Discriminative Graphical Models for Sparsity-Based Hyperspectral Target Detection

Abstract

The inherent discriminative capability of sparse representations has been exploited recently for hyperspectral target detection. This approach relies on the observation that the spectral signature of a pixel can be represented as a linear combination of a few training spectra drawn from both target and background classes. The sparse representation corresponding to a given test spectrum captures class-specific discriminative information crucial for detection tasks. Spatiospectral information has also been introduced into this framework via a joint sparsity model that simultaneously solves for the sparse features for a group of spatially local pixels, since such pixels are highly likely to have similar spectral characteristics. In this paper, we propose a probabilistic graphical model framework that can explicitly learn the class conditional correlations between these distinct sparse representations corresponding to different pixels in a spatial neighborhood. Simulation results show that the proposed algorithm outperforms classical hyperspectral target detection algorithms as well as support vector machines.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2012
Accession Number
ADA580458

Entities

People

  • Nasser M. Nasrabadi
  • Trac D. Tran
  • Umamahesh Srinivas
  • Vishal Monga
  • Yi Chen

Organizations

  • Johns Hopkins University

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Compressed Sensing
  • Computational Complexity
  • Detection
  • Detectors
  • Dictionaries
  • False Alarms
  • Feature Extraction
  • Information Science
  • Machine Learning
  • Probability
  • Probability Distributions
  • Random Variables
  • Spectra
  • Supervised Machine Learning
  • Target Detection

Fields of Study

  • Computer science

Readers

  • Image Processing and Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML