Dictionaries of deep features for land-use scene classification of very high spatial resolution images

作者：

Highlights：

• A very high spatial resolution images land-use classification scheme is proposed.

• The proposed method relies on dictionaries of deep features.

• These dictionaries are very discriminative and compact.

• Likelihoods are linked to the sparse representation approach.

• The proposed method can be competitive in a comparison with the state-of-the-art.

摘要

•A very high spatial resolution images land-use classification scheme is proposed.•The proposed method relies on dictionaries of deep features.•These dictionaries are very discriminative and compact.•Likelihoods are linked to the sparse representation approach.•The proposed method can be competitive in a comparison with the state-of-the-art.

论文关键词：Deep learning,Dictionary learning,Feature learning,Land-use classification,Sparse representation

论文评审过程：Received 29 January 2018, Revised 30 November 2018, Accepted 16 December 2018, Available online 17 December 2018, Version of Record 27 December 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.12.019