Shaoju Wang

Shaoju Wang

Auto-generated profile, based on publicly available information

Shaoju Wang

Wuhan University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2024 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
YGYuxuan Guo
Yuxuan Guo
XDXiaobing Dai
Xiaobing Dai
SWShaoju Wang
Shaoju Wang
GJGuang Jin
Guang Jin
XZXuemin Zhang
Xuemin Zhang
Polarization imaging beyond traditional imaging offers a wide range of advantages, encompassing not only the detection of geometric shapes and surfaces, but also the measurement of physical properties. The divided focal plane (DoFP), an ideal real-time imaging, comprises a 2 × 2 linear polarization filter overlaid on a focal plane array sensor. Consequently, performing polarization demosaicing (PDM) becomes crucial to restore the missing components in the pixel data. The objective of PDM extends beyond the acquisition of intensity, and its primary goal is to minimize the estimation error of polarization characteristics. However, existing demosaicing networks often neglect the issues of polarization spatial-intensity attention and are trained similarly for generalization, thereby failing to effectively distinguish between genuine details and artifacts, which renders demosaicing vulnerable to distortion. In this work, we propose a novel generative adversarial network framework that integrates attention mechanisms and progressive discrimination for polarimetric images. The GAN-based framework introduces a global attention mechanism that enhances the interaction between spatial and polarization intensity information across different regions, resulting in improved network performance. Additionally, the framework generates artifact maps to normalize the model training process. To evaluate the effectiveness of our method, we assess its performance using full-resolution polarimetric image and compare it against traditional and recent PDM methods. The experimental results demonstrate that our proposed method achieves the highest peak signal-to-noise ratio (PSNR) and exhibits excellent visual quality for the output Stokes images when compared to existing methods.

27 November 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
YKYingdong Kang
Yingdong Kang
XWXINYU WANG
XINYU WANG
XZXuemin Zhang
Xuemin Zhang
SWShaoju Wang
Shaoju Wang
GJGuang Jin
Guang Jin
Recently, Transformer-based methods have shown impressive performances in remote sensing image superresolution (RSISR). However, the application of Transformer in RSISR frequently results in artifacts and the loss of image detail due to limited information transmission pathways and the constraints of uni-dimensional self-attention mechanisms. To solve these problems, an Aggregation Connection Transformer (ACT-SR) is proposed for RSISR. ACT-SR employs an advanced attention mechanism designed to enrich information transmission across spatial and channel dimensions, thereby enlarging the receptive fields for more accurate feature extraction. A core component of ACT-SR is the novel aggregation connection attention block, which effectively captures spatial similarities and channel importance, aggregating this information through a combination of series and parallel connections for enhanced feature representation. Furthermore, a new gated feed-forward network is introduced to enhance the nonlinear mapping capabilities of the Transformer and control the information flow through the network. In addition, ACT-SR integrates a shifted windows scheme alongside interpolation residual calculation to facilitate efficient detail recovery and artifact elimination. Experimental results confirm the effectiveness of the proposed modules, with ACT-SR outperforming several state-of-the-art RSISR methods in both objective metrics and visual quality

13 February 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
YKYingdong Kang
Yingdong Kang
XZXuemin Zhang
Xuemin Zhang
SWShaoju Wang
Shaoju Wang
GJGuang Jin
Guang Jin
The quadratic increase in computational complexity caused by global receptive fields has been a persistent challenge when applying Transformer-based methods in remote sensing image super-resolution (RSISR), involving high-resolution images. Channel attention (CA)-based Transformers offer an efficient approach with linear complexity by computing self-attention across the channel dimension. However, current CA-based Transformers suffer from performance degradation due to two main issues: constrained receptive field in the channel dimension caused by the multihead strategy and insufficient feature diversity resulting from the small size of attention matrices. To address these drawbacks, a novel shift channel attention Transformer (SCAT) is proposed for RSISR in this article. The core innovation of SCAT lies in its shift channel attention block (SCAB), which expands the receptive field by facilitating cross-head communication through a shift channel strategy. This design enables parallel computation of self-attention across multiple heads while ensuring robust cross-channel connections, thereby enhancing the global context modeling capabilities of the network. In addition, an attention supplementation module using depthwise convolution (DWC) is incorporated into SCAB to improve feature diversity. Finally, the proposed gated feedforward network utilizes the gating mechanism and DWC to effectively control the information flow and extract complementary spatial details. In the experiments, the effectiveness of these proposed modules is verified, and the SCAT model demonstrated superior performance in terms of quantitative and qualitative compared to several state-of-the-art RSISR methods.

24 March 2025 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ZLZijian Li
Zijian Li
Mi WangMi Wang
Mi Wang
SWShaoju Wang
Shaoju Wang
Band selection is an effective dimensionality reduction technique for hyperspectral image (HSI). In recent years, many unsupervised band selection methods have been proposed, but most of them measure the similarity between bands only from the spectral dimension, ignoring their high spatial correlation. In addition, these methods provide a less than ideal quantitative description of spectral information and neglect the redundancy within the selected bands. To address these issues, we propose a hyperspectral band selection via structural correlation and information measures (SCIM), claiming the following contributions: 1) through introducing the structural similarity (SSIM) index to assess the correlation between bands, both spectral and spatial information are considered; 2) the HSI cube is partitioned into several groups by considering both intragroup and intergroup similarity measured by SSIM; 3) in order to obtain a high quality band subset, a representative band is selected in each group from the point of view of information as well as redundancy. The experimental results on three HSI data sets show that the proposed method has significant advantages compared with competitors.

2 December 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SZSiqing Zhang
Siqing Zhang
KRKeyi Rao
Keyi Rao
ZWZhaocong Wu
Zhaocong Wu
SWShaoju Wang
Shaoju Wang
ZDZhixiong Dai
Zhixiong Dai
KWKexin Wang
Kexin Wang
On-orbit radiometric calibration is essential for the quantitative use of hyperspectral satellite and sensor monitoring, but its frequency is constrained by available calibration sites, especially for microsatellites with limited imaging capabilities. To reduce dependence on specific sites for on-orbit radiometric calibration, this article introduces a cross-calibration method that uses spectral homogeneity factor (SpecHF) to select targets in open fields. Initially, utilizing hyperspectral images from the advanced hyperspectral imager on board the Gaofen-5B satellite, we developed the SpecHF and selected calibration targets in the Ulanbuh Desert, Inner Mongolia, China. Then, the cross-calibration of the Compact Continuous Tunable LVF-based Hyperspectral Imager on board the microsatellite QMX-1 and the well-calibrated orbita hyperspectral sensor carried by the Zhuhai-1 satellite was performed on 10 September 2022. The intrinsic offsets between two sensors caused by spectral response functions (SRFs) mismatches were compensated using the spectral band adjustment factor, which accounts for the target's spectral profile and the SRF of both sensors. The comparison of the cross-calibrated top-of-atmosphere reflectance from Q1C with datasets from the radiometric calibration network revealed high consistency, with a root-mean-square error of 0.032. Additionally, a ground simultaneous validation conducted in Wuxi, China, on 31 December 2022, demonstrated the high accuracy and effective performance of the cross-calibration results in real-world settings, achieving an average MAE of 0.009. The results show that SpecHF-selected spectral homogeneous targets are well-suited for on-orbit radiometric cross-calibration. By overcoming site limitations, this method provides a viable solution for facilitating the flexibility of on-orbit calibration.

22 January 2025 in Geo-spatial Information Science
Verified
Journal Article
Open access
DCDong Chen
Dong Chen
SWShaoju Wang
Shaoju Wang
CWChao Wang
Chao Wang
XIANG ZHANGXIANG ZHANG
XIANG ZHANG
NCNengcheng Chen
Nengcheng Chen