Unmixing-Guided Convolutional Transformer for Spectral Reconstruction
نویسندگان
چکیده
Deep learning networks based on CNNs or transformers have made progress in spectral reconstruction (SR). However, many methods focus solely feature extraction, overlooking the interpretability of network design. Additionally, models exclusively may lose other prior information, sacrificing accuracy and robustness. In this paper, we propose a novel Unmixing-Guided Convolutional Transformer Network (UGCT) for interpretable SR. Specifically, transformer ResBlock components are embedded Paralleled-Residual Multi-Head Self-Attention (PMSA) to facilitate fine extraction guided by excellent priors local non-local information from transformers. Furthermore, Spectral–Spatial Aggregation Module (S2AM) combines advantages geometric invariance global receptive fields enhance performance. Finally, exploit hyperspectral unmixing (HU) mechanism-driven framework at end model, incorporating detailed features library using LMM employing precise endmember achieve more refined interpretation mixed pixels HSI sub-pixel scales. Experimental results demonstrate superiority our proposed UGCT, especially grss_d f c_2018 dataset, which UGCT attains an RMSE 0.0866, outperforming comparative methods.
منابع مشابه
Spectral Unmixing for Information Extraction
“From pixels to processes” – this the shortest and most essential formulation of all studies, experiments and investigations carried out in the field of Earth remote sensing observations. This formulation reveals two main directions of data interpretation: the first related to classification and feature retrieval, and the second associated with multi-temporal aspects of remotely sensed data and...
متن کاملHyperspectral Super-Resolution with Spectral Unmixing Constraints
Hyperspectral sensors capture a portion of the visible and near-infrared spectrum with many narrow spectral bands. This makes it possible to better discriminate objects based on their reflectance spectra and to derive more detailed object properties. For technical reasons, the high spectral resolution comes at the cost of lower spatial resolution. To mitigate that problem, one may combine such ...
متن کاملUnmixing and target recognition in hyper - spectral
4 We present two new linear algorithms that perform unmixing in hyper-spectral 5 images and then recognize their targets whose spectral signatures are given. The 6 first algorithm is based on the ordered topology of spectral signatures. The second 7 algorithm is based on a linear decomposition in each pixel’s neighborhood. The sought 8 after target can occupy subor above pixel. These algorithms...
متن کاملSpectral Unmixing Datasets with Ground Truths
Hyperspectral unmixing (HU) is a very useful and increasingly popular preprocessing step for a wide range of hyperspectral applications. However, the HU research has been constrained a lot by three factors: (a) the number of hyperspectral images (especially the ones with ground truths) are very limited; (b) the ground truths of most hyperspectral images are not shared on the web, which may caus...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2023
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs15102619