many researchers have presented results showing the empirical performance of target detection algorithms using hyperspectral or synthetic aperture radar imagery. In nearly all cases, these probabilities of detection and false alarm are presented as precise values as opposed to their true nature as estimates of random values. In this letter, we provide analytical tools and examples of computing confidence intervals and regions around these estimates commonly presented as points on receiver operating characteristic (ROC) curves. It is suggested that these tools be adopted by researchers when presenting their results to provide their audience with a quantitative metric for proper interpretation of empirically estimated ROC curves.

Characterization of the joint (among wavebands) probability density function (pdf) of hyperspectral imaging (HSI) data is crucial for several applications, including the design of constant false alarm rate (CFAR) detectors and statistical classifiers. HSI data are vector (or equivalently multivariate) data in a vector space with dimension equal to the number of spectral bands. As a result, the scalar statistics utilized by many detection and classification algorithms depend upon the joint pdf of the data and the vector-to--scalar mapping defining the specific algorithm. For reasons of analytical tractability, the multivariate Gaussian assumption has dominated the development and evaluation of algorithms for detection and classification in HSI data, although it is widely recognized that it does not always provide an accurate model for the data. The purpose ofthis paper is to provide a detailed investigation ofthejoint and marginal distributional properties of HSI data. To this end, we assess how well the multivanate Gaussian pdf describes HSI data using univariate techniques for evaluating marginal normality, and techniques that use unidimensional views (projections) of multivanate data. We show that the class of elliptically contoured distributions, which includes the multivariate normal distribution as a special case, provides a better characterization of the data. Finally, it is demonstrated that the class of univariate stable random variables provides a better model for the heavy-tailed output distribution of the well known matched filter target detection algorithm.

Abstract-Data from multispectral and hyperspectral imaging systems have been used in many applications including land cover classification, surface characterization, material identification, and spatially unresolved object detection. While these optical spectral imaging systems have provided useful data, their design and utility could be further enhanced by better understanding the sensitivities and relative roles of various system attributes; in particular, when application data product accuracy is used as a metric. To study system parameters in the context of land cover classification, an end-to-end remote sensing system modeling approach was previously developed. In this paper, we extend this model to subpixel object detection applications by including a linear mixing model for an unresolved object in a background and using object detection algorithms and probability of detection ( ) versus false alarm ( ) curves to characterize performance. Validations with results obtained from airborne hyperspectral data show good agreement between model predictions and the measured data. Examples are presented which show the utility of the modeling approach in understanding the relative importance of various system parameters and the sensitivity of versus curves to changes in the system for a subpixel road detection scenario.Index Terms-Hyperspectral imaging, multispectral imaging, remote sensing system modeling, subpixel object detection.