Remote sensing image classification based on Stacked Denoising Autoencoder

Peng Liang, Wenzhong Shi, Xiaokang Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

65 Citations (Scopus)


Focused on the issue that conventional remote sensing image classification methods have run into the bottlenecks in accuracy, a new remote sensing image classification method inspired by deep learning is proposed, which is based on Stacked Denoising Autoencoder. First, the deep network model is built through the stacked layers of Denoising Autoencoder. Then, with noised input, the unsupervised Greedy layer-wise training algorithm is used to train each layer in turn for more robust expressing, characteristics are obtained in supervised learning by Back Propagation (BP) neural network, and the whole network is optimized by error back propagation. Finally, Gaofen-1 satellite (GF-1) remote sensing data are used for evaluation, and the total accuracy and kappa accuracy reach 95.7% and 0.955, respectively, which are higher than that of the Support Vector Machine and Back Propagation neural network. The experiment results show that the proposed method can effectively improve the accuracy of remote sensing image classification.

Original languageEnglish
Article number16
JournalRemote Sensing
Issue number1
Publication statusPublished - 1 Jan 2018


  • Back Propagation neural network
  • Deep learning
  • Land cover classification
  • Stacked denoising autoencoder

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)


Dive into the research topics of 'Remote sensing image classification based on Stacked Denoising Autoencoder'. Together they form a unique fingerprint.

Cite this