Abstract
Target detection and classification in the shadow area of hyperspectral images (HSIs) has always been an important problem in the field of HSI data processing. However, there are few methods to detect or classify targets in the shadow area effectively because of occlusion of objects or oblique solar radiation. Dynamic stochastic resonance (DSR) theory shows that under the synergistic action of weak input signal, noise and non-linear system, the energy of noise can be transferred into signal partially. It breaks the idea that signal can be enhanced only by eliminating noise and has been proved to be effective in many fields. In this paper, DSR is introduced into the shadow area enhancement of HSI from both spatial and spectral dimensions. Then, the enhanced HSI data can be obtained by fusing the processed shadow with the original HSI data. Finally, 2D convolutional neural networks (2D-CNN) is used to classify the enhanced HSI. To evaluate the proposed method, a real-world HSI has been processed in the experiment and the results show that DSR can improve the contrast and the spectral intensity of HSI shadow area. Compared to other state-of-the-art methods, the classification accuracy is better at containing different targets with small samples, especially in the spectral dimension.
Highlights
Based on the theory of electromagnetic wave, hyperspectral remote sensing technology provides abundant information of ground objects by accurately receiving and recording the complex interactions between electromagnetic wave and objects [1], so hyperspectral images (HSIs) containing both spatial and spectral information of objects can help to improve the classification and target detection [2]
The well-known dark-channel prior (DCP) image enhancement method is used to compare with Dynamic stochastic resonance (DSR) method and three widely used methods spectral angle mapping (SAM), support vector machine (SVM) and deep belief network (DBN) are selected to compare with 2D convolutional neural networks (2D-convolutional neural networks (CNN))
It means that the proposed method combining DSR and 2D-CNN has potential capability in the HSI information exploration of the shadow areas containing different targets with small samples
Summary
Based on the theory of electromagnetic wave, hyperspectral remote sensing technology provides abundant information of ground objects by accurately receiving and recording the complex interactions between electromagnetic wave and objects [1], so hyperspectral images (HSIs) containing both spatial and spectral information of objects can help to improve the classification and target detection [2]. Step 2: Because the hyperspectral data has both spatial and spectral characteristics, the 3D shadow areas extracted from the HSI could be enhanced from two perspectives of spatial and spectral dimensions. Step 3: A fusion mask contrary to the shadow extraction mask is used to fuse the enhanced shadow data with the original HSI, so that the HSIs with enhanced shadow areas could be acquired in spatial and spectral dimensions respectively. EXPERIMENT A real-world HYDICE (Hyperspectral Digital Imagery Collection Experiment) HSI data is processed to evaluate the performance of the proposed method The parameter of 2D-CNN would be adjusted according to the single variable principle to obtain superior classification performance [32]
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
