For many years, the entire target detection scientific community has felt the urge for fully ground-truthed hyperspectral imagery data sets expressly released for testing and comparing detection algorithms. Although a few excellent data-sharing efforts have been carried out in the last decade, the use of either restricted or not well ground-truthed imagery still remains a common practice in the target detection literature. In this paper, we provide an overview of a new hyperspectral data set that we release to the scientific community with the specific goal of fostering unbiased comparison and scientific discussions of anomaly detection (AD), object detection, and anomalous change detection (ACD) algorithms. The data set is fully ground-truthed and documented and includes scenarios and experiments specifically conceived for detection algorithm comparison and benchmarking. Insights about the various possible data exploitation tasks are provided by making reference to noise estimation and reduction, AD, spectral signature-based target detection (SSBTD), and ACD. Experimental results concerning ACD and SSBTD are presented and highlight the usefulness of this new data set from the data sharing and algorithmic comparison perspectives.

Hyperspectral Airborne “Viareggio 2013 Trial” Data Collection for Detection Algorithm Assessment

In this paper, we propose a novel sparsity-based algorithm for anomaly detection in hyperspectral imagery. The algorithm is based on the concept that a background pixel can be approximately represented as a sparse linear combination of its spatial neighbors while an anomaly pixel cannot if the anomalies are removed from its neighborhood. To be physically meaningful, the sum-to-one and nonnegativity constraints are imposed to abundance vector based on the linear mixture model, and the upper bound constraint on sparsity level is removed for better recovery of the test pixel. First, the proposed method utilizes the redundant background information to automatically remove anomalies from the background dictionary. Then, the reconstruction error obtained by the new background dictionary is directly used for anomaly detection. Moreover, a kernel version of the proposed method is also derived to completely exploit the nonlinear feature of hyperspectral data. An important advantage of the proposed methods is their capability to adaptively model the background even when some anomaly pixels are involved. Extensive experiments have been conducted on three real hyperspectral data sets. It is demonstrated that the proposed detectors achieve a promising detection performance with a relatively low computational cost.

A Constrained Sparse Representation Model for Hyperspectral Anomaly Detection

The functions of multiple instances (FUMI) approach for learning target and nontarget signatures is introduced. FUMI is a generalization of the multiple-instance learning (MIL) approach for supervised learning. FUMI differs significantly from standard MIL and supervised learning approaches because only data points which are functions of class concepts/signatures are available. In particular, this paper addresses the problem in which data points are convex combinations of target and nontarget signatures. Two algorithms, convex FUMI ( $c$ FUMI) and extended $c$ FUMI ( $e$ FUMI) , are presented and applied to the problem of hyperspectral unmixing and target detection. $c$ FUMI learns target and nontarget signatures (i.e., target and nontarget endmembers) , the number of nontarget signatures, and the proportion of each signature for every data point. The $e$ FUMI algorithm extends the $c$ FUMI to allow for additional “bag level” uncertainty in training labels. For these methods, training data need only binary labels indicating whether a data point (or some spatial area in the case of $e$ FUMI) contains or does not contain some proportion of the target; the specific target proportions for the training data are not needed. After learning the target signature using the binary-labeled training data, target detection can be performed on test data. Results for subpixel target detection on simulated and real airborne hyperspectral data are shown.

Functions of Multiple Instances for Learning Target Signatures

In this article, a two-stream convolutional network-based target detector (denoted as TSCNTD) for hyperspectral images is proposed. The TSCNTD utilizes the two-stream convolutional networks to extract abundant spectral information in hyperspectral images. For the background samples, the TSCNTD finds enough typical background pixels via a hybrid sparse representation and classification-based pixel selection strategy in the entire image. To tackle the problem under limited target samples, a novel synthesis method is proposed to generate sufficient target samples with a target priori and some typical background pixels. Once the target and background samples are obtained, then the designed two-stream convolutional networks were trained with a target priori, target samples, and background samples. During training, a target priori and a target sample, which construct a positive training sample, are considered as two inputs of the two-stream convolutional networks, while a target priori and a background sample construct a negative training sample. During testing, the test samples, which are constructed by a target priori and the detected pixels, are classified by the well-trained network. The outputs of the network constitute the final detection result of the TSCNTD. Extensive experiments were made on four benchmark hyperspectral images. The experimental results indicate that the TSCNTD can achieve superior performances in target detection.

Two-Stream Convolutional Networks for Hyperspectral Target Detection

A practical hyperspectral target characterization task estimates a target signature from imprecisely labeled training data. The imprecisions arise from the characteristics of the real-world tasks. First, accurate pixel-level labels on training data are often unavailable. Second, the subpixel targets and occluded targets cause the training samples to contain mixed data and multiple target types. To address these imprecisions, this paper proposes a new hyperspectral target characterization method to produce diverse multiple hyperspectral target signatures under a multiple instance learning (MIL) framework. The proposed method uses only bag-level training samples and labels, which solves the problems arising from the mixed data and lack of pixel-level labels. Moreover, by formulating a multiple characterization MIL and including a diversity-promoting term, the proposed method can learn a set of diverse target signatures, which solves the problems arising from multiple target types in training samples. The experiments on hyperspectral target detections using the learned multiple target signatures over synthetic and real-world data show the effectiveness of the proposed method.

Multiple Instance Learning for Multiple Diverse Hyperspectral Target Characterizations

A multi-modal (hyperspectral, multispectral, and LIDAR) imaging data collection campaign was conducted just south of Rochester New York in Avon, NY on September 20, 2012 by the Rochester Institute of Technology (RIT) in conjunction with SpecTIR, LLC, the Air Force Research Lab (AFRL), the Naval Research Lab (NRL), United Technologies Aerospace Systems (UTAS) and MITRE. The campaign was a follow on from the SpecTIR Hyperspectral Airborne Rochester Experiment (SHARE) from 2010. Data was collected in support of the eleven simultaneous experiments described here. The airborne imagery was collected over four different sites with hyperspectral, multispectral, and LIDAR sensors. The sites for data collection included Avon, NY, Conesus Lake, Hemlock Lake and forest, and a nearby quarry. Experiments included topics such as target unmixing, subpixel detection, material identification, impacts of illumination on materials, forest health, and in-water target detection. An extensive ground truthing effort was conducted in addition to collection of the airborne imagery. The ultimate goal of the data collection campaign is to provide the remote sensing community with a shareable resource to support future research. This paper details the experiments conducted and the data that was collected during this campaign.

https://www.cis.rit.edu/people/faculty/kerekes/pdfs/SPIE_2013_SHARE_Overview.pdf

Lauwrence Scarff

Papers

The SHARE 2012 data campaign