WCWei Cui

Wei Cui

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei Cui has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PCACNet: A Physics-Constrained Deep Atmospheric Correction Network with Differentiable Radiative Transfer Closure for Multispectral Optical Imagery

    by Gang Li, Li Yan, Hong Xie, Wei Cui, Jianbing Yang, Jiang Song

    Atmospheric correction of multispectral optical remote-sensing imagery aims to recover surface reflectance from top-of-atmosphere (TOA) observations and serves as a fundamental preprocessing step for quantitative remote-sensing applications. Existing deep-learning approaches generally formulate the conversion from TOA to bottom-of-atmosphere (BOA) reflectance as one-way supervised regression, without explicitly enforcing radiative-transfer consistency between the predicted BOA and original TOA observations. We propose the Physics-Constrained Deep Atmospheric Correction Network (PCACNet), which incorporates differentiable radiative-transfer closure into deep learning-based atmospheric correction. A large paired TOA-BOA simulation database with realistic spectral priors is first generated by driving the 6S radiative transfer model with real BOA spectra. A frozen but differentiable radiative transfer model emulator is subsequently incorporated into the training framework to establish a TOA–BOA–TOA differentiable radiative-transfer closure loop. PCACNet further employs separate encoders for spectral, atmospheric, and observation geometry, and an uncertainty-aware progressive learning strategy with reliability weighting based on TOA reconstruction residuals. On an independent simulated test set, PCACNet reduced BOA inversion RMSE and TOA reconstruction RMSE by 50.6% and 43.3%, respectively, relative to the best-performing comparison method, SAAC-Net. Evaluation on real Sentinel-2 imagery further supported the spatial and temporal transferability of PCACNet across the examined regions and acquisition periods, as demonstrated by consistent agreement with Sen2Cor-derived L2A products in spatial patterns, spectral characteristics, and remote-sensing indices. These findings support the effectiveness of the proposed physics-constrained framework under controlled simulation conditions and its applicability to real Sentinel-2 observations.

  • Open Access

    ViTrans: Inter-Frame Alignment Enhancement for Moving Vehicle Detection in Satellite Videos with Stabilization Offsets

    by Tao He, Kaimin Sun, Yu Duan, Wei Cui, Ziang Wang, Song Gao, Yuan Yao, Zijie Chen

    Satellite videos typically employ image registration techniques for video stabilization in order to achieve persistent observation. However, existing methods largely neglect the residual stabilization offsets, particularly when exceeding the physical dimensions of target vehicles, which inevitably causes performance degradation. Furthermore, the detection pipeline struggles with hard-to-discriminate samples that exhibit low contrast, motion blur, or occlusion, while conventional sample assignment strategies fail to address the inherent annotation ambiguity for extremely small objects. We propose an end-to-end method called ViTrans for detecting moving vehicles in satellite video under stabilization offsets. ViTrans consists of three core modules: (1) a feature-aligned stabilization offset correction module (SCM) that mitigates feature misalignment by aligning features between the reference frame and the current frame; (2) a feature adaptive aggregation enhancement module (AAEM) based on vehicle trajectory consistency, which leverages the motion characteristics of objects across consecutive frames to eliminate dynamic clutter and false-alarm artifacts; and (3) a Gaussian distribution-based metric that dynamically adapts to bounding box dimensions, thereby providing more accurate positive sample feedback during model training. Extensive experiments on the VISO and SDM-Car datasets under simulated stabilization offsets demonstrate that ViTrans achieves state-of-the-art performance, improving F1-score by 14.4% on VISO and 6.9% on SDM-Car over existing methods.


  • Open Access

    Cross-Visual Style Change Detection for Remote Sensing Images via Representation Consistency Deep Supervised Learning

    by Jinjiang Wei, Kaimin Sun, Wenzhuo Li, Wangbin Li, Song Gao, Shunxia Miao, Yingjiao Tan, Wei Cui, Yu Duan

    Change detection techniques, which extract different regions of interest from bi-temporal remote sensing images, play a crucial role in various fields such as environmental protection, damage assessment, and urban planning. However, visual style interferences stemming from varying acquisition times, such as radiation, weather, and phenology changes, often lead to false detections. Existing methods struggle to robustly measure background similarity in the presence of such discrepancies and lack quantitative validation for assessing their effectiveness. To address these limitations, we propose Representation Consistency Change Detection (RCCD), a novel deep learning framework that enforces global style and local spatial consistency of features across encoding and decoding stages for robust cross-visual style change detection. RCCD leverages large-kernel convolutional supervision for local spatial context awareness and global content-aware style transfer for feature harmonization, effectively suppressing interference from background variations. Extensive evaluations on S2Looking and LEVIR-CD+ datasets demonstrate RCCD’s superior performance, achieving state-of-the-art F1-scores. Furthermore, on dedicated subsets with large visual style differences, RCCD exhibits more substantial improvements, highlighting its effectiveness in mitigating interference caused by visual style errors. The code has been open-sourced on GitHub.


  • Open Access

    STFNet: A Spatiotemporal Fusion Network for Forest Change Detection Using Multi-Source Satellite Images

    by Yingjiao Tan, Kaimin Sun, Jinjiang Wei, Song Gao, Wei Cui, Yu Duan, Junyi Liu, Wanghui Zhou

    Forest resources have important ecological and environmental values, and monitoring forest changes using remote sensing images is essential for resource management and ecological protection. However, current forest change detection methods fail to simultaneously integrate fine spatial information with temporal dynamic data, making them susceptible to pseudo changes induced by seasonal factors. In this paper, we propose a forest change detection method called STFNet that integrates multi-source spatiotemporal information. By combining fine spatial details of high-resolution images with dynamic information from time-series images, STFNet enhances the accuracy of forest change detection, alleviating the problem of information fusion difficulties caused by inconsistent granularity in spatiotemporal spectral features from different sources. In STFNet, we propose a cross-attention-based temporal differential feature fusion module (CATFF) to capture spatiotemporal dependencies within time-series images and a multiresolution contextual differential feature fusion module (MCDF) to achieve efficient spatial contexture fusion across multiresolution images. To validate our method, we conduct experiments using Gaofen and Sentinel-2 satellite images. Experimental results demonstrate that STFNet achieves excellent performance with an F1-score of 87.65%, outperforming state-of-the-art methods by at least 2.02%. Our ablation study further confirms the effectiveness of our method in leveraging time-series information to detect forest changes and suppress seasonal interference.