Loading...

Remote Sensing of Hyperspectral Images for Detection Surface Mines

Motahari Kelarestaghi, Alireza | 2020

1756 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52677 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Amini, Arash
  7. Abstract:
  8. Hyperspectral unmixing (HU) is a method used to estimate the fractional abundances corresponding to endmembers in each of the mixed pixels in the hyperspectral remote sensing image. In recent times, deep learning has been recognized as an effective technique for hyperspectral image classification. In this thesis, an end-to-end HU method is proposed based on the convolutional neural network (CNN) and multi-layer perceptron (MLP). which consists of two steps: the first stage extracts features from the input data along with the inverse learning of the spectral library matrix in the hyperspectral image where columns represent the pure spectral of endmembers and The second stage is to estimate the fractional abundances corresponding to endmembers in each of the mixed pixels using the extracted features along with learning the spectral library as well as the noise reduction in the pixel image. In the following, we compare the performance of the proposed methods with previous methods available in Jasper Ridge, Samson, Urban and synthetic datasets in hyperspectral unmixing and show that it can improve the accuracy of it. Finally, we present the advantages and disadvantages of these methods along with suggestions for future research
  9. Keywords:
  10. Hyperspectral Unmixing ; Hyperspectral Images ; Convolutional Neural Network ; Multi-Layer Perceptron (MLP) ; Spectral Library

 Digital Object List

 Bookmark

...see more