Liyan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liyan Zhang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Rumei Li
College of Resource Environment and Tourism, Capital Normal University, No. 105, North Road of West 3rd Ring, Beijing 100048, China
2 shared publications - Zun Wang
College of Resource Environment and Tourism, Capital Normal University, No. 105, North Road of West 3rd Ring, Beijing 100048, China
2 shared publications - Da-Qi Xu1 shared publication
- Jing Feng
Capital Normal University, College of Resource Environment and Tourism, Key Laboratory of 3D Informa
1 shared publication - Jun Lin1 shared publication
- Sui-Xian Li
Flying College, Binzhou University, Binzhou 256600, China
1 shared publication
Latest Publications
- Open Access
FCSwinU: Fourier Convolutions and Swin Transformer UNet for Hyperspectral and Multispectral Image Fusion
The fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) provides a cost-effective approach to obtaining high-resolution hyperspectral images (HR-HSI). Existing methods primarily based on convolutional neural networks (CNNs) struggle to capture global features and do not adequately address the significant scale and spectral resolution differences between LR-HSI and HR-MSI. To tackle these challenges, our novel FCSwinU network leverages the spectral fast Fourier convolution (SFFC) module for spectral feature extraction and utilizes the Swin Transformer’s self-attention mechanism for multi-scale global feature fusion. FCSwinU employs a UNet-like encoder–decoder framework to effectively merge spatiospectral features. The encoder integrates the Swin Transformer feature abstraction module (SwinTFAM) to encode pixel correlations and perform multi-scale transformations, facilitating the adaptive fusion of hyperspectral and multispectral data. The decoder then employs the Swin Transformer feature reconstruction module (SwinTFRM) to reconstruct the fused features, restoring the original image dimensions and ensuring the precise recovery of spatial and spectral details. Experimental results from three benchmark datasets and a real-world dataset robustly validate the superior performance of our method in both visual representation and quantitative assessment compared to existing fusion methods.
Open AccessFCSwinU: Fourier Convolutions and Swin Transformer UNet for Hyperspectral and Multispectral Image Fusion
The fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) provides a cost-effective approach to obtaining high-resolution hyperspectral images (HR-HSI). Existing methods primarily based on convolutional neural networks (CNNs) struggle to capture global features and do not adequately address the significant scale and spectral resolution differences between LR-HSI and HR-MSI. To tackle these challenges, our novel FCSwinU network leverages the spectral fast Fourier convolution (SFFC) module for spectral feature extraction and utilizes the Swin Transformer’s self-attention mechanism for multi-scale global feature fusion. FCSwinU employs a UNet-like encoder–decoder framework to effectively merge spatiospectral features. The encoder integrates the Swin Transformer feature abstraction module (SwinTFAM) to encode pixel correlations and perform multi-scale transformations, facilitating the adaptive fusion of hyperspectral and multispectral data. The decoder then employs the Swin Transformer feature reconstruction module (SwinTFRM) to reconstruct the fused features, restoring the original image dimensions and ensuring the precise recovery of spatial and spectral details. Experimental results from three benchmark datasets and a real-world dataset robustly validate the superior performance of our method in both visual representation and quantitative assessment compared to existing fusion methods.
- Open Access
- 22 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 15122-15135
MIMFormer: Multiscale Inception Mixer Transformer for Hyperspectral and Multispectral Image Fusion
The fusion of low-spatial-resolution hyperspectral image (LR-HSI) and high-spatial-resolution multispectral image (HR-MSI) provides an effective method to obtain high-spatial-resolution hyperspectral image (HR-HSI). However, existing hybrid fusion architectures combining Convolutional Neural Networks (CNNs) and Transformers face significant challenges. Sequential approaches struggle with simultaneous local and global modeling, while parallel approaches often result in information redundancy. In this paper, to meet diverse information demands at different layers, we propose a novel Multiscale Inception Mixer Transformer network (MIMFormer), a multiscale hybrid network based on the Inception structure integrating CNN and Transformer. The core of this network is the Multiscale Spatial Transformer (MST) structure, which enhances the detail richness of fused images by integrating local and global information at various scales. The Inception Spatial-spectral Mixer (ISSM) module within the MST leverages an Inception architecture and employs a spectral splitting mechanism to regulate spectral channel counts across different branches. This design allows the ISSM module to efficiently extract local spatial-spectral features through convolution and max pooling, while global features are captured using a self-attention mechanism, ensuring comprehensive feature fusion across spectral groups. Experimental results on three benchmark datasets and one real remote sensing dataset demonstrate that MIMFormer outperforms ten advanced fusion methods. The source code is publicly available at https://github.com/meiruni/MIMFormer .
- 22 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 15122-15135
Open AccessMIMFormer: Multiscale Inception Mixer Transformer for Hyperspectral and Multispectral Image Fusion
The fusion of low-spatial-resolution hyperspectral image (LR-HSI) and high-spatial-resolution multispectral image (HR-MSI) provides an effective method to obtain high-spatial-resolution hyperspectral image (HR-HSI). However, existing hybrid fusion architectures combining Convolutional Neural Networks (CNNs) and Transformers face significant challenges. Sequential approaches struggle with simultaneous local and global modeling, while parallel approaches often result in information redundancy. In this paper, to meet diverse information demands at different layers, we propose a novel Multiscale Inception Mixer Transformer network (MIMFormer), a multiscale hybrid network based on the Inception structure integrating CNN and Transformer. The core of this network is the Multiscale Spatial Transformer (MST) structure, which enhances the detail richness of fused images by integrating local and global information at various scales. The Inception Spatial-spectral Mixer (ISSM) module within the MST leverages an Inception architecture and employs a spectral splitting mechanism to regulate spectral channel counts across different branches. This design allows the ISSM module to efficiently extract local spatial-spectral features through convolution and max pooling, while global features are captured using a self-attention mechanism, ensuring comprehensive feature fusion across spectral groups. Experimental results on three benchmark datasets and one real remote sensing dataset demonstrate that MIMFormer outperforms ten advanced fusion methods. The source code is publicly available at https://github.com/meiruni/MIMFormer .
- Open Access
- 1 July 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 15 (03) , 038507-13
Hyperspectral anomaly detection based on autoencoder and spatial morphology extraction
Anomaly detection (AD) is a crucial task for detecting salient objects in cluttered backgrounds. Classical AD algorithms based on statistical models or geometric models have achieved acceptable detection results. However, most of them do not hierarchically extract deep features or consider the spatial structure of the images. We propose a method that combines the reconstruction error of autoencoder (AE) and spatial morphological characteristics to estimate anomalousness. The reconstruction errors and the spatially dominant information are comprehensively considered. Specifically, given the compression capability of the AE, we use the dimensionality reduction results obtained by encoding for analyzing local pixel difference; an adaptive dual window is employed in this process. The morphological transformation commonly used in edge detection is utilized to refine the small space anomalies. Experimental results on different hyperspectral images show that the proposed AE and spatial morphology extraction-based approach significantly surpasses several traditional alternatives.
- 1 July 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 15 (03) , 038507-13
Open AccessHyperspectral anomaly detection based on autoencoder and spatial morphology extraction
Anomaly detection (AD) is a crucial task for detecting salient objects in cluttered backgrounds. Classical AD algorithms based on statistical models or geometric models have achieved acceptable detection results. However, most of them do not hierarchically extract deep features or consider the spatial structure of the images. We propose a method that combines the reconstruction error of autoencoder (AE) and spatial morphological characteristics to estimate anomalousness. The reconstruction errors and the spatially dominant information are comprehensively considered. Specifically, given the compression capability of the AE, we use the dimensionality reduction results obtained by encoding for analyzing local pixel difference; an adaptive dual window is employed in this process. The morphological transformation commonly used in edge detection is utilized to refine the small space anomalies. Experimental results on different hyperspectral images show that the proposed AE and spatial morphology extraction-based approach significantly surpasses several traditional alternatives.
- Open Access
- 29 November 2017
- Published by MDPI AG in Preprints.org
Filter Selection for Optimizing Spectral Sensitivity of Broadband Multispectral Camera Based on Maximum Linear Independence
Previous research has shown that the effectiveness of selecting filter set from a large set of commercial broadband filters by vector analyzing method based on maximum linear independence (MLI). However, the traditional MLI is suboptimal due to predefining the first filter of the selected filter set being the maximum ℓ2 norm among all those of the filters. An exhaustive imaging simulation is conducted to investigate the features of the most competent filter set. In the simulation, every filter in a subset of all the filters is selected serving as the first filter in turn. From the results of the simulation, we found there are remarkable characteristics for the most competent filter set. Besides smaller condition number, the geometric features of the best-performed filter set comprise the distinct peak of the transmittance of the first filter, the generally uniform distributing of the peaks of the transmittance curve of the filters, the substantial overlapping of the transmittance curves with those of the adjacent filer sets. Therefore, the best-performed filter sets can be decided intuitively by simple vector analyzing and just a few experimental verifications. This work would be useful for optimizing spectral sensitivity of broadband multispectral imaging sensors or SFA sensors.
- 29 November 2017
- Published by MDPI AG in Preprints.org
Open AccessFilter Selection for Optimizing Spectral Sensitivity of Broadband Multispectral Camera Based on Maximum Linear Independence
Previous research has shown that the effectiveness of selecting filter set from a large set of commercial broadband filters by vector analyzing method based on maximum linear independence (MLI). However, the traditional MLI is suboptimal due to predefining the first filter of the selected filter set being the maximum ℓ2 norm among all those of the filters. An exhaustive imaging simulation is conducted to investigate the features of the most competent filter set. In the simulation, every filter in a subset of all the filters is selected serving as the first filter in turn. From the results of the simulation, we found there are remarkable characteristics for the most competent filter set. Besides smaller condition number, the geometric features of the best-performed filter set comprise the distinct peak of the transmittance of the first filter, the generally uniform distributing of the peaks of the transmittance curve of the filters, the substantial overlapping of the transmittance curves with those of the adjacent filer sets. Therefore, the best-performed filter sets can be decided intuitively by simple vector analyzing and just a few experimental verifications. This work would be useful for optimizing spectral sensitivity of broadband multispectral imaging sensors or SFA sensors.