Semiconductor Optoelectronics, Volume. 46, Issue 3, 508(2025)
Hyperspectral Unmixing Network Combined with Overlapping Spectral Patch Embedding and Deep Convolution
The hyperspectral unmixing method, based on Transformer, divides a hyperspectral image into small patches of fixed size without overlapping. The divided patches are then fed as inputs into the Transformer encoder and unmixed by a decoder. However, non-overlapping patch division eliminates similar information between neighboring pixels. Furthermore, some local information is lost in the Transformer feedforward layer, which affects the unmixing effect. In this study, we adopt an improved hyperspectral unmixing method with overlapping spectral patch division and deep convolution in the fully connected layer of Transformer. Hyperspectral imaging experiments show that the unmixing effect achieved by the improved method is more pronounced than that of the original method.
Get Citation
Copy Citation Text
LI Shihui, YANG Huadong. Hyperspectral Unmixing Network Combined with Overlapping Spectral Patch Embedding and Deep Convolution[J]. Semiconductor Optoelectronics, 2025, 46(3): 508
Category:
Received: Feb. 19, 2025
Accepted: Sep. 18, 2025
Published Online: Sep. 18, 2025
The Author Email: