Abstract
With the development of high-resolution optical sensors, the classification of ground objects combined with multivariate optical sensors is a hot topic at present. Deep learning methods, such as convolutional neural networks, are applied to feature extraction and classification. In this work, a novel deep belief network (DBN) hyperspectral image classification method based on multivariate optical sensors and stacked by restricted Boltzmann machines is proposed. We introduced the DBN framework to classify spatial hyperspectral sensor data on the basis of DBN. Then, the improved method (combination of spectral and spatial information) was verified. After unsupervised pretraining and supervised fine-tuning, the DBN model could successfully learn features. Additionally, we added a logistic regression layer that could classify the hyperspectral images. Moreover, the proposed training method, which fuses spectral and spatial information, was tested over the Indian Pines and Pavia University datasets. The advantages of this method over traditional methods are as follows: (1) the network has deep structure and the ability of feature extraction is stronger than traditional classifiers; (2) experimental results indicate that our method outperforms traditional classification and other deep learning approaches.
Highlights
With the development of high-resolution optical sensors, hyperspectral remote sensing images are achieved, which consist of hundreds of different spectral bands of the same remote sensing scene.Hyperspectral remote images are essential tools for tasks such as target detection and classification because of these images’ advantage in describing ground truth information
The proposed training method, which fuses spectral and spatial information, was tested over the Indian Pines and Pavia University datasets. The advantages of this method over traditional methods are as follows: (1) the network has deep structure and the ability of feature extraction is stronger than traditional classifiers; (2) experimental results indicate that our method outperforms traditional classification and other deep learning approaches
An effective method using the TLCNN-restricted Boltzmann machine (RBM) model for a small sample of voiceprint recognition was provided by Reference [7]
Summary
With the development of high-resolution optical sensors, hyperspectral remote sensing images are achieved, which consist of hundreds of different spectral bands of the same remote sensing scene. Neural networks and support vector machines (SVMs) [2] are extensively used in hyperspectral classification because of their potential in handling high-dimension data They can manage most of the classification but cannot provide enriched information. An RBM and its learning algorithm can address the problems of deep neural networks, such as classification, regression, image feature extraction, and collaborative filtering. An effective method using the TLCNN-RBM (convolutional neural network mixed restricted Boltzmann machine based on transfer learning) model for a small sample of voiceprint recognition was provided by Reference [7]. The rest of this paper is organized as follows: in Section 2, the main ideas and the structure of the DBN are discussed in detail, and the proposed hyperspectral sensor data classification method is presented in combination with spectral information and the spatial context.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
