Loading...

When pixels team up: Spatially weighted sparse coding for hyperspectral image classification

Soltani Farani, A ; Sharif University of Technology | 2015

503 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/LGRS.2014.2328319
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2015
  4. Abstract:
  5. In this letter, a spatially weighted sparse unmixing approach is proposed as a front-end for hyperspectral image classification using a linear SVM. The idea is to partition the pixels of a hyperspectral image into a number of disjoint spatial neighborhoods. Since neighboring pixels are often composed of similar materials, their sparse codes are encouraged to have similar sparsity patterns. This is accomplished by means of a reweighted ℓ1 framework where it is assumed that fractional abundances of neighboring pixels are distributed according to a common Laplacian Scale Mixture (LSM) prior with a shared scale parameter. This shared parameter determines which endmembers contribute to the group of pixels. Experiments on the AVIRIS Indian Pines show that the model is very effective in finding discriminative representations for HSI pixels, especially when the training data is limited
  6. Keywords:
  7. hyperspectral imagery (HSI) ; linear support vector machines (SVMs) ; Classification (of information) ; Image classification ; Spectroscopy ; Support vector machines ; Dictionary learning ; Hyper-spectral images ; Hyperspectral image classification ; Similar material ; Sparsity patterns ; Spatial neighborhoods ; Pixels
  8. Source: IEEE Geoscience and Remote Sensing Letters ; Volume 12, Issue 1 , Jan , 2015 , Pages 107-111 ; 1545598X (ISSN)
  9. URL: http://ieeexplore.ieee.org/document/6842643