AUTOMATIC HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON DEEP FEATURE FUSION NETWORK, 363-373.
Yunfei Zhang,∗ Yuelong Zhu,∗ Hexuan Hu,∗ and Hongyan Wang∗∗
Keywords
Hyperspectral image classification, 2D–3D fusion strategy, featureextraction, feature fusion
Abstract
The traditional machine learning algorithm always pays attention
to spectral features on automatic hyperspectral image (HSI) clas-
sification, and there exists insufficient feature extraction under the
condition of small samples. In addition, the generalization ability
of the model is not strong. In this paper, a novel method named
specific two-dimensional–three-dimensional fusion strategy is pro-
posed, which uses a spatial–spectral feature fusion network based on
two-dimensional convolution and three-dimensional convolution to
extract the rich features, so as to keep the spatial and spectral infor-
mation intact. The validity of this method is verified by comparing
different classification algorithms. Experiments were carried out on
three widely used HSI data sets (i.e. Indian Pines, Salinas and
Pavia University). In case of small training sets, the experimental
results show that the proposed method outperforms the existing
methods.
Important Links:
Go Back