A5102788843- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Advanced Image Fusion Techniques
Lanzhou Jiaotong University
2023-2024
Gansu Academy of Sciences
2023
With the powerful discriminative capabilities of convolutional neural networks, change detection has achieved significant success. However, current methods either ignore spatiotemporal dependencies between dual-temporal images or suffer from decreased accuracy due to registration errors. Addressing these challenges, this paper proposes a method for remote sensing image based on cross-mixing attention network. To minimize impact errors results, feature alignment module (FAM) is specifically...
With the increase of spatial resolution remote sensing images, features feature imaging become more and complex, change detection methods based on techniques such as texture representation local semantics are difficult to meet demand. Most usually focus extracting semantic ignore importance high-resolution shallow information fine-grained features, which often lead uncertainty in edge small target detection. For single-input networks when two temporal images connected, layer network cannot...
Abstract Change detection is a crucial undertaking in the field of remote sensing. Current change methods tend to emphasize modelling difference features, ignoring alignment error dual-temporal images and spatio-temporal relationship between images, which affects recognition ability features makes it difficult distinguish real region. Aiming at above problems, this paper proposes sensing image method based on cross mixing attention network. The employs feature module obtain correction...