Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Geography and cartography computing

More general concepts than this:

1-1 of 1 results

Filter by subject:

< Any subject

  • Physics [1]
  • General [1]
  • Mathematical methods in physics [1]
  • Probability theory, stochastic processes, and statistics [1]
  • Geophysics, astronomy and astrophysics [1]
  • Geophysical observations, instrumentation, and techniques [1]
  • Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research [1]
  • Electrical and electronic engineering [1]
  • General topics, engineering mathematics and materials science [1]
  • Engineering mathematics and mathematical techniques [1]
  • See more See less

Filter by content type:

< Any content type

  • Article [1]

Filter by publication date:

Filter by author:

< Any author

  • Chunmei Qing [1]
  • Jaime Zabalza [1]
  • Jiawei Ruan [1]
  • Jinchang Ren [1]
  • Xiangmin Xu [1]
Spatial-spectral classification of hyperspectral images: a deep learning framework with Markov Random fields based modelling
Author(s): Chunmei Qing, Jiawei Ruan, Xiangmin Xu, Jinchang Ren, Jaime Zabalza
Source: IET Image Processing, Volume 13, Issue 2, February 2019, p. 235 - 245
Type: Article
+ Show details - Hide details

For the spatial-spectral classification of hyperspectral images (HSIs), a deep learning framework is proposed in this study, which consists of convolutional neural networks (CNNs) and Markov random fields (MRFs). Firstly, a CNN model to learn the deep spectral feature from the HSI is built and the class posterior probability distribution is estimated. The CNN with a dropout layer can relieve the overfitting in classification. The CNN is utilised as a pixel-classifier, so it only works in the spectral domain. Then, the spatial information will be encoded by MRF-based multilevel logistic prior for regularising the classification. To derive the correlation of both spectral and spatial features for improving algorithm performance, the marginal probability distribution in HSI is learned using MRF-based loopy belief propagation. In comparison with several state-of-the-art approaches for data classification on three publicly available HSI datasets, experimental results have demonstrated the superior performance of the proposed methodology.

Add to favourites
Export citations
Items per page 20 | 50 | 100
Print this page
This is a required field
Please enter a valid email address