Abstract | ||
---|---|---|
This paper proposes a new method, called multilayer stacked covariance pooling (MSCP), for remote sensing scene classification. The innovative contribution of the proposed method is that it is able to naturally combine multilayer feature maps, obtained by pretrained convolutional neural network (CNN) models. Specifically, the proposed MSCP-based classification framework consists of the following t... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TGRS.2018.2845668 | IEEE Transactions on Geoscience and Remote Sensing |
Keywords | Field | DocType |
Feature extraction,Remote sensing,Nonhomogeneous media,Support vector machines,Covariance matrices,Computational modeling,Semantics | Data set,Convolutional neural network,Matrix (mathematics),Support vector machine,Remote sensing,Pooling,Feature extraction,Covariance matrix,Mathematics,Covariance | Journal |
Volume | Issue | ISSN |
56 | 12 | 0196-2892 |
Citations | PageRank | References |
7 | 0.44 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nanjun He | 1 | 42 | 3.70 |
Leyuan Fang | 2 | 116 | 11.15 |
Shutao Li | 3 | 191 | 16.15 |
Antonio Plaza | 4 | 83 | 17.35 |
Javier Plaza | 5 | 298 | 30.10 |