Litcius/Paper detail

A Novel 2D-3D CNN with Spectral-Spatial Multi-Scale Feature Fusion for Hyperspectral Image Classification

Dongxu Liu, Guangliang Han, Peixun Liu, Hang Yang, Xinglong Sun, Qingqing Li, Jiajia Wu

2021Remote Sensing32 citationsDOIOpen Access PDF

Abstract

Multifarious hyperspectral image (HSI) classification methods based on convolutional neural networks (CNN) have been gradually proposed and achieve a promising classification performance. However, hyperspectral image classification still suffers from various challenges, including abundant redundant information, insufficient spectral-spatial representation, irregular class distribution, and so forth. To address these issues, we propose a novel 2D-3D CNN with spectral-spatial multi-scale feature fusion for hyperspectral image classification, which consists of two feature extraction streams, a feature fusion module as well as a classification scheme. First, we employ two diverse backbone modules for feature representation, that is, the spectral feature and the spatial feature extraction streams. The former utilizes a hierarchical feature extraction module to capture multi-scale spectral features, while the latter extracts multi-stage spatial features by introducing a multi-level fusion structure. With these network units, the category attribute information of HSI can be fully excavated. Then, to output more complete and robust information for classification, a multi-scale spectral-spatial-semantic feature fusion module is presented based on a Decomposition-Reconstruction structure. Last of all, we innovate a classification scheme to lift the classification accuracy. Experimental results on three public datasets demonstrate that the proposed method outperforms the state-of-the-art methods.

Topics & Concepts

Hyperspectral imagingPattern recognition (psychology)Computer scienceArtificial intelligenceFeature extractionFeature (linguistics)Convolutional neural networkFusionSpatial analysisContextual image classificationImage (mathematics)Remote sensingGeographyPhilosophyLinguisticsRemote-Sensing Image ClassificationRemote Sensing and Land UseAdvanced Image Fusion Techniques
A Novel 2D-3D CNN with Spectral-Spatial Multi-Scale Feature Fusion for Hyperspectral Image Classification | Litcius