Open AccessClassification of hyperspectral images via improved cycle‐MLP
Author(s) -
Gong Na,
Zhang Chunlei,
Zhou Heng,
Zhang Kai,
Wu Zhongyuan,
Zhang Xin
Publication year - 2022
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/cvi2.12104
Subject(s) - hyperspectral imaging , artificial intelligence , computer science , pattern recognition (psychology) , feature extraction , feature (linguistics) , multilayer perceptron , convolution (computer science) , pixel , field (mathematics) , contextual image classification , image resolution , computer vision , artificial neural network , image (mathematics) , mathematics , philosophy , linguistics , pure mathematics
Pixel‐wise classification of hyperspectral image (HSI) is a hot spot in the field of remote sensing. The classification of HSI requires the model to be more sensitive to dense features, which is quite different from the modelling requirements of traditional image classification tasks. Cycle‐Multilayer Perceptron (MLP) has achieved satisfactory results in dense feature prediction tasks because it is an expert in extracting high‐resolution features. In order to obtain a more stable receptive field and enhance the effect of feature extraction in multiple directions, we propose an MLP‐like model called DriftNet for HSI classification inspired by Cycle‐MLP and deformable convolution. Besides, the proposed DriftNet uses a unique ladder‐like fully connected structure to achieve progressive activation of neurons and facilitates the fusion of spatial and spectral information, thereby obtaining more sensitive location information for better classification results. Experimental results on three public hyperspectral datasets demonstrate the effectiveness and generalisation of DriftNet.