Abstract

Although hyperspectral remote sensing images have rich spectral features, for small samples of remote sensing images, feature selection, feature mining, and feature integration are very important. A single model is difficult to apply to multiple tasks such as feature selection, feature mining, and feature integration during training, resulting in poor classification results for small sample classification of hyperspectral images. To improve the classification of small samples, a sequential joint deep learning algorithm is proposed in this paper. (In this algorithm, the deep features of multiscale convolution under an attention mechanism are integrated by using Bidirectional Long Short-Term Memory(Bi-LSTM) and AML.) First, we used principal component analysis (PCA) to reduce the dimensionality of the hyperspectral data and retain their key features. Second, the model uses an integrated attention mechanism to distribute the probability weight of the key input feature. Third, the model uses multiscale convolution to mine features after the distribution weight to obtain deep features. Fourth, the model uses bidirectional long short-term memory (Bi-LSTM) to integrate the convolution results at different scales. Finally, the softmax classifier is used to complete the classification of multiclass hyperspectral remote sensing images. Experiments were carried out on three public hyperspectral data sets, and the results proved that our proposed AML algorithm is effective, thus demonstrating powerful performance in the prediction of hyperspectral images (HSIs) of small samples.

Highlights

  • Hyperspectral images (HSIs) contain hundreds of bands in each pixel

  • To solve the above problems, we propose a sequential joint deep learning algorithm [27](The Deep features of Multi-scale convolution under Attention Mechanism are integrated by bidirectional long short-term memory (Bi-long short-term memory (LSTM)), AML)

  • The results show that the algorithm is efficient and suitable for hyperspectral remote sensing image classification

Read more

Summary

Introduction

Hyperspectral images (HSIs) contain hundreds of bands in each pixel. Due to the richness of the hyperspectral image spectrum, HSIs are widely used in agriculture [1], forestry [2], and urban topography [3]. The rich bands bring sufficient features to HSIs while producing many redundant features. Researchers have proposed new methods for solving redundant features and choosing useful features. Nie et al [9] proposed a model for the automatic weighting of features to minimize redundant features. By establishing relative cosine distances for different redundant features, Ayinde et al [10] eliminated many redundant features and reduced model computational costs.

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call