Abstract
In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).
Highlights
A hyperspectral image presents a target region in a spectrum of continuous and narrow bands, containing both spatial and spectral feature information at a pixel-level resolution [1].Hyperspectral imagery is widely used in various applications such as urban planning, agricultural development, and environmental testing [2]
Hyperspectral images are prone to the Hughes phenomenon due to the complexity of their structure and suffer from a small number of labeled samples affecting the overall performance of hyperspectral image classification
This paper proposes a multi-scale residual convolutional neural network that integrates an attention mechanism, embeds the lightweight and improved channel attention mechanism proposed by Wang et al [30], i.e., the efficient channel attention network (ECA-NET), and uses local cross-channel interaction without dimensionality reduction
Summary
A hyperspectral image presents a target region in a spectrum of continuous and narrow bands, containing both spatial and spectral feature information at a pixel-level resolution [1]. To extract better spatial and spectral features, [16,17,18] use 3D convolution to extract hyperspectral image features, and [19,20,21] fuse a residual with an attention deep network Methods such as attention mechanism [22] and joint space–spectral features [23] that improve the convolutional neural network classification accuracy and increase the number of the network parameters have been used. This paper proposes a multi-scale residual convolutional neural network that integrates an attention mechanism, embeds the lightweight and improved channel attention mechanism proposed by Wang et al [30], i.e., the efficient channel attention network (ECA-NET), and uses local cross-channel interaction without dimensionality reduction This strategy, through the adaptive one-dimensional convolution, effectively extracts the spatial and spectral features of the image and reduces the redundancy of the training sample information.
Sign-in/Register to view highlights & summary 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.
