Multiscale DenseNet Meets With Bi-RNN for Hyperspectral Image Classification

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 15; pp. 5401 - 5415
• Main Authors: Liang, Lianhui, Zhang, Shaoquan, Li, Jun
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Attention mechanism; bidirection recurrent neural network (Bi-RNN); Classification; Convolution; convolutional neural network (CNN); Convolutional neural networks; Correlation; Data mining; dense connected convolutional network (DenseNet); Exploitation; Feature extraction; hyperspectral image (HSI) classification; Hyperspectral imaging; Image classification; Kernel; Methods; Neural networks; Recurrent neural networks; Spacecraft recovery; Spatial data; Three-dimensional displays
• ISSN: 1939-1404; 2151-1535; 2151-1535
• DOI: 10.1109/JSTARS.2022.3187009

Convolutional neural network (CNN) has been successfully introduced to hyperspectral image (HSI) classification and achieved effective performance. With the depth of the CNN increases, it may cause the gradient to become zero, and the structure lacks the utilization of the correlated spatial feature information between different convolutional layers. At the same time, this single-scale convolution kernel is insufficient in expressing the complex spatial structure information of HSI. In addition, the CNN-based methods treat the HSIs spectral band data as a disordered vector in the process of feature extraction, which abandons the exploitation of its internal spectral correlations. To address these issues, we propose a novel spectral-spatial network classification framework based on multiscale dense connected convolutional network (DenseNet) and bidirection recurrent neural network (Bi-RNN) with attention mechanism network (MDRN). For the proposed MDRN, in terms of spatial feature extraction, a multiscale DenseNet is exploited to combine shallow and deep convolution features to extract the multiscale and complex spatial structure features at each layer. In the aspects of spectral feature extraction, Bi-RNN with attention mechanism is used to capture the inner spectral correlations within a continuous spectrum. Three standard real hyperspectral datasets were used to verify the effectiveness of the proposed MDRN approach. Experimental results indicate that the proposed MDRN method can make full use of the spectral and spatial information of the image, and it has better performance than some advanced algorithms in HSI classification. Finally, in the application of hyperspectral data captured by Gaofen-5 satellite, the practicability of the proposed MDRN method is also superior to other methods.