Sparse Representation for Target Detection in Hyperspectral Imagery

• Published in: IEEE journal of selected topics in signal processing Vol. 5; no. 3; pp. 629 - 640
• Main Authors: Yi Chen, Nasrabadi, N M, Tran, T D
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2011; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Detectors; Dictionaries; Hyperspectral imagery; Imagery; Kernel; Mathematical analysis; Minimization; Object detection; Pixel; Pixels; sparse recovery; sparse representation; Sparsity; spatial correlation; Studies; Subspaces; Support vector machines; Target detection; Training; Vectors (mathematics)
• ISSN: 1932-4553; 1941-0484
• DOI: 10.1109/JSTSP.2011.2113170

In this paper, we propose a new sparsity-based algorithm for automatic target detection in hyperspectral imagery (HSI). This algorithm is based on the concept that a pixel in HSI lies in a low-dimensional subspace and thus can be represented as a sparse linear combination of the training samples. The sparse representation (a sparse vector corresponding to the linear combination of a few selected training samples) of a test sample can be recovered by solving an l 0 -norm minimization problem. With the recent development of the compressed sensing theory, such minimization problem can be recast as a standard linear programming problem or efficiently approximated by greedy pursuit algorithms. Once the sparse vector is obtained, the class of the test sample can be determined by the characteristics of the sparse vector on reconstruction. In addition to the constraints on sparsity and reconstruction accuracy, we also exploit the fact that in HSI the neighboring pixels have a similar spectral characteristic (smoothness). In our proposed algorithm, a smoothness constraint is also imposed by forcing the vector Laplacian at each reconstructed pixel to be minimum all the time within the minimization process. The proposed sparsity-based algorithm is applied to several hyperspectral imagery to detect targets of interest. Simulation results show that our algorithm outperforms the classical hyperspectral target detection algorithms, such as the popular spectral matched filters, matched subspace detectors, adaptive subspace detectors, as well as binary classifiers such as support vector machines.