Objective

2

Hyperspectral images （HSIs） provide rich spectral and spatial information， which is essential for a wide range of applications， including disaster assessment， resource management， and land surveys. The rich data content of HSIs allows for the detailed analysis of various materials and surfaces， making them invaluable in monitoring environmental changes， assessing natural disasters， and managing agricultural resources. However， the application of HSIs in change detection tasks is often hindered by several challenges， primarily due to the presence of various types of noise. HSIs are particularly susceptible to Gaussian noise， which is typically introduced during the image acquisition process due to sensor limitations and environmental conditions. This type of noise can obscure the spectral signatures of materials， making it difficult to accurately detect changes over time. Additionally， striping noise， which occurs due to inconsistencies in the sensor response across different spectral bands， further complicates the interpretation of HSIs. These noise types can significantly degrade the quality of the data， leading to less reliable change detection results. Given these challenges， there is a pressing need for advanced methods that can effectively mitigate the impact of noise and enhance the accuracy of change detection in HSIs. Traditional methods often fall short in addressing the intricate balance between preserving local details and capturing global context， both of which are crucial for accurate change detection. This is particularly challenging in complex and variable environments where the nature of changes can be subtle and distributed across different spatial and spectral dimensions.

Method

2

To address these issues， this paper proposes a novel hyperspectral image change detection method based on hybrid attention and bidirectional gated networks. The proposed method integrates local and global features by enhancing the self-attention mechanism and feedforward neural network in the Transformer architecture. Specifically， a hybrid attention module （HAM） is introduced， which employs parallel structures of Convolutional Neural Networks （CNN） and MLP layers with gating （gMLP） to extract local features and global contextual information， respectively. CNNs are particularly effective at identifying fine details and local patterns in the spatial domain， which are crucial for detecting subtle changes in hyperspectral images. By using convolutional layers， the HAM can efficiently extract and represent local information. gMLP layers with gating mechanisms are adept at modeling long-range dependencies and global interactions within the data. This allows the HAM to balance the detailed local information extracted by the CNNs with a broader， global perspective， ensuring that the overall feature representation is comprehensive and robust against noise. This dual approach effectively balances the extraction of fine local details and broad global context， thereby reducing the impact of noise and enhancing feature representation. Additionally， a bidirectional gated network （BGFN） is constructed to further improve feature extraction and integration. The BGFN is designed to enhance feature extraction and integration across both channel and spatial dimensions， providing a more holistic understanding of the hyperspectral data. The BGFN leverages a bidirectional gating mechanism to selectively emphasize relevant features while suppressing irrelevant ones. This selective emphasis is crucial for dealing with the noise inherent in HSIs， as it allows the network to focus on the most informative and significant features， improving the accuracy of change detection. By enhancing interactions across both channel and spatial dimensions， the BGFN ensures that the extracted features are well-integrated and representative of the underlying data. This comprehensive fusion of local and global information is key to achieving deep integration of multi-temporal hyperspectral image features， enabling more accurate and reliable change detection.

Result

2

Extensive experiments were conducted on three hyperspectral datasets： Framland， Hermiston， and River dataset. The proposed method was compared with six mainstream methods， including BiT and CBANet， to evaluate its performance in terms of accuracy and Kappa coefficient. On the River dataset， HBFormer achieves a reduction in False Positive （FP）， False Negative （FN）， and Overall Error （OE）， an improvement of 0.13% in accuracy， and an improvement of 0.77% in Kappa coefficient compared to CBANet. On the Farmland dataset， HBFormer achieves the lowest False Alarm Number （FP）， with 0.34% improvement in accuracy and 2.02% improvement in Kappa coefficient over BiT， while on the Hermiston dataset， HBFormer achieves the lowest FP and OE， with 1% and 2.08% improvement in accuracy and Kappa coefficient over CBANet， respectively. The accuracy and Kappa coefficient are improved by 1% and 2.08% respectively over CBANet. Ablation experiments were also conducted to assess the contribution of each component of the proposed method. The results demonstrated that both the hybrid attention module and the bidirectional gated network play crucial roles in enhancing change detection accuracy by effectively integrating local and global information. The proposed method consistently outperformed the mainstream methods across all datasets， showcasing its superior capability in handling noise and providing accurate change detection. The results underline the importance of integrating local and global features and highlight the robustness of the hybrid attention and bidirectional gated network approach.

Conclusion

2

The comprehensive experiments on three hyperspectral datasets validate the efficacy of the proposed method in change detection tasks. The hybrid attention and bidirectional gated network approach not only enhances accuracy and robustness but also offers a scalable solution for various hyperspectral image analysis applications. The overarching goal of this research is to enhance the performance of change detection in HSIs， making it more accurate and reliable even under complex and variable conditions. The method's ability to effectively fuse local and global features results in improved accuracy and resilience to noise， making it a valuable tool for remote sensing tasks. The significant performance gains over current mainstream methods such as BiT and CBANet underscore the method's potential for practical deployment in real-world scenarios. Furthermore， the study opens avenues for future research to explore the application of this method across diverse datasets and environments. Enhancing the generalization capabilities of the proposed method could lead to even broader applicability and stronger support for real-world remote sensing tasks. In conclusion， the proposed hyperspectral image change detection method based on hybrid attention and bidirectional gated networks presents a significant advancement in the field. It addresses the challenges posed by noise and the need for robust feature integration， providing a reliable and effective solution for complex and variable environments. The promising results and potential for further improvements make this method a valuable contribution to hyperspectral image analysis and remote sensing.